Compare commits

...

1280 Commits

Author SHA1 Message Date
jmorganca
201a987ff9 some more menu options... 2024-04-28 12:40:52 -04:00
jmorganca
2d8125042a Touch ID for cli install; server restarts 2024-04-27 22:42:38 -04:00
jmorganca
776e7bb5e4 app: fix status item icons 2024-04-27 15:57:57 -04:00
jmorganca
b8d7ca1a7b Native implementation of macOS app 2024-04-27 14:20:10 -04:00
Blake Mizerany
2bed62926e types/model: remove Digest (for now) (#3970)
The Digest type needs more thought and is not necessary at the moment.
2024-04-26 21:14:28 -07:00
Jeffrey Morgan
aad8d128a0 also look at cwd as a root for windows runners (#3959) 2024-04-26 19:14:08 -04:00
Daniel Hiltgen
ec1acbb867 Merge pull request #3968 from dhiltgen/win_generate
Fine grain control over windows generate steps
2024-04-26 16:03:38 -07:00
Daniel Hiltgen
e4859c4563 Fine grain control over windows generate steps
This will speed up CI which already tries to only build static for unit tests
2024-04-26 15:49:46 -07:00
Nataly Merezhuk
8e30eb26bd Updates the setup command to use llama3. (#3962) 2024-04-26 18:41:01 -04:00
Daniel Hiltgen
0b5c589ca2 Merge pull request #3966 from dhiltgen/bump
Fix target in gen_windows.ps1
2024-04-26 15:36:53 -07:00
Michael Yang
65fadddc85 Merge pull request #3964 from ollama/mxyng/weights
fix gemma, command-r layer weights
2024-04-26 15:23:33 -07:00
Daniel Hiltgen
ed5fb088c4 Fix target in gen_windows.ps1 2024-04-26 15:10:42 -07:00
Michael Yang
f81f308118 fix gemma, command-r layer weights 2024-04-26 15:00:55 -07:00
Blake Mizerany
b1390a7b37 types/model: export ParseNameBare and Merge (#3957)
These are useful outside this package.
2024-04-26 14:58:07 -07:00
Michael Yang
11d83386a5 Merge pull request #3951 from ollama/mxyng/zip
check file type before zip
2024-04-26 14:51:23 -07:00
Jeffrey Morgan
bb31def011 return code 499 when user cancels request while a model is loading (#3955) 2024-04-26 17:38:29 -04:00
Michael Yang
41e03ede95 check file type before zip 2024-04-26 14:18:07 -07:00
Michael Yang
7fea1ecdf6 Merge pull request #3958 from ollama/mxyng/fix-workflow
use merge base for diff-tree
2024-04-26 14:17:56 -07:00
Blake Mizerany
054894271d .github/workflows/test.yaml: add in-flight cancellations on new push (#3956)
Also, remove a superfluous 'go get'
2024-04-26 13:54:24 -07:00
Michael Yang
6fef042f0b use merge base for diff-tree 2024-04-26 13:54:15 -07:00
Daniel Hiltgen
5c0c2d1d09 Merge pull request #3954 from dhiltgen/ci_fixes
Put back non-avx CPU build for windows
2024-04-26 13:09:03 -07:00
Blake Mizerany
37f9c8ad99 types/model: overhaul Name and Digest types (#3924) 2024-04-26 13:08:32 -07:00
Quinten van Buul
2a80f55e2a Update windows.md (#3855)
Fixed a typo
2024-04-26 16:04:15 -04:00
Daniel Hiltgen
421c878a2d Put back non-avx CPU build for windows 2024-04-26 12:44:07 -07:00
Daniel Hiltgen
36666c2142 Merge pull request #3925 from dhiltgen/bump
Bump llama.cpp to b2737
2024-04-26 10:09:38 -07:00
Daniel Hiltgen
85801317d1 Fix clip log import 2024-04-26 09:43:46 -07:00
Daniel Hiltgen
2ed0d65948 Bump llama.cpp to b2737 2024-04-26 09:43:28 -07:00
Daniel Hiltgen
d459dc4ad1 Merge pull request #3950 from dhiltgen/windows_packaging
Fix exe name for zip packaging on windows
2024-04-26 09:27:37 -07:00
Daniel Hiltgen
40bc4622ef Fix exe name for zip packaging on windows
The zip file encodes the OS and architecture, so keep the short exe name
2024-04-26 09:18:05 -07:00
Daniel Hiltgen
c0f818a07a Merge pull request #3948 from dhiltgen/win_generate
Refactor windows generate for more modular usage
2024-04-26 09:17:20 -07:00
Daniel Hiltgen
8671fdeda6 Refactor windows generate for more modular usage 2024-04-26 08:35:50 -07:00
Daniel Hiltgen
2619850fb4 Merge pull request #3933 from dhiltgen/ci_fixes
Move cuda/rocm dependency gathering into generate script
2024-04-26 07:01:24 -07:00
Daniel Hiltgen
8feb97dc0d Move cuda/rocm dependency gathering into generate script
This will make it simpler for CI to accumulate artifacts from prior steps
2024-04-25 22:38:44 -07:00
Daniel Hiltgen
4e1ff6dcbb Merge pull request #3926 from dhiltgen/ci_fixes
Fix release CI
2024-04-25 17:42:31 -07:00
Daniel Hiltgen
8589d752ac Fix release CI
download-artifact path was being used incorrectly.  It is where to
extract the zip not the files in the zip to extract.  Default is
workspace dir which is what we want, so omit it
2024-04-25 17:27:11 -07:00
Michael Yang
de4ded68b0 Merge pull request #3923 from ollama/mxyng/mem
only count output tensors
2024-04-25 16:34:17 -07:00
Daniel Hiltgen
9b5a3c5991 Merge pull request #3914 from dhiltgen/mac_perf
Improve mac parallel performance
2024-04-25 16:28:31 -07:00
Jeffrey Morgan
00b0699c75 Reload model if num_gpu changes (#3920)
* reload model if `num_gpu` changes

* dont reload on -1

* fix tests
2024-04-25 19:02:40 -04:00
Jeffrey Morgan
993cf8bf55 llm: limit generation to 10x context size to avoid run on generations (#3918)
* llm: limit generation to 10x context size to avoid run on generations

* add comment

* simplify condition statement
2024-04-25 19:02:30 -04:00
Michael Yang
7bb7cb8a60 only count output tensors 2024-04-25 15:24:08 -07:00
Daniel Hiltgen
b123be5b71 Adjust context size for parallelism 2024-04-25 13:58:54 -07:00
jmorganca
ddf5c09a9b use matrix multiplcation kernels in more cases 2024-04-25 13:58:54 -07:00
Roy Yang
5f73c08729 Remove trailing spaces (#3889) 2024-04-25 14:32:26 -04:00
Daniel Hiltgen
f503a848c2 Merge pull request #3895 from brycereitano/shiftloading
Move ggml loading to when attempting to fit
2024-04-25 09:24:08 -07:00
Bryce Reitano
36a6daccab Restructure loading conditional chain 2024-04-24 17:37:03 -06:00
Bryce Reitano
ceb0e26e5e Provide variable ggml for TestLoad 2024-04-24 17:19:55 -06:00
Bryce Reitano
284e02bed0 Move ggml loading to when we attempt fitting 2024-04-24 17:17:24 -06:00
Michael Yang
3450a57d4a Merge pull request #3713 from ollama/mxyng/modelname
update copy handler to use model.Name
2024-04-24 16:00:32 -07:00
Michael Yang
592dae31c8 update copy to use model.Name 2024-04-24 15:54:54 -07:00
Michael Yang
2010cbc5fa Merge pull request #3833 from ollama/mxyng/fix-from
fix: from blob
2024-04-24 15:13:47 -07:00
Michael Yang
ac0801eced only replace if it matches command 2024-04-24 14:49:26 -07:00
Michael Yang
ad66e5b060 split temp zip files 2024-04-24 14:18:01 -07:00
Blake Mizerany
ade4b55520 types/model: make ParseName use default without question (#3886) 2024-04-24 11:52:55 -07:00
Daniel Hiltgen
a6d62e0617 Merge pull request #3882 from dhiltgen/amd_gfx
AMD gfx patch rev is hex
2024-04-24 11:07:49 -07:00
Daniel Hiltgen
6e76348df7 Merge pull request #3834 from dhiltgen/not_found_in_path
Report errors on server lookup instead of path lookup failure
2024-04-24 10:50:48 -07:00
Daniel Hiltgen
0d6687f84c AMD gfx patch rev is hex
Correctly handle gfx90a discovery
2024-04-24 09:43:52 -07:00
Patrick Devine
74d2a9ef9a add OLLAMA_KEEP_ALIVE env variable to FAQ (#3865) 2024-04-23 21:06:51 -07:00
Patrick Devine
14476d48cc fixes for gguf (#3863) 2024-04-23 20:57:20 -07:00
Patrick Devine
ce8ce82567 add mixtral 8x7b model conversion (#3859) 2024-04-23 20:17:04 -07:00
Blake Mizerany
4dc4f1be34 types/model: restrict digest hash part to a minimum of 2 characters (#3858)
This allows users of a valid Digest to know it has a minimum of 2
characters in the hash part for use when sharding.

This is a reasonable restriction as the hash part is a SHA256 hash which
is 64 characters long, which is the common hash used. There is no
anticipation of using a hash with less than 2 characters.

Also, add MustParseDigest.

Also, replace Digest.Type with Digest.Split for getting both the type
and hash parts together, which is most the common case when asking for
either.
2024-04-23 18:24:17 -07:00
Daniel Hiltgen
16b52331a4 Merge pull request #3857 from dhiltgen/mem_escape_valve
Add back memory escape valve
2024-04-23 17:32:24 -07:00
Daniel Hiltgen
5445aaa94e Add back memory escape valve
If we get our predictions wrong, this can be used to
set a lower memory limit as a workaround.  Recent multi-gpu
refactoring accidentally removed it, so this adds it back.
2024-04-23 17:09:02 -07:00
Daniel Hiltgen
2ac3dd6853 Merge pull request #3850 from dhiltgen/windows_packaging
Move nested payloads to installer and zip file on windows
2024-04-23 16:35:20 -07:00
Daniel Hiltgen
d8851cb7a0 Harden sched TestLoad
Give the go routine a moment to deliver the expired event
2024-04-23 16:14:47 -07:00
Daniel Hiltgen
058f6cd2cc Move nested payloads to installer and zip file on windows
Now that the llm runner is an executable and not just a dll, more users are facing
problems with security policy configurations on windows that prevent users
writing to directories and then executing binaries from the same location.
This change removes payloads from the main executable on windows and shifts them
over to be packaged in the installer and discovered based on the executables location.
This also adds a new zip file for people who want to "roll their own" installation model.
2024-04-23 16:14:47 -07:00
Daniel Hiltgen
790cf34d17 Merge pull request #3846 from dhiltgen/missing_runner
Detect and recover if runner removed
2024-04-23 13:14:12 -07:00
Michael
928d844896 adding phi-3 mini to readme
adding phi-3 mini to readme
2024-04-23 13:58:31 -04:00
Daniel Hiltgen
939d6a8606 Make CI lint verbvose 2024-04-23 10:17:42 -07:00
Daniel Hiltgen
58888a74bc Detect and recover if runner removed
Tmp cleaners can nuke the file out from underneath us.  This detects the missing
runner, and re-initializes the payloads.
2024-04-23 10:05:26 -07:00
Daniel Hiltgen
cc5a71e0e3 Merge pull request #3709 from remy415/custom-gpu-defs
Adds support for customizing GPU build flags in llama.cpp
2024-04-23 09:28:34 -07:00
Michael Yang
e83bcf7f9a Merge pull request #3836 from ollama/mxyng/mixtral
fix: mixtral graph
2024-04-23 09:15:10 -07:00
Daniel Hiltgen
5690e5ce99 Merge pull request #3418 from dhiltgen/concurrency
Request and model concurrency
2024-04-23 08:31:38 -07:00
Daniel Hiltgen
f2ea8470e5 Local unicode test case 2024-04-22 19:29:12 -07:00
Daniel Hiltgen
34b9db5afc Request and model concurrency
This change adds support for multiple concurrent requests, as well as
loading multiple models by spawning multiple runners. The default
settings are currently set at 1 concurrent request per model and only 1
loaded model at a time, but these can be adjusted by setting
OLLAMA_NUM_PARALLEL and OLLAMA_MAX_LOADED_MODELS.
2024-04-22 19:29:12 -07:00
Daniel Hiltgen
8711d03df7 Report errors on server lookup instead of path lookup failure 2024-04-22 19:08:47 -07:00
Daniel Hiltgen
ee448deaba Merge pull request #3835 from dhiltgen/harden_llm_override
Trim spaces and quotes from llm lib override
2024-04-22 19:06:54 -07:00
Bruce MacDonald
6e8db04716 tidy community integrations
- move some popular integrations to the top of the lists
2024-04-22 17:29:08 -07:00
Bruce MacDonald
658e60cf73 Revert "stop running model on interactive exit"
This reverts commit fad00a85e5.
2024-04-22 17:23:11 -07:00
Bruce MacDonald
4c78f028f8 Merge branch 'main' of https://github.com/ollama/ollama 2024-04-22 17:22:28 -07:00
Michael Yang
435cc866a3 fix: mixtral graph 2024-04-22 17:19:44 -07:00
Hao Wu
c7d3a558f6 docs: update README to add chat (web UI) for LLM (#3810)
* add chat (web UI) for LLM

I have used chat with llama3 in local successfully and the code is MIT licensed.

* Update README.md

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-04-22 20:19:39 -04:00
Maple Gao
089cdb2877 docs: Update README for Lobe-chat integration. (#3817)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-04-22 20:18:15 -04:00
Võ Đình Đạt
ea1e9aa36b Update README.md (#3655) 2024-04-22 20:16:55 -04:00
Jonathan Smoley
d0d28ef90d Update README.md with Discord-Ollama project (#3633)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-04-22 20:14:20 -04:00
Eric Curtin
6654186a7c Add podman-ollama to terminal apps (#3626)
The goal of podman-ollama is to make AI even more boring.

Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2024-04-22 20:13:23 -04:00
Daniel Hiltgen
aa72281eae Trim spaces and quotes from llm lib override 2024-04-22 17:11:14 -07:00
reid41
74bcbf828f add qa-pilot link (#3612)
* add qa-pilot link

* format the link

* add shell-pilot
2024-04-22 20:10:34 -04:00
Christian Neff
fe39147e64 Add Chatbot UI v2 to Community Integrations (#3503) 2024-04-22 20:09:55 -04:00
Bruce MacDonald
fad00a85e5 stop running model on interactive exit 2024-04-22 16:22:14 -07:00
Jeremy
9c0db4cc83 Update gen_windows.ps1
Fixed improper env references
2024-04-21 16:13:41 -04:00
Cheng
62be2050dd chore: use errors.New to replace fmt.Errorf will much better (#3789) 2024-04-20 22:11:06 -04:00
Blake Mizerany
56f8aa6912 types/model: export IsValidNamePart (#3788) 2024-04-20 18:26:34 -07:00
Sri Siddhaarth
e6f9bfc0e8 Update api.md (#3705) 2024-04-20 15:17:03 -04:00
Jeremy
6f18297b3a Update gen_windows.ps1
Forgot a " on the write-host
2024-04-18 19:47:44 -04:00
Jeremy
15016413de Update gen_windows.ps1
Added OLLAMA_CUSTOM_CUDA_DEFS and OLLAMA_CUSTOM_ROCM_DEFS to customize GPU builds on Windows
2024-04-18 19:27:16 -04:00
Jeremy
440b7190ed Update gen_linux.sh
Added OLLAMA_CUSTOM_CUDA_DEFS and OLLAMA_CUSTOM_ROCM_DEFS instead of OLLAMA_CUSTOM_GPU_DEFS
2024-04-18 19:18:10 -04:00
Daniel Hiltgen
8d1995c625 Merge pull request #3708 from remy415/arm64static
move Ollama static build to its own flag
2024-04-18 16:04:12 -07:00
Daniel Hiltgen
fd01fbf038 Merge pull request #3710 from remy415/update-jetson-docs
update jetson tutorial
2024-04-18 16:02:08 -07:00
Blake Mizerany
0408205c1c types/model: accept former : as a separator in digest (#3724)
This also converges the old sep `:` to the new sep `-`.
2024-04-18 14:17:46 -07:00
Jeffrey Morgan
63a7edd771 Update README.md 2024-04-18 16:09:38 -04:00
Michael
554ffdcce3 add llama3 to readme
add llama3 to readme
2024-04-18 15:18:48 -04:00
Jeremy
9850a4ce08 Merge branch 'ollama:main' into update-jetson-docs 2024-04-18 09:55:17 -04:00
Jeremy
3934c15895 Merge branch 'ollama:main' into custom-gpu-defs 2024-04-18 09:55:10 -04:00
Jeremy
fd048f1367 Merge branch 'ollama:main' into arm64static 2024-04-18 09:55:04 -04:00
Michael Yang
8645076a71 Merge pull request #3712 from ollama/mxyng/mem
add stablelm graph calculation
2024-04-17 15:57:51 -07:00
Michael Yang
05e9424824 Merge pull request #3664 from ollama/mxyng/fix-padding-2
fix padding to only return padding
2024-04-17 15:57:40 -07:00
Michael Yang
52ebe67a98 Merge pull request #3714 from ollama/mxyng/model-name-host
types/model: support : in PartHost for host:port
2024-04-17 15:34:03 -07:00
Michael Yang
889b31ab78 types/model: support : in PartHost for host:port 2024-04-17 15:16:07 -07:00
Michael Yang
3cf483fe48 add stablelm graph calculation 2024-04-17 13:57:19 -07:00
Jeremy
8dca03173d Merge remote-tracking branch 'upstream/main' into update-jetson-docs 2024-04-17 16:18:50 -04:00
Jeremy
85bdf14b56 update jetson tutorial 2024-04-17 16:17:42 -04:00
Jeremy
d524e5ef5e Merge branch 'custom-gpu-defs' of https://github.com/remy415/ollama into custom-gpu-defs 2024-04-17 16:01:03 -04:00
Jeremy
52f5370c48 add support for custom gpu build flags for llama.cpp 2024-04-17 16:00:48 -04:00
Jeremy
da8a0c7657 Merge branch 'ollama:main' into arm64static 2024-04-17 15:22:34 -04:00
Jeremy
1b42b4b59a Merge branch 'ollama:main' into custom-gpu-defs 2024-04-17 15:21:56 -04:00
Jeremy
7c000ec3ed adds support for OLLAMA_CUSTOM_GPU_DEFS to customize GPU build flags 2024-04-17 15:21:05 -04:00
jmorganca
c8afe7168c use correct extension for feature and model request issue templates 2024-04-17 15:18:40 -04:00
jmorganca
28d3cd0148 simpler feature and model request forms 2024-04-17 15:17:08 -04:00
jmorganca
eb5554232a simpler feature and model request forms 2024-04-17 15:14:49 -04:00
Jeremy
ea4c284a48 Merge branch 'ollama:main' into arm64static 2024-04-17 15:11:38 -04:00
jmorganca
2bdc320216 add descriptions to issue templates 2024-04-17 15:08:36 -04:00
jmorganca
32561aed09 simplify github issue templates a bit 2024-04-17 15:07:03 -04:00
Michael Yang
71548d9829 Merge pull request #3706 from ollama/mxyng/mem
account for all non-repeating layers
2024-04-17 11:58:20 -07:00
Jeremy
8aec92fa6d rearranged conditional logic for static build, dockerfile updated 2024-04-17 14:43:28 -04:00
Michael Yang
a8b9b930b4 account for all non-repeating layers 2024-04-17 11:21:21 -07:00
Michael
9755cf9173 acknowledge the amazing work done by Georgi and team! 2024-04-17 13:48:14 -04:00
Jeremy
70261b9bb6 move static build to its own flag 2024-04-17 13:04:28 -04:00
Blake Mizerany
9df6c85c3a types/model: add FilepathNoBuild (#3680)
Also, add test for DisplayLongest.

Also, plumb fill param to ParseName in MustParseName
2024-04-16 18:35:43 -07:00
Michael Yang
e74163af4c fix padding to only return padding 2024-04-16 15:43:26 -07:00
Michael Yang
fb9580df85 Merge pull request #3684 from ollama/mxyng/scale-graph
scale graph based on gpu count
2024-04-16 14:57:09 -07:00
Michael Yang
26df674785 scale graph based on gpu count 2024-04-16 14:44:13 -07:00
Jeffrey Morgan
7c9792a6e0 Support unicode characters in model path (#3681)
* parse wide argv characters on windows

* cleanup

* move cleanup to end of `main`
2024-04-16 17:00:12 -04:00
Michael Yang
7afb2e125a Merge pull request #3678 from ollama/mxyng/fix-darwin-partial-offloading
darwin: no partial offloading if required memory greater than system
2024-04-16 12:05:56 -07:00
Michael Yang
41a272de9f darwin: no partial offloading if required memory greater than system 2024-04-16 11:22:38 -07:00
Jeffrey Morgan
f335722275 update llama.cpp submodule to 7593639 (#3665) 2024-04-15 23:04:43 -04:00
Michael Yang
6d53b67c2c Merge pull request #3663 from ollama/mxyng/fix-padding 2024-04-15 17:44:54 -07:00
Michael Yang
969238b19e fix padding in decode
TODO: update padding() to _only_ returning the padding
2024-04-15 17:27:06 -07:00
Blake Mizerany
949d7832cf Revert "cmd: provide feedback if OLLAMA_MODELS is set on non-serve command (#3470)" (#3662)
This reverts commit 7d05a6ee8f.

This proved to be more painful than useful.

See: https://github.com/ollama/ollama/issues/3624
2024-04-15 16:58:00 -07:00
Sung Kim
99d227c9db Added Solar example at README.md (#3610)
Added just one line

| Solar              | 10.7B      | 6.1GB | `ollama run solar`             |
2024-04-15 19:54:23 -04:00
Carlos Gamez
a27e419b47 Update langchainjs.md (#2030)
Changed ollama.call() for ollama.invoke() as per deprecated documentation from langchain
2024-04-15 18:37:30 -04:00
Chandre Van Der Westhuizen
e4d0db5a97 Added MindsDB information (#3595)
* Added MindsDB information

Added more details to MindsDB so that Ollama users can know that they can connect their Ollama model with 200+ databases and apps

* updated text for mindsdb
2024-04-15 18:35:29 -04:00
Eli Bendersky
ba460802c2 examples: add more Go examples using the API (#3599)
* examples: go-multimodal

* examples: add go-pull-progress

* examples: add go-chat

* fix
2024-04-15 18:34:54 -04:00
Jeffrey Morgan
e54a3c7fcd Update modelfile.md
Remove Modelfile parameters that are decided at runtime
2024-04-15 15:35:44 -04:00
Patrick Devine
9f8691c6c8 Add llama2 / torch models for ollama create (#3607) 2024-04-15 11:26:42 -07:00
Jeffrey Morgan
a0b8a32eb4 Terminate subprocess if receiving SIGINT or SIGTERM signals while model is loading (#3653)
* terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading

* use `unload` in signal handler
2024-04-15 12:09:32 -04:00
Jeffrey Morgan
7027f264fb app: gracefully shut down ollama serve on windows (#3641)
* app: gracefully shut down `ollama serve` on windows

* fix linter errors

* bring back `HideWindow`

* remove creation flags

* restore `windows.CREATE_NEW_PROCESS_GROUP`
2024-04-14 18:33:25 -04:00
Blake Mizerany
9bee3b63b1 types/model: add path helpers (#3619)
This commit adds path helpers for working with Names in URL and file
paths. The new helpers are ParseNameFromPath, ParseNameFromFilePath,
Name.Path, and Name.FilePath.

This commit also adds Name.DisplayLongest, and Name.DisplayLong.

Also, be it updates a place where strings.StripPrefix is more consistent
with the surrounding code.

Also, replace Parts with specific methods
2024-04-13 12:59:19 -07:00
Jeffrey Morgan
309aef7fee update llama.cpp submodule to 4bd0f93 (#3627) 2024-04-13 10:43:02 -07:00
Blake Mizerany
08655170aa types/model: make ParseName variants less confusing (#3617)
Also, fix http stripping bug.

Also, improve upon docs about fills and masks.
2024-04-12 13:57:57 -07:00
Blake Mizerany
2b341069a7 types/model: remove (*Digest).Scan and Digest.Value (#3605) 2024-04-11 13:32:31 -07:00
Daniel Hiltgen
c00fee6936 Merge pull request #3604 from dhiltgen/fix_rocm_deps
Fix rocm deps with new subprocess paths
2024-04-11 13:08:29 -07:00
Daniel Hiltgen
c2d813bdc3 Fix rocm deps with new subprocess paths 2024-04-11 12:52:06 -07:00
Michael Yang
786f3a1c44 Merge pull request #3600 from ollama/mxyng/mixtral 2024-04-11 12:23:37 -07:00
Michael Yang
3397eff0cd mixtral mem 2024-04-11 11:10:41 -07:00
Blake Mizerany
0efb7931c7 Revert "types/model: remove (*Digest).Scan and Digest.Value (#3589)"
This reverts commit 42f2cc408e.
2024-04-11 00:45:07 -07:00
Blake Mizerany
42f2cc408e types/model: remove (*Digest).Scan and Digest.Value (#3589) 2024-04-11 00:37:26 -07:00
Blake Mizerany
9446b795b5 types/model: remove DisplayLong (#3587) 2024-04-10 16:55:12 -07:00
Blake Mizerany
62f8cda3b3 types/model: remove MarshalText/UnmarshalText from Digest (#3586) 2024-04-10 16:52:49 -07:00
Blake Mizerany
6a1de23175 types/model: init with Name and Digest types (#3541) 2024-04-10 16:30:05 -07:00
Blake Mizerany
a7b431e743 server: provide helpful workaround hint when stalling on pull (#3584)
This is a quick fix to help users who are stuck on the "pull" step at
99%.

In the near future we're introducing a new registry client that
should/will hopefully be smarter. In the meantime, this should unblock
the users hitting issue #1736.
2024-04-10 16:24:37 -07:00
Michael Yang
5a25f93522 Merge pull request #3478 from ollama/mxyng/tensor-layer
refactor tensor query
2024-04-10 12:45:03 -07:00
Michael Yang
7e33a017c0 partial offloading 2024-04-10 11:37:20 -07:00
Michael Yang
8b2c10061c refactor tensor query 2024-04-10 11:37:20 -07:00
Michael Yang
c5c451ca3b Merge pull request #3579 from ollama/mxyng/fix-ci
fix ci
2024-04-10 11:37:01 -07:00
Michael Yang
2b4ca6cf36 fix ci 2024-04-10 11:35:12 -07:00
Eli Bendersky
ad90b9ab3d api: start adding documentation to package api (#2878)
* api: start adding documentation to package api

Updates #2840

* Fix lint typo report
2024-04-10 13:31:55 -04:00
Eli Bendersky
4340f8eba4 examples: start adding Go examples using api/ (#2879)
We can have the same examples as e.g. https://github.com/ollama/ollama-python/tree/main/examples
here. Using consistent naming and renaming the existing example to have -http-
since it uses direct HTTP requests rather than api/

Updates #2840
2024-04-10 13:26:45 -04:00
Daniel Hiltgen
4c7db6b7e9 Merge pull request #3566 from dhiltgen/more_time
Handle very slow model loads
2024-04-09 16:53:49 -07:00
Michael Yang
c03f0e3c3d Merge pull request #3565 from ollama/mxyng/rope
fix: rope
2024-04-09 16:36:55 -07:00
Daniel Hiltgen
c5ff443b9f Handle very slow model loads
During testing, we're seeing some models take over 3 minutes.
2024-04-09 16:35:10 -07:00
Michael Yang
01114b4526 fix: rope 2024-04-09 16:15:24 -07:00
Blake Mizerany
1524f323a3 Revert "build.go: introduce a friendlier way to build Ollama (#3548)" (#3564) 2024-04-09 15:57:45 -07:00
Blake Mizerany
fccf3eecaa build.go: introduce a friendlier way to build Ollama (#3548)
This commit introduces a more friendly way to build Ollama dependencies
and the binary without abusing `go generate` and removing the
unnecessary extra steps it brings with it.

This script also provides nicer feedback to the user about what is
happening during the build process.

At the end, it prints a helpful message to the user about what to do
next (e.g. run the new local Ollama).
2024-04-09 14:18:47 -07:00
Michael Yang
c77d45d836 Merge pull request #3506 from ollama/mxyng/quantize-redux
cgo quantize
2024-04-09 12:32:53 -07:00
Jeffrey Morgan
5ec12cec6c update llama.cpp submodule to 1b67731 (#3561) 2024-04-09 15:10:17 -04:00
Michael Yang
d9578d2bad Merge pull request #3559 from ollama/mxyng/ci
ci: use go-version-file
2024-04-09 11:03:18 -07:00
Michael Yang
cb8352d6b4 ci: use go-version-file 2024-04-09 09:50:12 -07:00
Alex Mavrogiannis
fc6558f47f Correct directory reference in macapp/README (#3555) 2024-04-09 09:48:46 -04:00
Michael Yang
9502e5661f cgo quantize 2024-04-08 15:31:08 -07:00
Michael Yang
e1c9a2a00f no blob create if already exists 2024-04-08 15:09:48 -07:00
writinwaters
1341ee1b56 Update README.md (#3539)
RAGFlow now supports integration with Ollama.
2024-04-08 10:58:14 -04:00
Jeffrey Morgan
63efa075a0 update generate scripts with new LLAMA_CUDA variable, set HIP_PLATFORM to avoid compiler errors (#3528) 2024-04-07 19:29:51 -04:00
Thomas Vitale
cb03fc9571 Docs: Remove wrong parameter for Chat Completion (#3515)
Fixes gh-3514

Signed-off-by: Thomas Vitale <ThomasVitale@users.noreply.github.com>
2024-04-06 09:08:35 -07:00
Michael Yang
a5ec9cfc0f Merge pull request #3508 from ollama/mxyng/rope 2024-04-05 18:46:06 -07:00
Michael Yang
be517e491c no rope parameters 2024-04-05 18:05:27 -07:00
Michael Yang
fc8e108642 Merge pull request #3496 from ollama/mxyng/cmd-r-graph
add command-r graph estimate
2024-04-05 12:26:21 -07:00
Daniel Hiltgen
c5d5c4a96c Merge pull request #3491 from dhiltgen/context_bust_test
Add test case for context exhaustion
2024-04-04 16:20:20 -07:00
Daniel Hiltgen
dfe330fa1c Merge pull request #3488 from mofanke/fix-windows-dll-compress
fix dll compress in windows building
2024-04-04 16:12:13 -07:00
Michael Yang
01f77ae25d add command-r graph estimate 2024-04-04 14:07:24 -07:00
Daniel Hiltgen
483b81a863 Merge pull request #3494 from dhiltgen/ci_release
Fail fast if mingw missing on windows
2024-04-04 10:15:40 -07:00
Daniel Hiltgen
36bd967722 Fail fast if mingw missing on windows 2024-04-04 09:51:26 -07:00
Jeffrey Morgan
b0e7d35db8 use an older version of the mac os sdk in release (#3484) 2024-04-04 09:48:54 -07:00
Daniel Hiltgen
aeb1fb5192 Add test case for context exhaustion
Confirmed this fails on 0.1.30 with known regression
but passes on main
2024-04-04 07:42:17 -07:00
Daniel Hiltgen
a2e60ebcaf Merge pull request #3490 from dhiltgen/ci_fixes
CI missing archive
2024-04-04 07:24:24 -07:00
Daniel Hiltgen
883ec4d1ef CI missing archive 2024-04-04 07:23:27 -07:00
mofanke
4de0126719 fix dll compress in windows building 2024-04-04 21:27:33 +08:00
Daniel Hiltgen
9768e2dc75 Merge pull request #3481 from dhiltgen/ci_fixes
CI subprocess path fix
2024-04-03 19:29:09 -07:00
Daniel Hiltgen
08600d5bec CI subprocess path fix 2024-04-03 19:12:53 -07:00
Daniel Hiltgen
a624e672d2 Merge pull request #3479 from dhiltgen/ci_fixes
Fix CI release glitches
2024-04-03 18:42:27 -07:00
Daniel Hiltgen
e4a7e5b2ca Fix CI release glitches
The subprocess change moved the build directory
arm64 builds weren't setting cross-compilation flags when building on x86
2024-04-03 16:41:40 -07:00
Michael Yang
a0a15cfd5b Merge pull request #3463 from ollama/mxyng/graph-estimate
update graph size estimate
2024-04-03 14:27:30 -07:00
Michael Yang
12e923e158 update graph size estimate 2024-04-03 13:34:12 -07:00
Jeffrey Morgan
cd135317d2 Fix macOS builds on older SDKs (#3467) 2024-04-03 10:45:54 -07:00
Michael Yang
4f895d633f Merge pull request #3466 from ollama/mxyng/head-kv
default head_kv to 1
2024-04-03 10:41:00 -07:00
Blake Mizerany
7d05a6ee8f cmd: provide feedback if OLLAMA_MODELS is set on non-serve command (#3470)
This also moves the checkServerHeartbeat call out of the "RunE" Cobra
stuff (that's the only word I have for that) to on-site where it's after
the check for OLLAMA_MODELS, which allows the helpful error message to
be printed before the server heartbeat check. This also arguably makes
the code more readable without the magic/superfluous "pre" function
caller.
2024-04-02 22:11:13 -07:00
Daniel Hiltgen
464d817824 Merge pull request #3464 from dhiltgen/subprocess
Fix numgpu opt miscomparison
2024-04-02 20:10:17 -07:00
Pier Francesco Contino
531324a9be feat: add OLLAMA_DEBUG in ollama server help message (#3461)
Co-authored-by: Pier Francesco Contino <pfcontino@gmail.com>
2024-04-02 18:20:03 -07:00
Daniel Hiltgen
6589eb8a8c Revert options as a ref in the server 2024-04-02 16:44:10 -07:00
Michael Yang
90f071c658 default head_kv to 1 2024-04-02 16:37:59 -07:00
Michael Yang
a039e383cd Merge pull request #3465 from ollama/mxyng/fix-metal
fix metal gpu
2024-04-02 16:29:58 -07:00
Michael Yang
80163ebcb5 fix metal gpu 2024-04-02 16:06:45 -07:00
Daniel Hiltgen
a57818d93e Merge pull request #3343 from dhiltgen/bump_more2
Bump llama.cpp to b2581
2024-04-02 15:08:26 -07:00
Daniel Hiltgen
841adda157 Fix windows lint CI flakiness 2024-04-02 12:22:16 -07:00
Daniel Hiltgen
0035e31af8 Bump to b2581 2024-04-02 11:53:07 -07:00
Daniel Hiltgen
c863c6a96d Merge pull request #3218 from dhiltgen/subprocess
Switch back to subprocessing for llama.cpp
2024-04-02 10:49:44 -07:00
Daniel Hiltgen
1f11b52511 Refined min memory from testing 2024-04-01 16:48:33 -07:00
Daniel Hiltgen
526d4eb204 Release gpu discovery library after use
Leaving the cudart library loaded kept ~30m of memory
pinned in the GPU in the main process.  This change ensures
we don't hold GPU resources when idle.
2024-04-01 16:48:33 -07:00
Daniel Hiltgen
0a74cb31d5 Safeguard for noexec
We may have users that run into problems with our current
payload model, so this gives us an escape valve.
2024-04-01 16:48:33 -07:00
Daniel Hiltgen
10ed1b6292 Detect too-old cuda driver
"cudart init failure: 35" isn't particularly helpful in the logs.
2024-04-01 16:48:33 -07:00
Daniel Hiltgen
4fec5816d6 Integration test improvements
Cleaner shutdown logic, a bit of response hardening
2024-04-01 16:48:18 -07:00
Daniel Hiltgen
0a0e9f3e0f Apply 01-cache.diff 2024-04-01 16:48:18 -07:00
Daniel Hiltgen
58d95cc9bd Switch back to subprocessing for llama.cpp
This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.
2024-04-01 16:48:18 -07:00
Patrick Devine
3b6a9154dd Simplify model conversion (#3422) 2024-04-01 16:14:53 -07:00
Michael Yang
d6dd2ff839 Merge pull request #3241 from ollama/mxyng/mem
update memory estimations for gpu offloading
2024-04-01 13:59:14 -07:00
Michael Yang
e57a6ba89f Merge pull request #2926 from ollama/mxyng/decode-ggml-v2
refactor model parsing
2024-04-01 13:58:13 -07:00
Michael Yang
12ec2346ef Merge pull request #3442 from ollama/mxyng/generate-output
fix generate output
2024-04-01 13:56:09 -07:00
Michael Yang
1ec0df1069 fix generate output 2024-04-01 13:47:34 -07:00
Michael Yang
91b3e4d282 update memory calcualtions
count each layer independently when deciding gpu offloading
2024-04-01 13:16:32 -07:00
Michael Yang
d338d70492 refactor model parsing 2024-04-01 13:16:15 -07:00
Philipp Gillé
011bb67351 Add chromem-go to community integrations (#3437) 2024-04-01 11:17:37 -04:00
Saifeddine ALOUI
d124627202 Update README.md (#3436) 2024-04-01 11:16:31 -04:00
Jesse Zhang
b0a8246a69 Community Integration: CRAG Ollama Chat (#3423)
Corrective Retrieval Augmented Generation Demo, powered by Langgraph and Streamlit 🤗

Support: 
- Ollama
- OpenAI APIs
2024-04-01 11:16:14 -04:00
Yaroslav
e6fb39c182 Update README.md (#3378)
Plugins list updated
2024-03-31 13:10:05 -04:00
sugarforever
e1f1c374ea Community Integration: ChatOllama (#3400)
* Community Integration: ChatOllama

* fixed typo
2024-03-30 22:46:50 -04:00
Jeffrey Morgan
06a1508bfe Update 90_bug_report.yml 2024-03-29 10:11:17 -04:00
Patrick Devine
5a5efee46b Add gemma safetensors conversion (#3250)
Co-authored-by: Michael Yang <mxyng@pm.me>
2024-03-28 18:54:01 -07:00
Daniel Hiltgen
97ae517fbf Merge pull request #3398 from dhiltgen/release_latest
CI automation for tagging latest images
2024-03-28 16:25:54 -07:00
Daniel Hiltgen
44b813e459 Merge pull request #3377 from dhiltgen/rocm_v6_bump
Bump ROCm to 6.0.2 patch release
2024-03-28 16:07:54 -07:00
Daniel Hiltgen
539043f5e0 CI automation for tagging latest images 2024-03-28 16:07:37 -07:00
Daniel Hiltgen
dbcace6847 Merge pull request #3392 from dhiltgen/ci_build_win_cuda
CI windows gpu builds
2024-03-28 16:03:52 -07:00
Daniel Hiltgen
c91a4ebcff Bump ROCm to 6.0.2 patch release 2024-03-28 15:58:57 -07:00
Daniel Hiltgen
b79c7e4528 CI windows gpu builds
If we're doing generate, test windows cuda and rocm as well
2024-03-28 14:39:10 -07:00
Michael Yang
035b274b70 Merge pull request #3379 from ollama/mxyng/origins
fix: trim quotes on OLLAMA_ORIGINS
2024-03-28 14:14:18 -07:00
Michael Yang
9c6a254945 Merge pull request #3391 from ollama/mxyng-patch-1 2024-03-28 13:15:56 -07:00
Michael Yang
f31f2bedf4 Update troubleshooting link 2024-03-28 12:05:26 -07:00
Michael Yang
756c257553 Merge pull request #3380 from ollama/mxyng/conditional-generate
fix: workflows
2024-03-28 00:35:27 +01:00
Michael Yang
5255d0af8a fix: workflows 2024-03-27 16:30:01 -07:00
Michael Yang
af8a8a6b59 fix: trim quotes on OLLAMA_ORIGINS 2024-03-27 15:24:29 -07:00
Michael Yang
461ad25015 Merge pull request #3376 from ollama/mxyng/conditional-generate
only generate on changes to llm subdirectory
2024-03-27 22:12:53 +01:00
Michael Yang
8838ae787d stub stub 2024-03-27 13:59:12 -07:00
Michael Yang
db75402ade mangle arch 2024-03-27 13:44:50 -07:00
Michael Yang
1e85a140a3 only generate on changes to llm subdirectory 2024-03-27 12:45:35 -07:00
Michael Yang
c363282fdc Merge pull request #3375 from ollama/mxyng/conditional-generate
only generate cuda/rocm when changes to llm detected
2024-03-27 20:40:55 +01:00
Michael Yang
5b0c48d29e only generate cuda/rocm when changes to llm detected 2024-03-27 12:23:09 -07:00
Jeffrey Morgan
913306f4fd Detect arrow keys on windows (#3363)
* detect arrow keys on windows
* add some helpful comments
2024-03-26 18:21:56 -04:00
Jeffrey Morgan
f5ca7f8c8e add license in file header for vendored llama.cpp code (#3351) 2024-03-26 16:23:23 -04:00
Jeffrey Morgan
856b8ec131 remove need for $VSINSTALLDIR since build will fail if ninja cannot be found (#3350) 2024-03-26 16:23:16 -04:00
Patrick Devine
1b272d5bcd change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
Christophe Dervieux
29715dbca7 malformed markdown link (#3358) 2024-03-26 10:46:36 -04:00
Daniel Hiltgen
54a028d07f Merge pull request #3356 from dhiltgen/fix_arm_linux
Switch runner for final release job
2024-03-25 20:54:46 -07:00
Daniel Hiltgen
f83e4db365 Switch runner for final release job
The manifest and tagging step use a lot of disk space
2024-03-25 20:51:40 -07:00
Daniel Hiltgen
3b5866a233 Merge pull request #3353 from dhiltgen/fix_arm_linux
Use Rocky Linux Vault to get GCC 10.2 installed
2024-03-25 19:38:56 -07:00
Daniel Hiltgen
b8c2be6142 Use Rocky Linux Vault to get GCC 10.2 installed
This should hopefully only be a temporary workaround until Rocky 8
picks up GCC 10.4 which fixes the NVCC bug
2024-03-25 19:18:50 -07:00
Daniel Hiltgen
e0319bd78d Revert "Switch arm cuda base image to centos 7"
This reverts commit 5dacc1ebe8.
2024-03-25 19:01:11 -07:00
Daniel Hiltgen
b31ed7f031 Merge pull request #3352 from dhiltgen/fix_arm_linux
Switch arm cuda base image to centos 7
2024-03-25 16:13:10 -07:00
Daniel Hiltgen
5dacc1ebe8 Switch arm cuda base image to centos 7
We had started using rocky linux 8, but they've updated to GCC 10.3,
which breaks NVCC.  10.2 is compatible (or 10.4, but that's not
available from rocky linux 8 repos yet)
2024-03-25 15:57:08 -07:00
Daniel Hiltgen
c2712b5566 Merge pull request #3348 from dhiltgen/bump_llamacpp
Bump llama.cpp to b2527
2024-03-25 14:15:53 -07:00
Daniel Hiltgen
8091ef2eeb Bump llama.cpp to b2527 2024-03-25 13:47:44 -07:00
Jeffrey Morgan
f38b705dc7 Fix ROCm link in development.md 2024-03-25 16:32:44 -04:00
Daniel Hiltgen
560be5e0b6 Merge pull request #3308 from dhiltgen/bump_more
Bump llama.cpp to b2510
2024-03-25 12:56:12 -07:00
Daniel Hiltgen
4a1c76b3aa Merge pull request #3331 from dhiltgen/integration_testing
Integration tests conditionally pull
2024-03-25 12:48:51 -07:00
Daniel Hiltgen
28a64e23ca Merge pull request #2279 from remy415/main
Add support for libcudart.so for CUDA devices (Adds Jetson support)
2024-03-25 12:46:28 -07:00
Niclas Pahlfer
92d74e2f59 adds ooo to community integrations (#1623)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 15:08:33 -04:00
Herval Freire
6f8f57dd1d Add cliobot to ollama supported list (#1873)
* Update README.md

* Update README.md

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 15:07:19 -04:00
Chenhe Gu
b2fa68b0ea Add Dify.AI to community integrations (#1944)
Dify.AI is a model-agnostic LLMOps platform for building and managing LLM applications.

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 15:06:39 -04:00
Marco Antônio
3767d5ef0d enh: add ollero.nvim to community applications (#1905)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 15:06:08 -04:00
Ani Betts
9fed85bc8b Add typechat-cli to Terminal apps (#2428)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 15:05:04 -04:00
Miguel
4501bc0913 add new Web & Desktop link in readme for alpaca webui (#2881)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 15:00:18 -04:00
Danny Avila
57ba519e63 Add LibreChat to Web & Desktop Apps (#2918) 2024-03-25 14:59:18 -04:00
enoch1118
d98d322d24 Add Community Integration: OllamaGUI (#2927)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 14:58:28 -04:00
fly2tomato
0c3ec74cf1 Add Community Integration: OpenAOE (#2946)
* Update README.md

* Update README.md

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 14:57:40 -04:00
tusharhero
42ae8359fa docs: Add AI telegram to Community Integrations. (#3033) 2024-03-25 14:56:42 -04:00
Timothy Carambat
e4b76dfb76 docs: Add AnythingLLM to README as integration option (#3145)
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 14:54:48 -04:00
Jikku Jose
2c56517494 Add Saddle (#3178) 2024-03-25 14:54:09 -04:00
Yusuf Can Bayrak
cfbc1b152b tlm added to README.md terminal section. (#3274) 2024-03-25 14:53:26 -04:00
RAPID ARCHITECT
9305ac1b2e Update README.md (#3288)
Added Ollama Basic chat based on hyperdiv

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-03-25 14:52:25 -04:00
drazdra
45d6292959 Update README.md (#3338)
adding drazdra/ollama-chats to the list of UI :)
2024-03-25 14:50:51 -04:00
Blake Mizerany
22921a3969 doc: specify ADAPTER is optional (#3333) 2024-03-25 09:43:19 -07:00
Daniel Hiltgen
7b6cbc10ec Integration tests conditionally pull
If images aren't present, pull them.
Also fixes the expected responses
2024-03-25 08:57:45 -07:00
Jeremy
dfc6721b20 add support for libcudart.so for CUDA devices (adds Jetson support) 2024-03-25 11:07:44 -04:00
Blake Mizerany
acfa2b9422 llm: prevent race appending to slice (#3320) 2024-03-24 11:35:54 -07:00
Daniel Hiltgen
2c390a73ac Merge pull request #3282 from dhiltgen/gpu_docs
Add docs for GPU selection and nvidia uvm workaround
2024-03-24 19:15:03 +01:00
Daniel Hiltgen
3e30c75f3e Bump llama.cpp to b2510 2024-03-23 19:55:56 +01:00
Eddú Meléndez Gonzales
7e430ff352 Add Testcontainers into Libraries section (#3291)
Testcontainers provides a module for Ollama.
2024-03-23 19:55:25 +01:00
Daniel Hiltgen
1784113ef5 Merge pull request #3309 from dhiltgen/integration_testing
Revamp go based integration tests
2024-03-23 19:08:49 +01:00
Daniel Hiltgen
949b6c01e0 Revamp go based integration tests
This uplevels the integration tests to run the server which can allow
testing an existing server, or a remote server.
2024-03-23 14:24:18 +01:00
jmorganca
38daf0a252 rename .gitattributes 2024-03-23 12:40:31 +01:00
Daniel Hiltgen
43799532c1 Bump llama.cpp to b2474
The release just before ggml-cuda.cu refactoring
2024-03-23 09:54:56 +01:00
Daniel Hiltgen
d8fdbfd8da Add docs for GPU selection and nvidia uvm workaround 2024-03-21 11:52:54 +01:00
Bruce MacDonald
a5ba0fcf78 doc: faq gpu compatibility (#3142) 2024-03-21 05:21:34 -04:00
Jeffrey Morgan
3a30bf56dc Update faq.md 2024-03-20 17:48:39 +01:00
Daniel Hiltgen
a1c0a48524 Merge pull request #3122 from dhiltgen/better_tmp_cleanup
Better tmpdir cleanup
2024-03-20 16:28:03 +01:00
Daniel Hiltgen
74788b487c Better tmpdir cleanup
If expanding the runners fails, don't leave a corrupt/incomplete payloads dir
We now write a pid file out to the tmpdir, which allows us to scan for stale tmpdirs
and remove this as long as there isn't still a process running.
2024-03-20 16:03:19 +01:00
Jeffrey Morgan
7ed3e94105 Update faq.md 2024-03-18 10:24:39 +01:00
jmorganca
2297ad39da update faq.md 2024-03-18 10:17:59 +01:00
Michael Yang
01cff6136d Merge pull request #3217 from ollama/mxyng/cleanup
remove global
2024-03-18 02:13:30 -07:00
Michael Yang
3c4ad0ecab dyn global 2024-03-18 09:45:45 +01:00
Michael Yang
22f326464e Merge pull request #3083 from ollama/mxyng/refactor-readseeker
refactor readseeker
2024-03-16 12:08:56 -07:00
Jeffrey Morgan
e95ffc7448 llama: remove server static assets (#3174) 2024-03-15 19:24:12 -07:00
Jeffrey Morgan
2dce1ab40b add llm/ext_server directory to linguist-vendored (#3173) 2024-03-15 17:46:46 -07:00
Daniel Hiltgen
f4b31c2d53 Merge pull request #3111 from alitrack/main
Update ollama.iss
2024-03-15 16:46:59 -07:00
Daniel Hiltgen
ab3456207b Merge pull request #3028 from ollama/ci_release
CI release process
2024-03-15 16:40:54 -07:00
Daniel Hiltgen
6ad414f31e Merge pull request #3086 from dhiltgen/import_server
Import server.cpp to retain llava support
2024-03-15 16:10:35 -07:00
Daniel Hiltgen
052b5a3b77 Merge pull request #3171 from dhiltgen/rocm_94x
Add Radeon gfx940-942 GPU support
2024-03-15 15:58:33 -07:00
Daniel Hiltgen
d4c10df2b0 Add Radeon gfx940-942 GPU support 2024-03-15 15:34:58 -07:00
Daniel Hiltgen
540f4af45f Wire up more complete CI for releases
Flesh out our github actions CI so we can build official releaes.
2024-03-15 12:37:36 -07:00
Blake Mizerany
6ce37e4d96 llm,readline: use errors.Is instead of simple == check (#3161)
This fixes some brittle, simple equality checks to use errors.Is. Since
go1.13, errors.Is is the idiomatic way to check for errors.

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2024-03-15 07:14:12 -07:00
Blake Mizerany
703684a82a server: replace blob prefix separator from ':' to '-' (#3146)
This fixes issues with blob file names that contain ':' characters to be rejected by file systems that do not support them.
2024-03-14 20:18:06 -07:00
Daniel Hiltgen
6459377ae0 Add ROCm support to linux install script (#2966) 2024-03-14 18:00:16 -07:00
Blake Mizerany
8546dd3d72 .github: fix model and feature request yml (#3155) 2024-03-14 15:26:06 -07:00
Blake Mizerany
87100be5e0 .github: add issue templates (#3143) 2024-03-14 15:19:10 -07:00
Michael Yang
e87c780ff9 Merge pull request #3149 from ollama/mxyng/fix-memory-leak
fix: clip memory leak
2024-03-14 13:34:15 -07:00
Michael Yang
291c663865 fix: clip memory leak 2024-03-14 13:12:42 -07:00
Daniel Hiltgen
da20786e3e Merge pull request #3068 from dhiltgen/win_pipe
Use stdin for term discovery on windows
2024-03-14 11:55:19 -07:00
Jeffrey Morgan
5ce997a7b9 Update README.md 2024-03-13 21:12:17 -07:00
Jeffrey Morgan
672ffe9b7d add OLLAMA_KEEP_ALIVE to environment variable docs for ollama serve (#3127) 2024-03-13 14:35:33 -07:00
Patrick Devine
47cfe58af5 Default Keep Alive environment variable (#3094)
---------

Co-authored-by: Chris-AS1 <8493773+Chris-AS1@users.noreply.github.com>
2024-03-13 13:29:40 -07:00
Daniel Hiltgen
c1a81c6fe3 Use stdin for term discovery on windows
When you feed input to the cmd via a pipe it no longer reports a warning
2024-03-13 10:37:31 -07:00
Steven Lee
152ab524c2 Update ollama.iss
add arm64 support
2024-03-13 20:15:45 +08:00
Jeffrey Morgan
e72c567cfd restore locale patch (#3091) 2024-03-12 22:08:13 -07:00
Bruce MacDonald
3e22611200 token repeat limit for prediction requests (#3080) 2024-03-12 22:08:25 -04:00
Daniel Hiltgen
a54d4a28dc Merge pull request #3088 from dhiltgen/rocm_igpu_linux
Fix iGPU detection for linux
2024-03-12 17:20:27 -07:00
Daniel Hiltgen
82b0c7c27e Fix iGPU detection for linux
This fixes a few bugs in the new sysfs discovery logic.  iGPUs are now
correctly identified by their <1G VRAM reported.  the sysfs IDs are off
by one compared to what HIP wants due to the CPU being reported
in amdgpu, but HIP only cares about GPUs.
2024-03-12 16:57:19 -07:00
Patrick Devine
ba7cf7fb66 add more docs on for the modelfile message command (#3087) 2024-03-12 16:41:41 -07:00
Bruce MacDonald
2f804068bd warn when json format is expected but not mentioned in prompt (#3081) 2024-03-12 19:07:11 -04:00
Daniel Hiltgen
85129d3a32 Adapt our build for imported server.cpp 2024-03-12 14:57:15 -07:00
Daniel Hiltgen
9ac6440da3 Import server.cpp as of b2356 2024-03-12 13:58:06 -07:00
Michael Yang
0085297928 refactor readseeker 2024-03-12 12:54:18 -07:00
Daniel Hiltgen
34d00f90b1 Merge pull request #3070 from dhiltgen/visible_devices
Add docs explaining GPU selection env vars
2024-03-12 11:36:46 -07:00
Daniel Hiltgen
b53229a2ed Add docs explaining GPU selection env vars 2024-03-12 11:33:06 -07:00
racerole
53c107e20e chore: fix typo (#3073)
Signed-off-by: racerole <jiangyifeng@outlook.com>
2024-03-12 14:09:22 -04:00
mofanke
51578d8573 fix gpu_info_cuda.c compile warning (#3077) 2024-03-12 14:08:40 -04:00
Jeffrey Morgan
b5fcd9d3aa use -trimpath when building releases (#3069) 2024-03-11 15:58:46 -07:00
Bruce MacDonald
b80661e8c7 relay load model errors to the client (#3065) 2024-03-11 16:48:27 -04:00
Jeffrey Morgan
6d3adfbea2 Update troubleshooting.md 2024-03-11 13:22:28 -07:00
Jeffrey Morgan
369eda65f5 update llama.cpp submodule to ceca1ae (#3064) 2024-03-11 12:57:48 -07:00
Michael Yang
f878e91070 Merge pull request #3044 from ollama/mxyng/fix-convert-shape
convert: fix shape
2024-03-11 09:56:57 -07:00
Daniel Hiltgen
0d651478e4 Merge pull request #3056 from dhiltgen/rocm_link_clash
Avoid rocm runner and dependency clash
2024-03-11 09:48:48 -07:00
Michael Yang
9ea492f1ce convert: fix shape 2024-03-11 09:41:01 -07:00
Daniel Hiltgen
bc13da2bfe Avoid rocm runner and dependency clash
Putting the rocm symlink next to the runners is risky.  This moves
the payloads into a subdir to avoid potential clashes.
2024-03-11 09:33:22 -07:00
Jeffrey Morgan
41b00b9856 fix 03-locale.diff 2024-03-10 16:21:05 -07:00
Daniel Hiltgen
c2a8ed48e7 Merge pull request #3048 from dhiltgen/harden_rocm_deps
Harden for deps file being empty (or short)
2024-03-10 15:17:22 -07:00
Daniel Hiltgen
3dc1bb6a35 Harden for deps file being empty (or short) 2024-03-10 14:45:38 -07:00
Daniel Hiltgen
7865a6996a Merge pull request #3046 from dhiltgen/rocm_search_paths
Add ollama executable peer dir for rocm
2024-03-10 12:30:56 -07:00
Daniel Hiltgen
00ec269321 Add ollama executable peer dir for rocm
This allows people who package up ollama on their own to place
the rocm dependencies in a peer directory to the ollama executable
much like our windows install flow.
2024-03-10 12:16:30 -07:00
Jeffrey Morgan
908005d90b patch: use default locale in wpm tokenizer (#3034) 2024-03-09 21:12:12 -08:00
Jeffrey Morgan
cdf65e793f only copy deps for amd64 in build_linux.sh 2024-03-09 17:55:22 -08:00
Daniel Hiltgen
82ca694d68 Rename ROCm deps file to avoid confusion (#3025) 2024-03-09 17:48:38 -08:00
Jeffrey Morgan
5017a15bcb add macapp to .dockerignore 2024-03-09 16:07:06 -08:00
Jeffrey Morgan
e11668aa07 add bundle_metal and cleanup_metal funtions to gen_darwin.sh 2024-03-09 16:04:57 -08:00
Jeffrey Morgan
0bd0f4a29c tidy cleanup logs 2024-03-09 15:56:48 -08:00
Jeffrey Morgan
1ffb1e2874 update llama.cpp submodule to 77d1ac7 (#3030) 2024-03-09 15:55:34 -08:00
Daniel Hiltgen
0a7844413c Merge pull request #3026 from dhiltgen/win_rocm_docs
Doc how to set up ROCm builds on windows
2024-03-09 14:17:19 -08:00
Jeffrey Morgan
f9cd55c70b disable gpu for certain model architectures and fix divide-by-zero on memory estimation 2024-03-09 12:51:38 -08:00
Daniel Hiltgen
0fdebb34a9 Doc how to set up ROCm builds on windows 2024-03-09 11:29:45 -08:00
Daniel Hiltgen
ac64cd4ef9 Merge pull request #3008 from dhiltgen/no_more_idempotent
Finish unwinding idempotent payload logic
2024-03-09 09:13:24 -08:00
Daniel Hiltgen
4a5c9b8035 Finish unwinding idempotent payload logic
The recent ROCm change partially removed idempotent
payloads, but the ggml-metal.metal file for mac was still
idempotent.  This finishes switching to always extract
the payloads, and now that idempotentcy is gone, the
version directory is no longer useful.
2024-03-09 08:34:39 -08:00
Jeffrey Morgan
efe5617b64 update llama.cpp submodule to c2101a2 (#3020) 2024-03-09 00:44:50 -08:00
Jeffrey Morgan
5b3fad9636 separate out isLocalIP 2024-03-09 00:22:08 -08:00
Jeffrey Morgan
bfec2c6e10 simplify host checks 2024-03-08 23:29:53 -08:00
Jeffrey Morgan
5c143af726 add additional allowed hosts 2024-03-08 23:23:59 -08:00
Jeffrey Morgan
6c0af2599e Update docs README.md and table of contents 2024-03-08 22:45:11 -08:00
Jeffrey Morgan
fc8c044584 add allowed host middleware and remove workDir middleware (#3018) 2024-03-08 22:23:47 -08:00
Michael Yang
ecc133d843 Merge pull request #3014 from ollama/mxyng/decode-ggla 2024-03-08 16:14:53 -08:00
Michael Yang
76bdebbadf decode ggla 2024-03-08 15:46:25 -08:00
Michael Yang
18979ad4a1 convert: fix default shape 2024-03-08 15:42:48 -08:00
Michael Yang
8e0ef931d8 Merge pull request #2990 from ollama/mxyng/default-term-size
fix: default terminal width, height
2024-03-08 15:20:54 -08:00
Daniel Hiltgen
280da44522 Merge pull request #2988 from dhiltgen/rocm_docs
Refined ROCm troubleshooting docs
2024-03-08 13:33:30 -08:00
Bruce MacDonald
0cebc79cba fix: allow importing a model from name reference (#3005) 2024-03-08 12:27:47 -05:00
Jeffrey Morgan
0e4669b04f update llama.cpp submodule to 6cdabe6 (#2999) 2024-03-08 00:26:20 -08:00
Jeffrey Morgan
b886bec3f9 Update api.md 2024-03-07 23:27:51 -08:00
Jeffrey Morgan
fc06205971 Revert "adjust download and upload concurrency based on available bandwidth" (#2995) 2024-03-07 18:10:16 -08:00
Blake Mizerany
2ada81e068 cmd: tighten up env var usage sections (#2962)
Also, document OLLAMA_HOST client semantics per command that honors it.
This looks nicer than having a general puprose environment variable
section in the root usage which was showing up after the "addition help
topics" section outputed by Cobra's default template.

It was decided this was easier to work with than using a custom template
for Cobra right now.
2024-03-07 13:57:07 -08:00
Michael Yang
b1e74d4fda default terminal width, height 2024-03-07 11:35:42 -08:00
Michael Yang
f678f5c5c3 Merge pull request #2991 from ollama/mxyng/fix-ci
fix ci
2024-03-07 11:35:06 -08:00
Michael Yang
2cb74e23fb fix ci 2024-03-07 11:33:49 -08:00
Daniel Hiltgen
69f0227813 Refined ROCm troubleshooting docs 2024-03-07 11:22:37 -08:00
Daniel Hiltgen
3c8df3808b Merge pull request #2885 from dhiltgen/rocm_v6_only
Revamp ROCm support
2024-03-07 10:51:00 -08:00
Michael Yang
7d564835c2 Merge pull request #2985 from ollama/rm-empty-examples
remove empty examples
2024-03-07 10:49:40 -08:00
Michael Yang
72431031d9 no ci test on docs, examples 2024-03-07 10:44:48 -08:00
Michael Yang
6041abb5b2 remove empty examples 2024-03-07 10:40:32 -08:00
Daniel Hiltgen
6c5ccb11f9 Revamp ROCm support
This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed.  It also cleans up after itself.

We now build only a single ROCm version (latest major) on both windows
and linux.  Given the large size of ROCms tensor files, we split the
dependency out.  It's bundled into the installer on windows, and a
separate download on windows.  The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.

For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us.  For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.
2024-03-07 10:36:50 -08:00
Michael Yang
2e20110e50 Merge pull request #2221 from ollama/mxyng/up-down-ccy
adjust download and upload concurrency based on available bandwidth
2024-03-07 09:27:33 -08:00
Daniel Hiltgen
82ddc3e441 Merge pull request #2964 from dhiltgen/mem_limit_var
Allow setting max vram for workarounds
2024-03-07 09:25:44 -08:00
Jeffrey Morgan
d481fb3cc8 update go to 1.22 in other places (#2975) 2024-03-07 07:39:49 -08:00
DJ Johnson
23ee633252 docs: Add LLM-X to Web Integration section (#2759) 2024-03-07 10:11:53 -05:00
John
23ebe8fe11 fix some typos (#2973)
Signed-off-by: hishope <csqiye@126.com>
2024-03-06 22:50:11 -08:00
Patrick Devine
2c017ca441 Convert Safetensors to an Ollama model (#2824) 2024-03-06 21:01:51 -08:00
Daniel Hiltgen
be330174dd Allow setting max vram for workarounds
Until we get all the memory calculations correct, this can provide
and escape valve for users to workaround out of memory crashes.
2024-03-06 17:15:06 -08:00
Blake Mizerany
0ded7fdc4b cmd: document environment variables for serve command
Updates #2944
2024-03-06 13:48:46 -08:00
Leo
2103a5073c Add Odin Runes, a Feature-Rich Java UI for Ollama, to README (#2440)
* Add Odin Runes to README

Add Odin Runes to README

This commit adds Odin Runes to the "Community Integrations" section of the README. Odin Runes is a Java-based GPT client designed to provide seamless interaction with GPT models, enhancing productivity in prompt engineering and text generation tasks. This addition highlights the integration between Odin Runes and Ollama, offering users the flexibility to leverage large language models locally within their development workflow.

* Update README.md

this commit applies the comments of the reviewer.
2024-03-06 11:57:49 -08:00
Jeffrey Morgan
ce9f7c4674 Update api.md 2024-03-05 13:13:23 -08:00
Anders Rex
e5596c1944 Add NotesOllama to Community Integrations (#2909) 2024-03-04 01:18:10 -08:00
Timothy Graupmann
9bc3fee694 Added community link for Ollama Copilot (#2582)
* Added community link for Ollama Copilot

* Update README.md

---------

Co-authored-by: Michael <mchiang0610@users.noreply.github.com>
2024-03-04 00:40:36 -08:00
Jeffrey Morgan
21347e1ed6 update llama.cpp submodule to c29af7e (#2868) 2024-03-01 15:26:04 -08:00
Jeffrey Morgan
3b4bab3dc5 Fix embeddings load model behavior (#2848) 2024-02-29 17:40:56 -08:00
Daniel Hiltgen
cbd6e3b38e Merge pull request #2838 from dhiltgen/opensuse
Add ollama user to video group
2024-02-29 15:47:56 -08:00
Daniel Hiltgen
b830afa716 Merge pull request #2837 from dhiltgen/podman_image_support
Add env var so podman will map cuda GPUs
2024-02-29 15:47:37 -08:00
Daniel Hiltgen
bd1d8b0d14 Merge pull request #2836 from bmwiedemann/gzip
Omit build date from gzip headers
2024-02-29 15:46:46 -08:00
fred-bf
25c2912120 Add Community Integration: NextChat (#2780) 2024-02-29 12:12:13 -08:00
Michael Yang
0e19476b56 prepend image tags (#2789)
instead of appending image tags, prepend them - this generally produces better results
2024-02-29 11:30:14 -08:00
tylinux
fa2f2b3563 fix: print usedMemory size right (#2827) 2024-02-29 11:11:04 -08:00
Jeffrey Morgan
cbf4970e0f bump submodule to 87c91c07663b707e831c59ec373b5e665ff9d64a (#2828) 2024-02-29 09:42:08 -08:00
Daniel Hiltgen
74468513bd Add ollama user to video group
On OpenSUSE, ollama needs to be a member of the video group
to access the GPU
2024-02-29 08:50:10 -08:00
Daniel Hiltgen
794a916a72 Add env var so podman will map cuda GPUs
Without this env var, podman's GPU logic doesn't map the GPU through
2024-02-29 08:43:08 -08:00
Bernhard M. Wiedemann
76e5d9ec88 Omit build date from gzip headers
See https://reproducible-builds.org/ for why this is good.

This patch was done while working on reproducible builds for openSUSE.
2024-02-29 16:48:19 +01:00
Daniel Hiltgen
076237b8ea Merge pull request #2771 from dhiltgen/toggle_models
Bump llama.cpp to b2276
2024-02-27 11:29:53 -08:00
Daniel Hiltgen
53d694c67f Merge pull request #2772 from dhiltgen/container_image
Refine container image build script
2024-02-27 11:29:08 -08:00
Daniel Hiltgen
5aa6bfea94 Merge pull request #2785 from dhiltgen/win_download
Log unexpected server errors checking for update
2024-02-27 10:43:14 -08:00
Daniel Hiltgen
1cde63dd64 Log unexpected server errors checking for update
This should unmask some failure modes that likely
show up in app logs as unmarshal errors
2024-02-27 09:17:04 -08:00
Daniel Hiltgen
98e0b7e94f Refine container image build script
Allow overriding the platform, image name, and tag latest for
standard and rocm images.
2024-02-26 17:26:49 -08:00
Daniel Hiltgen
061e8f6abc Bump llama.cpp to b2276 2024-02-26 16:49:24 -08:00
peanut256
a189810df6 Determine max VRAM on macOS using recommendedMaxWorkingSetSize (#2354)
* read iogpu.wired_limit_mb on macOS

Fix for https://github.com/ollama/ollama/issues/1826

* improved determination of available vram on macOS

read the recommended maximal vram on macOS via Metal API

* Removed macOS-specific logging

* Remove logging from gpu_darwin.go

* release Core Foundation object

fixes a possible memory leak
2024-02-25 18:16:45 -05:00
Ikko Eltociear Ashimine
e95b896790 Update types.go (#2744)
specfied -> specified
2024-02-25 13:41:25 -05:00
elthommy
1f087c4d26 Update langchain python tutorial (#2737)
Remove unused GPT4all
Use nomic-embed-text as embedded model
Fix a deprecation warning (__call__)
2024-02-25 00:31:36 -05:00
Jeffrey Morgan
5d7ea6616f no extra disk space for windows installation (#2739) 2024-02-25 00:20:35 -05:00
Michael Yang
2a4b128ae3 Merge pull request #2719 from ollama/mxyng/format-private-key
remove format private key
2024-02-23 17:15:14 -08:00
Michael Yang
fc483274ad clean up go.mod 2024-02-23 16:53:36 -08:00
Michael Yang
fd10a2ad4b remove format/openssh.go
this is unnecessary now that x/crypto/ssh.MarshalPrivateKey has been
added
2024-02-23 16:52:23 -08:00
Benn Huang
b291f63188 Add Community Integration: Chatbox
Co-authored-by: bennhuang <bennhuang@tencent.com>
2024-02-23 07:17:28 -05:00
Jeffrey Morgan
f58856bf6f better directory cleanup in ollama.iss 2024-02-23 07:14:59 -05:00
Jeffrey Morgan
275ea01587 restore windows build flags and compression 2024-02-22 18:07:18 -05:00
Jeffrey Morgan
8782dd5628 fix build_windows.ps1 script to run go build with the correct flags 2024-02-22 17:41:43 -05:00
Jeffrey Morgan
11bfff8ee1 update llama.cpp submodule to 96633eeca1265ed03e57230de54032041c58f9cd 2024-02-22 16:44:26 -05:00
Logan Yang
7c0167a8f6 Add copilot for obsidian plugin to community integration (#1918) 2024-02-22 14:17:20 -05:00
LangChain4j
74d898e37d Added LangChain4j links (#1690) 2024-02-22 14:09:08 -05:00
Yuan-Man
c6e8b00718 Add README.md (#2249) 2024-02-22 14:03:44 -05:00
B-Tocs.org Community
be9980ef13 Update README.md - Ollama for SAP ABAP (#2510) 2024-02-22 13:12:27 -05:00
Augustinas Malinauskas
646a0dedb9 Update README.md (#2504)
- Enchanted is now supported for desktop on macOS
2024-02-22 13:09:29 -05:00
Azhar Khan
7f964d938c update README to add Gemma 2B, 7B model in Model Library Table (#2686) 2024-02-22 13:07:47 -05:00
Pavel Frankov
e6b8a139ff Update README.md (#2138) 2024-02-22 10:52:36 -05:00
Jeffrey Morgan
bdc0ea1ba5 Update import.md 2024-02-22 02:08:03 -05:00
Jeffrey Morgan
7fab7918cc Update import.md 2024-02-22 02:06:24 -05:00
Michael Yang
74c1bdba0d Merge pull request #2657 from joshyan1/patch-1
Update install.sh success message
2024-02-21 15:55:20 -08:00
Josh
f983ef7f5f Update install.sh success message 2024-02-21 18:30:01 -05:00
Jeffrey Morgan
1ae1c33651 Windows build + installer adjustments (#2656)
* remove `-w -s` linker flags on windows

* use `zip` for windows installer compression
2024-02-21 18:21:26 -05:00
Michael Yang
084d846621 refactor 2024-02-21 13:42:48 -08:00
Michael Yang
6a4b994433 lint 2024-02-21 13:42:48 -08:00
Michael Yang
bea007deb7 use LimitGroup for uploads 2024-02-21 13:42:48 -08:00
Michael Yang
074934be03 adjust group limit based on download speed 2024-02-21 13:42:48 -08:00
Michael Yang
0de12368a0 add new LimitGroup for dynamic concurrency 2024-02-21 13:42:48 -08:00
Michael Yang
917bd61084 refactor download run 2024-02-21 13:42:46 -08:00
Jeffrey Morgan
efe040f8c0 reset with init_vars ahead of each cpu build in gen_windows.ps1 (#2654) 2024-02-21 16:35:34 -05:00
Jeffrey Morgan
2a7553ce09 update llama.cpp submodule to c14f72d 2024-02-21 09:03:14 -05:00
Sun Bo
10af6070a9 Update big-AGI config file link (#2626)
Co-authored-by: bo.sun <bo.sun@cotticoffee.com>
2024-02-21 01:24:48 -05:00
Jeffrey Morgan
92423b0600 add dist directory in build_windows.ps 2024-02-21 00:05:05 -05:00
Jeffrey Morgan
b3eac61cac update llama.cpp submodule to f0d1fafc029a056cd765bdae58dcaa12312e9879 2024-02-20 22:56:51 -05:00
Jeffrey Morgan
287ba11500 better error message when calling /api/generate or /api/chat with embedding models 2024-02-20 21:53:45 -05:00
Jeffrey Morgan
63861f58cc Support for bert and nomic-bert embedding models 2024-02-20 21:37:29 -05:00
Jeffrey Morgan
f0425d3de9 Update faq.md 2024-02-20 20:44:45 -05:00
Michael Yang
210b65268e replace strings buffer with hasher (#2437)
the buffered value is going into the hasher eventually so write directly
to the hasher instead
2024-02-20 19:07:50 -05:00
Michael Yang
949d7b1c48 add gguf file types (#2532) 2024-02-20 19:06:29 -05:00
Michael Yang
897b213468 use http.DefaultClient (#2530)
default client already handles proxy
2024-02-20 18:34:47 -05:00
Jeffrey Morgan
4613a080e7 update llama.cpp submodule to 66c1968f7 (#2618) 2024-02-20 17:42:31 -05:00
Muhammed Nazeem
ace2cdf1c6 Add Page Assist to the community integrations (#2447) 2024-02-20 14:03:58 -05:00
Nikesh Parajuli
eed92bc19a docs: add Msty app in readme (#1775)
* docs: add Msty app in readme

* docs: update msty url
2024-02-20 14:03:33 -05:00
Michael Edoror
e0a2f46466 Update README.md to include Elixir LangChain Library (#2180)
The Elixir LangChain Library now supports Ollama Chat with this [PR](https://github.com/brainlid/langchain/pull/70)
2024-02-20 14:03:02 -05:00
Taras Tsugrii
01ff2e14db [nit] Remove unused msg local var. (#2511) 2024-02-20 14:02:34 -05:00
BADR
199e79ec0c docs: add tenere to terminal clients (#2329) 2024-02-19 23:13:03 -05:00
Jeffrey Morgan
8125ce4cb6 Update import.md
Add instructions to get public key on windows
2024-02-19 22:48:24 -05:00
Daniel
636d6eea99 Add ShellOracle to community terminal integrations (#1767) 2024-02-19 22:18:05 -05:00
Jeffrey Morgan
df56f1ee5e Update faq.md 2024-02-19 22:16:42 -05:00
Jean-Baptiste Detroyes
0b6c6c9092 feat: add Helm Chart link to Package managers list (#1673) 2024-02-19 22:05:14 -05:00
Jakob Hoeg Mørk
cb60389de7 NextJS web interface for Ollama (#2466) 2024-02-19 21:57:36 -05:00
lulz
ce0c95d097 [fix] /bye and /exit are now treated as prefixes (#2381)
* [fix] /bye and /exit are now treated as prefixes
instead of being treated as entire lines which doesn't align with the way the rest of the commands are treated

* Update cmd/interactive.go

Fixing whitespace

---------

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2024-02-19 21:56:49 -05:00
Eddú Meléndez Gonzales
a9bc1e1c37 Add LangChain4J (#2164) 2024-02-19 21:17:32 -05:00
Branislav Gerazov
62c71f4cb1 add ollama-chat.nvim (#2188) 2024-02-19 21:14:29 -05:00
Jeffrey Morgan
41aca5c2d0 Update faq.md 2024-02-19 21:11:01 -05:00
Jeffrey Morgan
753724d867 Update api.md to include examples for reproducible outputs 2024-02-19 20:36:16 -05:00
Jeffrey Morgan
e4576c2ee1 Update README.md 2024-02-19 20:15:24 -05:00
Patrick Devine
9a7a4b9533 add faqs for memory pre-loading and the keep_alive setting (#2601) 2024-02-19 14:45:25 -08:00
Daniel Hiltgen
2653191222 Merge pull request #2600 from dhiltgen/refined_win_docs
Document setting server vars for windows
2024-02-19 13:46:37 -08:00
Daniel Hiltgen
b338c0635f Document setting server vars for windows 2024-02-19 13:30:46 -08:00
Daniel Hiltgen
4fcbf1cde6 Merge pull request #2599 from dhiltgen/fix_avx
Explicitly disable AVX2 on GPU builds
2024-02-19 13:13:05 -08:00
Daniel Hiltgen
9220b4fa91 Merge pull request #2585 from dhiltgen/cuda_leaks
Fix cuda leaks
2024-02-19 12:48:00 -08:00
Daniel Hiltgen
fc39a6cd7a Fix cuda leaks
This should resolve the problem where we don't fully unload from the GPU
when we go idle.
2024-02-18 18:37:20 -08:00
Justin Hayes
1e23e82324 Update Web UI link to new project name (#2563)
Ollama WebUI is now known as Open WebUI.
2024-02-17 20:05:20 -08:00
Daniel Hiltgen
f9fd08040b Merge pull request #2552 from dhiltgen/dup_update_menus
Fix duplicate menus on update and exit on signals
2024-02-16 17:23:37 -08:00
Daniel Hiltgen
4318e35ee3 Merge pull request #2553 from dhiltgen/amdgpu_version
Harden AMD driver lookup logic
2024-02-16 17:23:12 -08:00
Daniel Hiltgen
9754c6d9d8 Harden AMD driver lookup logic
It looks like the version file doesnt exist on older(?) drivers
2024-02-16 16:20:16 -08:00
Daniel Hiltgen
a497235a55 Fix view logs menu 2024-02-16 15:42:53 -08:00
Daniel Hiltgen
df6dc4fd96 Fix duplicate menus on update and exit on signals
Also fixes a few fit-and-finish items for better developer experience
2024-02-16 15:33:16 -08:00
Bruce MacDonald
88622847c6 fix: chat system prompting overrides (#2542) 2024-02-16 14:42:43 -05:00
Tristan Rhodes
9774663013 Update faq.md with the location of models on Windows (#2545) 2024-02-16 11:04:19 -08:00
Daniel Hiltgen
a468ae0459 Merge pull request #2499 from ollama/windows-preview
Windows Preview
2024-02-15 16:06:32 -08:00
Daniel Hiltgen
c3e62ba38a Merge pull request #2516 from dhiltgen/single_tray_app
Fix a couple duplicate instance bugs
2024-02-15 15:52:43 -08:00
Daniel Hiltgen
117369aa73 Exit if we detect another copy of Ollama running 2024-02-15 14:58:29 -08:00
Daniel Hiltgen
1ba734de67 typo 2024-02-15 14:56:55 -08:00
Daniel Hiltgen
5208cf09b1 clean up some logging 2024-02-15 14:56:55 -08:00
Daniel Hiltgen
bb9de6037c Prevent multiple installers running concurrently 2024-02-15 14:56:55 -08:00
Daniel Hiltgen
272e53a1f5 Prepare to distribute standalone windows executable
This will be useful for our automated test riggig, and may be useful for
advanced users who want to "roll their own" system service
2024-02-15 14:56:55 -08:00
Daniel Hiltgen
db2a9ad1fe Explicitly disable AVX2 on GPU builds
Even though we weren't setting it to on, somewhere in the cmake config
it was getting toggled on.  By explicitly setting it to off, we get `/arch:AVX`
as intended.
2024-02-15 14:50:11 -08:00
Daniel Hiltgen
c9ab1aead3 Merge pull request #2526 from dhiltgen/harden_for_quotes
Harden the OLLAMA_HOST lookup for quotes
2024-02-15 14:13:40 -08:00
Daniel Hiltgen
4a10e7a7fa Harden the OLLAMA_HOST lookup for quotes 2024-02-15 13:46:56 -08:00
Michael Yang
86808f80a8 remove unused import 2024-02-15 12:09:11 -08:00
Michael Yang
4240b045e6 always enable view logs 2024-02-15 12:08:27 -08:00
Michael Yang
e547378893 disable default debug 2024-02-15 12:05:13 -08:00
Michael Yang
fd77dbec4d do not print update request headers 2024-02-15 11:36:35 -08:00
Michael
fefb3e77d1 Update README.md 2024-02-15 10:32:40 -08:00
Jeffrey Morgan
ed5489a96e higher resolution tray icons 2024-02-14 22:55:03 -08:00
jmorganca
76113742cf update installer title 2024-02-15 05:56:45 +00:00
Jeffrey Morgan
57e60c836f better windows app and tray icons 2024-02-15 05:56:45 +00:00
jmorganca
622b1f3e67 update installer and app.exe metadata 2024-02-15 05:56:45 +00:00
jmorganca
7ad9844ac0 set exe metadata using resource files 2024-02-15 05:56:45 +00:00
Michael Yang
e43648afe5 rerefactor 2024-02-15 05:56:45 +00:00
Daniel Hiltgen
823a520266 Fix lint error on ignored error for win console 2024-02-15 05:56:45 +00:00
vinjn
66ef308abd Import "containerd/console" lib to support colorful output in Windows terminal 2024-02-15 05:56:45 +00:00
Daniel Hiltgen
29e90cc13b Implement new Go based Desktop app
This focuses on Windows first, but coudl be used for Mac
and possibly linux in the future.
2024-02-15 05:56:45 +00:00
Daniel Hiltgen
f397e0e988 Move hub auth out to new package 2024-02-15 05:56:45 +00:00
Daniel Hiltgen
9da9e8fb72 Move Mac App to a new dir 2024-02-15 05:56:45 +00:00
Patrick Devine
42e77e2a69 handle race condition while setting raw mode in windows (#2509) 2024-02-14 21:28:35 -08:00
Jeffrey Morgan
9241a29336 Revert "Revert "bump submodule to 6c00a06 (#2479)"" (#2485)
This reverts commit 6920964b87.
2024-02-13 18:18:41 -08:00
Jeffrey Morgan
f7231ad9ad set shutting_down to false once shutdown is complete (#2484) 2024-02-13 17:48:41 -08:00
Jeffrey Morgan
6920964b87 Revert "bump submodule to 6c00a06 (#2479)"
This reverts commit 2f9ed52bbd.
2024-02-13 17:23:05 -08:00
Jeffrey Morgan
2f9ed52bbd bump submodule to 6c00a06 (#2479) 2024-02-13 17:12:42 -08:00
bnorick
caf2b13c10 Fix infinite keep_alive (#2480) 2024-02-13 15:40:32 -08:00
lebrunel
1d263449ff Update README.md to include link to Ollama-ex Elixir library (#2477) 2024-02-13 11:40:44 -08:00
Jeffrey Morgan
48a273f80b Fix issues with templating prompt in chat mode (#2460) 2024-02-12 15:06:57 -08:00
Daniel Hiltgen
939c60473f Merge pull request #2422 from dhiltgen/better_kill
More robust shutdown
2024-02-12 14:05:06 -08:00
Jeffrey Morgan
f76ca04f9e update submodule to 099afc6 (#2468) 2024-02-12 14:01:16 -08:00
Daniel Hiltgen
76b8728f0c Merge pull request #2465 from dhiltgen/block_rocm_pre_9
Detect AMD GPU info via sysfs and block old cards
2024-02-12 12:41:43 -08:00
Jeffrey Morgan
1f9078d6ae Check image filetype in api handlers (#2467) 2024-02-12 11:16:20 -08:00
Daniel Hiltgen
6d84f07505 Detect AMD GPU info via sysfs and block old cards
This wires up some new logic to start using sysfs to discover AMD GPU
information and detects old cards we can't yet support so we can fallback to CPU mode.
2024-02-12 08:19:41 -08:00
Jeffrey Morgan
26b13fc33c patch: always add token to cache_tokens (#2459) 2024-02-12 08:10:16 -08:00
Jeffrey Morgan
1c8435ffa9 Update domain name references in docs and install script (#2435) 2024-02-09 15:19:30 -08:00
Daniel Hiltgen
6680761596 Shutdown faster
Make sure that when a shutdown signal comes, we shutdown quickly instead
of waiting for a potentially long exchange to wrap up.
2024-02-08 22:22:50 -08:00
Jeffrey Morgan
42b797ed9c Update openai.md 2024-02-08 15:03:23 -05:00
Jeffrey Morgan
336aa43f3c Update openai.md 2024-02-08 12:48:28 -05:00
Daniel Hiltgen
69f392c9b7 Merge pull request #2403 from dhiltgen/handle_tmp_cleanup
Ensure the libraries are present
2024-02-07 17:55:31 -08:00
Daniel Hiltgen
a1dfab43b9 Ensure the libraries are present
When we store our libraries in a temp dir, a reaper might clean
them when we are idle, so make sure to check for them before
we reload.
2024-02-07 17:27:49 -08:00
Jeffrey Morgan
a0a199b108 Fix hanging issue when sending empty content (#2399) 2024-02-07 19:30:33 -05:00
Jeffrey Morgan
ab0d37fde4 Update openai.md 2024-02-07 17:25:33 -05:00
Jeffrey Morgan
14e71350c8 Update openai.md 2024-02-07 17:25:24 -05:00
Jeffrey Morgan
453f572f83 Initial OpenAI /v1/chat/completions API compatibility (#2376) 2024-02-07 17:24:29 -05:00
Daniel Hiltgen
c9dfa6e571 Merge pull request #2377 from dhiltgen/bump_llamacpp
Bump llama.cpp to b2081
2024-02-07 12:04:38 -08:00
Michael Yang
3dcbcd367d Merge pull request #2394 from ollama/mxyng/fix-error-response 2024-02-07 11:47:31 -08:00
Michael Yang
e805ac1d59 fix response on token error 2024-02-07 11:05:49 -08:00
Michael Yang
b9229ffca5 Merge pull request #2378 from ollama/mxyng/runners
runners
2024-02-06 13:49:58 -08:00
Michael Yang
46c847c4ad enable rocm builds 2024-02-06 13:36:13 -08:00
Michael Yang
92b1a21f79 use linux runners 2024-02-06 13:36:04 -08:00
Daniel Hiltgen
de76b95dd4 Bump llama.cpp to b2081 2024-02-06 12:06:43 -08:00
Michael Yang
59ec837ef6 Merge pull request #2374 from ollama/mxyng/rocm-builds
disable rocm builds
2024-02-06 09:41:02 -08:00
Michael Yang
f06b99a461 disable rocm builds 2024-02-06 09:29:42 -08:00
Bruce MacDonald
128fce5495 docs: keep_alive (#2258) 2024-02-06 11:00:05 -05:00
Daniel Hiltgen
27aa2d4a19 Merge pull request #1849 from mraiser/main
Accomodate split cuda lib dir
2024-02-05 16:01:16 -08:00
Jeffrey Morgan
b9f91a0b36 Update import instructions to use convert and quantize tooling from llama.cpp submodule (#2247) 2024-02-05 00:50:44 -05:00
Erik S
b538dc3858 Add llm-ollama plugin for Datasette's LLM CLI to README (#2340)
Co-authored-by: Erik Sp <git@aschwa.com>
2024-02-03 15:40:50 -08:00
Jeffrey Morgan
f0e9496c85 Update api.md 2024-02-02 12:17:24 -08:00
Jeffrey Morgan
09a6f76f4c fix error on ollama run with a non-existent model 2024-02-01 23:11:52 -08:00
Jeffrey Morgan
e135167484 Add multimodel support to ollama run in noninteractive mopde (#2317) 2024-02-01 21:33:06 -08:00
Jeffrey Morgan
38296ab352 clear previous images when submitting an image to ollama run (#2316) 2024-02-01 21:30:26 -08:00
Daniel Hiltgen
f43dea68d1 Merge pull request #2318 from dhiltgen/more_clean
Harden generate patching model
2024-02-01 20:41:29 -08:00
Daniel Hiltgen
e1f50377f4 Harden generate patching model
Only apply patches if we have any, and make sure to cleanup
every file we patched at the end to leave the tree clean
2024-02-01 19:34:36 -08:00
Jeffrey Morgan
7913104527 Improvements to ollama run for multimodal models (#2300) 2024-02-01 17:09:51 -08:00
Michael Yang
bfbf2f7cf7 Merge pull request #2296 from ollama/mxyng/img-tags
append image tags to user content
2024-02-01 13:16:59 -08:00
Michael Yang
fe3cbd014f Merge pull request #2298 from ollama/mxyng/debug-prompt
structured debug prompt
2024-02-01 13:16:49 -08:00
Michael Yang
3d6f48507a structured debug prompt 2024-02-01 11:56:28 -08:00
Michael Yang
f3761405c8 use image id 2024-02-01 11:52:42 -08:00
Michael Yang
e49dc9f3d8 fix tests 2024-02-01 11:48:11 -08:00
Michael Yang
d125510b4b remove image tags 2024-02-01 11:32:51 -08:00
Russell Canfield
1ca386aa9e Feature - Add Wingman Extension (#2313) 2024-02-01 11:16:24 -08:00
Michael Yang
fb56988014 account for image projection in token count 2024-02-01 09:50:48 -08:00
Michael Yang
d046bee790 use llm.ImageData for chat 2024-01-31 19:18:25 -08:00
Jeffrey Morgan
f11bf0740b use llm.ImageData 2024-01-31 19:13:48 -08:00
Michael Yang
8450bf66e6 trim images 2024-01-31 19:13:47 -08:00
Michael Yang
b4e11be8ef append image tags to user content 2024-01-31 19:13:10 -08:00
Bruce MacDonald
a896079705 preserve last system message from modelfile (#2289) 2024-01-31 21:45:01 -05:00
Michael Yang
583950c828 Merge pull request #2294 from ollama/mxyng/slog-source
update slog handler options
2024-01-31 15:29:11 -08:00
Michael Yang
8ac08a0eec update slog handler options
- consistent format by using text handler for debug and non-debug
- truncate source file to just the file name
2024-01-31 15:15:00 -08:00
Michael Yang
60f47be64c Merge pull request #2284 from ollama/mxyng/parse-raw
remove unnecessary parse raw
2024-01-31 09:40:48 -08:00
Daniel Hiltgen
6e56077ada Merge pull request #2263 from dhiltgen/bump_llamacpp
Bump llama.cpp to b1999
2024-01-31 08:39:41 -08:00
Hoang Nguyen
98ae9467bb Added MindMac to Community Integrations -> Web & Desktop section (#1957) 2024-01-31 07:48:37 -08:00
Richard Macarthy
b7a24af083 Add twinny vscode extension to Extensions and Plugins (#1950) 2024-01-31 06:25:06 -08:00
Michael Yang
c8b1f2369e remove unnecessary parse raw 2024-01-30 17:00:53 -08:00
Daniel Hiltgen
72b12c3be7 Bump llama.cpp to b1999
This requires an upstream change to support graceful termination,
carried as a patch.
2024-01-30 16:52:12 -08:00
Bruce MacDonald
0632dff3f8 trim chat prompt based on llm context size (#1963) 2024-01-30 15:59:29 -05:00
Maximilian Weber
509e2dec8a Update README.md (#2252)
Added - [Ollama for R - rollama](https://github.com/JBGruber/rollama) in Libraries in README.md
2024-01-30 11:56:51 -08:00
Daniel Hiltgen
78a48de804 Merge pull request #2256 from dhiltgen/container_logs
Add container hints for troubleshooting
2024-01-30 08:12:48 -08:00
Daniel Hiltgen
e7dbb00331 Add container hints for troubleshooting
Some users are new to containers and unsure where the server logs go
2024-01-29 08:53:41 -08:00
Marc Raiser
c3f9538636 remove default.nix 2024-01-29 00:05:07 -05:00
Jeffrey Morgan
2e06ed01d5 remove unknown CPPFLAGS option 2024-01-28 17:51:23 -08:00
Daniel Hiltgen
4072b5879b Merge pull request #2246 from dhiltgen/reject_cuda_without_avx
Don't disable GPUs on arm without AVX
2024-01-28 16:26:55 -08:00
Daniel Hiltgen
15562e887d Don't disable GPUs on arm without AVX
AVX is an x86 feature, so ARM should be excluded from
the check.
2024-01-28 15:22:38 -08:00
Jeffrey Morgan
f2245c7c77 print prompt with OLLAMA_DEBUG=1 (#2245) 2024-01-28 15:22:35 -08:00
Jeffrey Morgan
e4b9b72f2a Do not repeat system prompt for chat templating (#2241) 2024-01-28 14:15:56 -08:00
Daniel Hiltgen
311f8e0c3f Merge pull request #2243 from dhiltgen/harden_zero_gpus
Harden for zero detected GPUs
2024-01-28 13:30:44 -08:00
Daniel Hiltgen
f07f8b7a9e Harden for zero detected GPUs
At least with the ROCm libraries, its possible to have the library
present with zero GPUs.  This fix avoids a divide by zero bug in llm.go
when we try to calculate GPU memory with zero GPUs.
2024-01-28 13:13:10 -08:00
mraiser
4c4c730a0a Merge branch 'ollama:main' into main 2024-01-27 21:56:11 -05:00
Daniel Hiltgen
e02ecfb6c8 Merge pull request #2116 from dhiltgen/cc_50_80
Add support for CUDA 5.0 cards
2024-01-27 10:28:38 -08:00
Daniel Hiltgen
c8059b4dcf Merge pull request #2224 from jaglinux/fix_rocm_get_version_message
ROCm: Correct the response string in rocm_get_version function
2024-01-27 07:29:32 -08:00
Jagadish Krishnamoorthy
59d87127f5 Update gpu_info_rocm.c 2024-01-26 22:08:27 -08:00
Patrick Devine
b5cf31b460 add keep_alive to generate/chat/embedding api endpoints (#2146) 2024-01-26 14:28:02 -08:00
Daniel Hiltgen
cc4915e262 Merge pull request #2214 from dhiltgen/reject_cuda_without_avx
Detect lack of AVX and fallback to CPU mode
2024-01-26 12:06:44 -08:00
Daniel Hiltgen
667a2ba18a Detect lack of AVX and fallback to CPU mode
We build the GPU libraries with AVX enabled to ensure that if not all
layers fit on the GPU we get better performance in a mixed mode.
If the user is using a virtualization/emulation system that lacks AVX
this used to result in an illegal instruction error and crash before this
fix.  Now we will report a warning in the server log, and just use
CPU mode to ensure we don't crash.
2024-01-26 11:36:03 -08:00
Michael Yang
e054ebe059 Merge pull request #2212 from ollama/mxyng/fix-build
fix build
2024-01-26 11:19:08 -08:00
Michael Yang
9d3dcfd0ec fix logging 2024-01-26 11:04:27 -08:00
Michael Yang
6e0ea5ecc8 Merge pull request #1916 from ollama/mxyng/inactivity-monitor
download: add inactivity monitor
2024-01-26 10:56:00 -08:00
Daniel Hiltgen
a47d8b2557 Merge pull request #2197 from dhiltgen/remove_rocm_image
Add back ROCm container support
2024-01-26 09:34:23 -08:00
Daniel Hiltgen
30c43c285c Merge pull request #2195 from dhiltgen/rocm_real_gpus
Ignore AMD integrated GPUs
2024-01-26 09:30:24 -08:00
Daniel Hiltgen
23a7ea593b Merge pull request #2209 from dhiltgen/harden_mgmt
Fix crash on cuda ml init failure
2024-01-26 09:30:13 -08:00
Daniel Hiltgen
75c44aa319 Add back ROCm container support
This adds ROCm support back as a discrete image.
2024-01-26 09:24:29 -08:00
Daniel Hiltgen
9d7b5d6c91 Ignore AMD integrated GPUs
Detect and ignore integrated GPUs reported by rocm.
2024-01-26 09:21:35 -08:00
Daniel Hiltgen
5d9c4a5f5a Fix crash on cuda ml init failure
The new driver lookup code was triggering after init failure due to a missing return
2024-01-26 09:18:33 -08:00
Daniel Hiltgen
197e420a97 Merge pull request #2196 from dhiltgen/remove_rocm_image
Switch back to ubuntu base
2024-01-25 16:50:32 -08:00
Daniel Hiltgen
a34e1ad3cf Switch back to ubuntu base
The size increase for rocm support in the standard image is problematic
We'll revisit multiple tags for rocm support in a follow up PR.
2024-01-25 16:46:01 -08:00
Michael Yang
2ae0556292 Merge pull request #1679 from ollama/mxyng/build-gpus
build cuda and rocm
2024-01-25 16:38:14 -08:00
Jeffrey Morgan
5be9bdd444 Update modelfile.md 2024-01-25 16:29:48 -08:00
Jeffrey Morgan
b706794905 Update modelfile.md to include MESSAGE 2024-01-25 16:29:32 -08:00
Michael Yang
a8c5413d06 only generate gpu libs 2024-01-25 15:41:56 -08:00
Michael Yang
5580de4571 archive ollama binaries 2024-01-25 15:40:16 -08:00
Michael Yang
946431d5b0 build cuda and rocm 2024-01-25 15:40:15 -08:00
Michael Yang
0610126049 remove env setting 2024-01-25 15:39:43 -08:00
Jeffrey Morgan
3ebd6a83fc update submodule to cd4fddb29f81d6a1f6d51a0c016bc6b486d68def 2024-01-25 13:54:11 -08:00
Jeffrey Morgan
a64570dcae Fix clearing kv cache between requests with the same prompt (#2186)
* Fix clearing kv cache between requests with the same prompt

* fix powershell script
2024-01-25 13:46:20 -08:00
Patrick Devine
7c40a67841 Save and load sessions (#2063) 2024-01-25 12:12:36 -08:00
Michael Yang
e64b5b07a2 Merge pull request #2181 from ollama/mxyng/stub-lint
stub generate outputs for lint
2024-01-25 11:55:15 -08:00
Michael Yang
9e1e295cdc Merge pull request #2175 from ollama/mxyng/refactor-tensor-read
refactor tensor read
2024-01-25 09:22:42 -08:00
Marc Raiser
6eb3cddcb6 To build on NixOS: nix-shell --run 'go generate ./... && go build .' 2024-01-25 10:17:22 -05:00
mraiser
a4564232a4 Update gen_linux.sh to find libcudart in separate directory 2024-01-25 09:49:35 -05:00
Jeffrey Morgan
a643823f86 Update README.md 2024-01-24 21:36:56 -08:00
Michael Yang
8e5d359a03 stub generate outputs for lint 2024-01-24 17:36:10 -08:00
Daniel Hiltgen
a170888dd4 Merge pull request #2174 from dhiltgen/rocm_real_gpus
More logging for gpu management
2024-01-24 11:09:17 -08:00
Michael Yang
cd22855ef8 refactor tensor read 2024-01-24 10:48:31 -08:00
Daniel Hiltgen
013fd07139 More logging for gpu management
Fix an ordering glitch of dlerr/dlclose and add more logging to help
root cause some crashes users are hitting. This also refines the
function pointer names to use the underlying function names instead
of simplified names for readability.
2024-01-24 10:32:36 -08:00
Daniel Hiltgen
f63dc2db5c Merge pull request #2162 from dhiltgen/rocm_real_gpus
Report more information about GPUs in verbose mode
2024-01-23 17:45:40 -08:00
Jeffrey Morgan
eaa5a396d9 Update README.md 2024-01-23 16:08:15 -08:00
Jeffrey Morgan
8ed22f5d72 Update README.md 2024-01-23 14:38:01 -08:00
Daniel Hiltgen
987c16b2f7 Report more information about GPUs in verbose mode
This adds additional calls to both CUDA and ROCm management libraries to
discover additional attributes about the GPU(s) detected in the system, and
wires up runtime verbosity selection.  When users hit problems with GPUs we can
ask them to run with `OLLAMA_DEBUG=1 ollama serve` and share the results.
2024-01-23 11:37:02 -08:00
Jeffrey Morgan
950f636d64 Update README.md 2024-01-23 10:29:10 -08:00
Jeffrey Morgan
4458efb73a Load all layers on arm64 macOS if model is small enough (#2149) 2024-01-22 17:40:06 -08:00
Daniel Hiltgen
ceea599494 Merge pull request #2150 from dhiltgen/default_version
Set a default version using git describe
2024-01-22 17:38:27 -08:00
Daniel Hiltgen
3005ec74b3 Set a default version using git describe
If a VERSION is not specified, this will generate a version string that
represents the state of the repo.  For example `0.1.21-12-gffaf52e-dirty`
representing 12 commits away from 0.1.21 tag, on commit gffaf52e
and the tree is dirty.
2024-01-22 17:12:20 -08:00
Daniel Hiltgen
0759d8996e Merge pull request #2148 from dhiltgen/intel_mac
Refine Accelerate usage on mac
2024-01-22 16:56:58 -08:00
Daniel Hiltgen
0f5b843319 Refine Accelerate usage on mac
For old macs, accelerate seems to cause crashes, but for
AVX2 capable macs, it does not.
2024-01-22 16:25:56 -08:00
Jeffrey Morgan
ffaf52e1e9 update submodule to 011e8ec577fd135cbc02993d3ea9840c516d6a1c 2024-01-22 15:16:54 -08:00
Michael Yang
940b10b036 Merge pull request #2144 from jmorganca/mxyng/update-faq
faq: update to use launchctl setenv
2024-01-22 13:46:57 -08:00
Daniel Hiltgen
3bc28736cd Merge pull request #2143 from dhiltgen/llm_verbosity
Refine debug logging for llm
2024-01-22 13:19:16 -08:00
Michael Yang
93a756266c faq: update to use launchctl setenv 2024-01-22 13:10:13 -08:00
Daniel Hiltgen
a0a829bf7a Merge pull request #2142 from dhiltgen/debug_on_fail
Debug logging on init failure
2024-01-22 12:29:22 -08:00
Daniel Hiltgen
730dcfcc7a Refine debug logging for llm
This wires up logging in llama.cpp to always go to stderr, and also
turns up logging if OLLAMA_DEBUG is set.
2024-01-22 12:26:49 -08:00
Daniel Hiltgen
27a2d5af54 Debug logging on init failure 2024-01-22 12:08:22 -08:00
Jeffrey Morgan
5f81a33f43 update submodule to 6f9939d (#2115) 2024-01-22 11:56:40 -08:00
Michael Yang
6225fde046 Merge pull request #2102 from jmorganca/mxyng/fix-create-override
fix: remove overwritten model layers
2024-01-22 09:37:48 -08:00
Meng Zhuo
069184562b readline: drop not use min function (#2134) 2024-01-22 08:15:08 -08:00
Daniel Hiltgen
5576bb2348 Merge pull request #2130 from dhiltgen/more_faster
Make CPU builds parallel and customizable AMD GPUs
2024-01-21 16:14:12 -08:00
Daniel Hiltgen
2738837786 Merge pull request #2131 from dhiltgen/probe_cards_at_init
Probe GPUs before backend init
2024-01-21 16:13:47 -08:00
Daniel Hiltgen
ec3764538d Probe GPUs before backend init
Detect potential error scenarios so we can fallback to CPU mode without
hitting asserts.
2024-01-21 15:59:38 -08:00
Daniel Hiltgen
df54c723ae Make CPU builds parallel and customizable AMD GPUs
The linux build now support parallel CPU builds to speed things up.
This also exposes AMD GPU targets as an optional setting for advaced
users who want to alter our default set.
2024-01-21 15:12:21 -08:00
Daniel Hiltgen
fa8c990e58 Merge pull request #2127 from dhiltgen/rocm_container
Combine the 2 Dockerfiles and add ROCm
2024-01-21 11:49:01 -08:00
Daniel Hiltgen
da72235ebf Combine the 2 Dockerfiles and add ROCm
This renames Dockerfile.build to Dockerfile, and adds some new stages
to support 2 modes of building - the build_linux.sh script uses
intermediate stages to extract the artifacts for ./dist, and the default
build generates a container image usable by both cuda and rocm cards.
This required transitioniing the x86 base to the rocm image to avoid
layer bloat.
2024-01-21 11:37:11 -08:00
Jeffrey Morgan
89c4aee29e Unlock mutex when failing to load model (#2117) 2024-01-20 20:54:46 -05:00
Daniel Hiltgen
a447a083f2 Add compute capability 5.0, 7.5, and 8.0 2024-01-20 14:24:05 -08:00
Jeffrey Morgan
f32ea81b21 increase minimum overhead to 1024MiB (#2114) 2024-01-20 17:11:38 -05:00
Daniel Hiltgen
681a914990 Add support for CUDA 5.2 cards 2024-01-20 10:48:43 -08:00
Jeffrey Morgan
4c54f0ddeb sign dylibs on macOS (#2101) 2024-01-19 19:24:11 -05:00
Michael Yang
c08dfaa23d fix: remove overwritten model layers
if create overrides a manifest, first add the older manifest's layers to
the delete map so they can be cleaned up
2024-01-19 14:58:37 -08:00
Daniel Hiltgen
3b76e736ae Merge pull request #2100 from dhiltgen/more_wsl_globs
More WSL paths
2024-01-19 13:41:08 -08:00
Daniel Hiltgen
552db98bf1 More WSL paths 2024-01-19 13:23:29 -08:00
Daniel Hiltgen
fdcdfef620 Merge pull request #2099 from dhiltgen/fix_cuda_model_swap
Switch to local dlopen symbols
2024-01-19 12:22:04 -08:00
Daniel Hiltgen
6a042438af Switch to local dlopen symbols 2024-01-19 11:37:02 -08:00
Jeffrey Morgan
dc88cc3981 use gzip for runner embedding (#2067) 2024-01-19 13:23:03 -05:00
Daniel Hiltgen
62976087c6 Merge pull request #1999 from lainedfles/termux_android_cpu_only
Fix CPU-only build under Android Termux enviornment.
2024-01-18 17:16:53 -08:00
Self Denial
344342abdf Restore dyn_ext_server.c since RTLD_DEEPBIND has been removed 2024-01-18 17:30:42 -07:00
Self Denial
eb76f3e379 Fix CPU-only build under Android Termux enviornment.
Update gpu.go initGPUHandles() to declare gpuHandles variable before
reading it. This resolves an "invalid memory address or nil pointer
dereference" error.

Update dyn_ext_server.c to avoid setting the RTLD_DEEPBIND flag under
__TERMUX__ (Android).
2024-01-18 17:25:33 -07:00
Michael Yang
d017e3d0a6 Merge pull request #2060 from jmorganca/mxyng/fix-show
fix show handler
2024-01-18 16:02:27 -08:00
Michael Yang
aac9ab4db7 fix show handler 2024-01-18 15:36:50 -08:00
Michael Yang
1f5b7ff976 Merge pull request #1932 from jmorganca/mxyng/api-fields
api: add model for all requests
2024-01-18 14:56:51 -08:00
Michael Yang
e299831e2c Merge pull request #1958 from purificant/ci
ci: update setup-go action
2024-01-18 14:53:36 -08:00
Michael Yang
745b5934fa add model to ModelResponse 2024-01-18 14:32:55 -08:00
Michael Yang
a38d88d828 api: add model for all requests
prefer using req.Model and fallback to req.Name
2024-01-18 14:31:37 -08:00
Daniel Hiltgen
abec7f06e5 Merge pull request #2056 from dhiltgen/slog
Mechanical switch from log to slog
2024-01-18 14:27:24 -08:00
Michael Yang
e5da190bac Merge pull request #2020 from jmorganca/mxyng/install-fedora
install: pin fedora to max 37
2024-01-18 14:23:42 -08:00
Daniel Hiltgen
ecbfc0182f Go bump to v1.21 to pick up slog 2024-01-18 14:12:57 -08:00
Daniel Hiltgen
fedd705aea Mechanical switch from log to slog
A few obvious levels were adjusted, but generally everything mapped to "info" level.
2024-01-18 14:12:57 -08:00
Mike Bird
82ee019bfc add open interpreter to list of extensions (#2016) 2024-01-18 13:59:39 -08:00
Sachin Sachdeva
ad9dbc2a04 Haystack Ollama Integration (#2021)
Updated readme with the web link for haystack ollama integration
2024-01-18 13:38:32 -08:00
Daniel Hiltgen
fccdf4c635 Merge pull request #1987 from xyproto/archlinux
Let gpu.go and gen_linux.sh also find CUDA on Arch Linux
2024-01-18 13:32:10 -08:00
Daniel Hiltgen
d450fb1d1e Merge pull request #2055 from dhiltgen/cuda_docs
Refine the linux cuda/rocm developer docs
2024-01-18 12:07:31 -08:00
Daniel Hiltgen
df40b11d03 Merge pull request #2007 from dhiltgen/cpu_fallback
Add multiple CPU variants for Intel Mac
2024-01-18 11:32:29 -08:00
Daniel Hiltgen
9cd20b0ec8 Refine the linux cuda/rocm developer docs 2024-01-18 09:44:44 -08:00
Daniel Hiltgen
b992bf65fc Disable arm64 for test phase
The runners are x86 so we can only run binaries that match.
2024-01-17 19:26:13 -08:00
Daniel Hiltgen
1b249748ab Add multiple CPU variants for Intel Mac
This also refines the build process for the ext_server build.
2024-01-17 15:08:54 -08:00
Alexander F. Rødseth
cbe2adc78a Merge branch 'main' into archlinux 2024-01-17 12:50:11 +01:00
Michael Yang
d5a7353357 Merge pull request #2026 from jmorganca/mxyng/fix-windows
fix: normalize name path before splitting
2024-01-16 16:58:42 -08:00
Michael Yang
96cfb62641 fix: normalize name path before splitting 2024-01-16 16:48:29 -08:00
Daniel Hiltgen
7d00b5d110 Merge pull request #1915 from dhiltgen/bump_llama_with_new_dep
Bump llama.cpp to b1842 and add new cuda lib dep
2024-01-16 13:36:49 -08:00
Daniel Hiltgen
795674dd90 Bump llama.cpp to b1842 and add new cuda lib dep
Upstream llama.cpp has added a new dependency with the
NVIDIA CUDA Driver Libraries (libcuda.so) which is part of the
driver distribution, not the general cuda libraries, and is not
available as an archive, so we can not statically link it.  This may
introduce some additional compatibility challenges which we'll
need to keep an eye on.
2024-01-16 12:53:52 -08:00
Daniel Hiltgen
e282bdccdd Merge pull request #1990 from dhiltgen/ci_mac_cross
Add macos cross-compile CI coverage
2024-01-16 12:31:37 -08:00
Michael Yang
d9bfb2f08f install: pin fedora to max 37
repos for fedora 38 and newer do not exist as of this commit

```
$ dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/fedora38/x86_64/cuda-fedora38.repo
Adding repo from: https://developer.download.nvidia.com/compute/cuda/repos/fedora38/x86_64/cuda-fedora38.repo
Status code: 404 for https://developer.download.nvidia.com/compute/cuda/repos/fedora38/x86_64/cuda-fedora38.repo (IP: 152.195.19.142)
Error: Configuration of repo failed
```
2024-01-16 11:45:21 -08:00
Michael Yang
598d6d5572 Merge pull request #1937 from jmorganca/mxyng/remove-client-py
remove client.py
2024-01-16 11:01:41 -08:00
Bruce MacDonald
a897e833b8 do not cache prompt (#2018)
- prompt cache causes inferance to hang after some time
2024-01-16 13:48:05 -05:00
Patrick Devine
eef50accb4 Fix show parameters (#2017) 2024-01-16 10:34:44 -08:00
Michael Yang
05d53de7a1 Merge pull request #1968 from jmorganca/mxyng/fix-request-retry
fix: request retry with error
2024-01-16 10:33:50 -08:00
Daniel Hiltgen
8795447dad Merge pull request #1966 from fpreiss/fpreiss/gen_linux_cuda_detection
improve cuda detection (rel. issue #1704)
2024-01-14 18:00:11 -08:00
Daniel Hiltgen
b3035112a1 Add macos cross-compile CI coverage 2024-01-14 10:38:59 -08:00
Daniel Hiltgen
95ad9a9fc8 Merge pull request #1988 from dhiltgen/fix_intel_mac
Fix typo in arm mac arch script
2024-01-14 08:45:18 -08:00
Daniel Hiltgen
3ca5f69ce8 Fix typo in arm mac arch script 2024-01-14 08:32:57 -08:00
Daniel Hiltgen
cfa6337960 Merge pull request #1982 from dhiltgen/fix_intel_mac
Fix intel mac build
2024-01-14 08:26:46 -08:00
Alexander F. Rødseth
f4bf1d514f Let gpu.go and gen_linux.sh also find CUDA on Arch Linux 2024-01-14 13:40:36 +01:00
Jeffrey Morgan
557110d0ba Disable mmap with lora layers (#1985) 2024-01-13 23:36:31 -05:00
Daniel Hiltgen
2ecb247276 Fix intel mac build
Make sure we're building an x86 ext_server lib when cross-compiling
2024-01-13 14:46:34 -08:00
Jeffrey Morgan
288ef8ff95 add gcc -lstdc++ flag for linux cpu (#1974) 2024-01-13 03:53:00 -05:00
Jeffrey Morgan
4cf17990f7 use g++ to build libext_server.so on linux (#1972) 2024-01-13 03:12:42 -05:00
Michael Yang
27331ae3a8 download: add inactivity monitor
if a download part is inactive for some time, restart it
2024-01-12 15:23:15 -08:00
Michael Yang
b6c0ef1e70 Merge pull request #1961 from jmorganca/mxyng/rm-double-newline
remove double newlines in /set parameter
2024-01-12 15:18:19 -08:00
Michael Yang
356d178f6e Merge pull request #1971 from jmorganca/mxyng/max-context-length
add max context length check
2024-01-12 15:10:25 -08:00
Michael Yang
eaed6f8c45 add max context length check 2024-01-12 14:54:07 -08:00
purificant
6a5bfc2ed6 update actions/setup-go 2024-01-12 22:27:25 +00:00
Michael Yang
cf29bd2d72 fix: request retry with error
this fixes a subtle bug with makeRequestWithRetry where an HTTP status
error on a retried request will potentially not return the right err
2024-01-12 13:32:27 -08:00
Fabian Preiss
905862e17b improve cuda detection (rel. issue #1704) 2024-01-12 21:59:19 +01:00
Patrick Devine
565f8a3c44 Convert the REPL to use /api/chat for interactive responses (#1936) 2024-01-12 12:05:52 -08:00
Michael Yang
5121b7ac9c remove double newlines in /set parameter 2024-01-12 11:21:15 -08:00
Michael Yang
a70262c6b2 Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2024-01-12 09:43:04 -08:00
Tristram Oaten
40a0a90a88 Add group delete to uninstall instructions (#1924)
After executing the `userdel ollama` command, I saw this message:

```sh
$ sudo userdel ollama
userdel: group ollama not removed because it has other members.
```

Which reminded me that I had to remove the dangling group too. For completeness, the uninstall instructions should do this too.

Thanks!
2024-01-12 00:07:00 -05:00
Michael Yang
cbe20c4375 update readme 2024-01-11 16:24:37 -08:00
Michael Yang
5ffbbea1d7 remove client.py 2024-01-11 15:53:10 -08:00
Daniel Hiltgen
3773fb6465 Merge pull request #1935 from dhiltgen/cpu_fallback
Fix up the CPU fallback selection
2024-01-11 15:52:32 -08:00
Daniel Hiltgen
7427fa1387 Fix up the CPU fallback selection
The memory changes and multi-variant change had some merge
glitches I missed.  This fixes them so we actually get the cpu llm lib
and best variant for the given system.
2024-01-11 15:27:06 -08:00
Michael Yang
f84537e0e0 Merge pull request #1934 from jmorganca/mxyng/fix-slices
fix build and lint
2024-01-11 14:36:20 -08:00
Michael Yang
d2be6387c9 fix typo 2024-01-11 14:25:21 -08:00
Michael Yang
d7af35d3d0 import fmt 2024-01-11 14:22:32 -08:00
Michael Yang
defc1dbd6e use x/exp/slices 2024-01-11 14:20:13 -08:00
Daniel Hiltgen
de2fbdec99 Merge pull request #1819 from dhiltgen/multi_variant
Support multiple LLM libs; ROCm v5 and v6; Rosetta, AVX, and AVX2 compatible CPU builds
2024-01-11 14:00:48 -08:00
Eduard van Valkenburg
f5faf79aa1 Add semantic kernel to Readme (#1931) 2024-01-11 14:40:23 -05:00
Michael Yang
f4f939de28 Merge pull request #1552 from jmorganca/mxyng/lint-test
add lint and test on pull_request
2024-01-11 09:37:45 -08:00
Daniel Hiltgen
39928a42e8 Always dynamically load the llm server library
This switches darwin to dynamic loading, and refactors the code now that no
static linking of the library is used on any platform
2024-01-11 08:42:47 -08:00
Daniel Hiltgen
d88c527be3 Build multiple CPU variants and pick the best
This reduces the built-in linux version to not use any vector extensions
which enables the resulting builds to run under Rosetta on MacOS in
Docker.  Then at runtime it checks for the actual CPU vector
extensions and loads the best CPU library available
2024-01-11 08:42:47 -08:00
Fabian Preiß
3bc8b9832b fix gpu_test.go Error (same type) uint64->uint32 (#1921) 2024-01-11 08:22:23 -05:00
Jeffrey Morgan
ab6be852c7 revisit memory allocation to account for full kv cache on main gpu 2024-01-11 01:45:31 -05:00
Daniel Hiltgen
052b33b81b DRY out the Dockefile.build 2024-01-10 17:27:51 -08:00
Daniel Hiltgen
8da7bef05f Support multiple variants for a given llm lib type
In some cases we may want multiple variants for a given GPU type or CPU.
This adds logic to have an optional Variant which we can use to select
an optimal library, but also allows us to try multiple variants in case
some fail to load.

This can be useful for scenarios such as ROCm v5 vs v6 incompatibility
or potentially CPU features.
2024-01-10 17:27:51 -08:00
Jeffrey Morgan
b24e8d17b2 Increase minimum CUDA memory allocation overhead and fix minimum overhead for multi-gpu (#1896)
* increase minimum cuda overhead and fix minimum overhead for multi-gpu

* fix multi gpu overhead

* limit overhead to 10% of all gpus

* better wording

* allocate fixed amount before layers

* fixed only includes graph alloc
2024-01-10 19:08:51 -05:00
Jeffrey Morgan
f83881390f revert submodule back to 328b83de23b33240e28f4e74900d1d06726f5eb1 2024-01-10 18:42:39 -05:00
Daniel Hiltgen
ac70ab6761 Merge pull request #1914 from dhiltgen/smarter_cuda_detection
Smarter GPU Management library detection
2024-01-10 15:21:56 -08:00
Daniel Hiltgen
3c49c3ab0d Harden GPU mgmt library lookup
When there are multiple management libraries installed on a system
not every one will be compatible with the current driver.  This change
improves our management library algorithm to build up a set of discovered
libraries based on glob patterns, and then try all of them until we're able to
load one without error.
2024-01-10 15:06:41 -08:00
Daniel Hiltgen
9754ae4c89 Support optional override of the target archictures
This can help speed up incremental builds when you're only testing one
archicture, like amd64.  E.g.
BUILD_ARCH=amd64 ./scripts/build_linux.sh && scp ./dist/ollama-linux-amd64 test-system:
2024-01-10 14:43:24 -08:00
Jeffrey Morgan
224fbf2795 update submodule to commit 1fc2f265ff9377a37fd2c61eae9cd813a3491bea until its main branch is fixed 2024-01-10 17:03:15 -05:00
Jeffrey Morgan
2c6e8f5248 Update submodule to 6efb8eb30e7025b168f3fda3ff83b9b386428ad6 (#1885)
* update submodule to `6efb8eb30e7025b168f3fda3ff83b9b386428ad6`
* unblock condition variable in `update_slots` when closing server
2024-01-10 16:48:38 -05:00
Jeffrey Morgan
34344d801c clean up cmake build directory when cross compiling macOS builds 2024-01-09 17:13:56 -05:00
Robin Glauser
e868c8a5c7 Update api.md (#1878)
Fixed assistant in the example response.
2024-01-09 16:21:17 -05:00
Jeffrey Morgan
c336693f07 calculate overhead based number of gpu devices (#1875) 2024-01-09 15:53:33 -05:00
Daniel Hiltgen
e89dc1d54b Merge pull request #1874 from dhiltgen/correct_cuda_min
Set corret CUDA minimum compute capability version
2024-01-09 11:37:22 -08:00
Daniel Hiltgen
1961a81f03 Set corret CUDA minimum compute capability version
If you attempt to run the current CUDA build on compute capability 5.2
cards, you'll hit the following failure:
cuBLAS error 15 at ggml-cuda.cu:7956: the requested functionality is not supported
2024-01-09 11:28:24 -08:00
Jeffrey Morgan
8a8c7e7f8d only build for metal on arm64 2024-01-09 13:51:08 -05:00
Jeffrey Morgan
6df83e6daa update rough cuda overhead estimate to 15% + 384MiB 2024-01-09 13:51:08 -05:00
Michael Yang
f921e2696e typo 2024-01-09 09:45:42 -08:00
Michael Yang
4a33cede20 remove unused fields and functions 2024-01-09 09:37:40 -08:00
Michael Yang
f95d2f25f3 fix temporary history file permissions 2024-01-09 09:36:58 -08:00
Michael Yang
2b9892a808 fix(windows): modelpath and list 2024-01-09 09:36:58 -08:00
Michael Yang
2bb2bdd5d4 fix lint 2024-01-09 09:36:58 -08:00
Michael Yang
acfc376efd add .golangci.yaml 2024-01-09 09:36:58 -08:00
Michael Yang
997253143f add lint and test on pull_request 2024-01-09 09:36:58 -08:00
Michael Yang
62023177f6 Merge pull request #1614 from jmorganca/mxyng/fix-set-template
fix: set template without triple quotes
2024-01-09 09:36:24 -08:00
Jeffrey Morgan
6164f378f2 revert cuda overhead to 20% 2024-01-09 00:54:29 -05:00
Jeffrey Morgan
f387e9631b use runner if cuda alloc won't fit 2024-01-09 00:44:34 -05:00
Jeffrey Morgan
6566387ae3 add TODO for cuda overhead 2024-01-09 00:28:03 -05:00
Jeffrey Morgan
37708931fb update cuda overhead to 20% to fix crashes when switching between models and large context sizes 2024-01-09 00:05:23 -05:00
Jeffrey Morgan
f6cb0a553c update cuda overhead to 15% or 400MiB 2024-01-08 23:45:45 -05:00
Jeffrey Morgan
2680078c13 fix build on linux 2024-01-08 23:44:13 -05:00
Jeffrey Morgan
f1b7e5f560 update overhead to 15% 2024-01-08 23:37:45 -05:00
Jeffrey Morgan
cb534e6ac2 use 10% vram overhead for cuda 2024-01-08 23:17:44 -05:00
Jeffrey Morgan
58ce2d8273 better estimate scratch buffer size 2024-01-08 21:32:44 -05:00
Jeffrey Morgan
18ddf6d57d fix windows build 2024-01-08 20:04:01 -05:00
Michael Yang
61e6502449 Merge pull request #1818 from jmorganca/mxyng/fix-alt-prompt
fix(cmd): history in alt prompt
2024-01-08 13:48:34 -08:00
Jeffrey Morgan
08f1e18965 Offload layers to GPU based on new model size estimates (#1850)
* select layers based on estimated model memory usage

* always account for scratch vram

* dont load +1 layers

* better estmation for graph alloc

* Update gpu/gpu_darwin.go

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update llm/llm.go

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* Update llm/llm.go

* add overhead for cuda memory

* Update llm/llm.go

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* fix build error on linux

* address comments

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2024-01-08 16:42:00 -05:00
Bruce MacDonald
7e8f7c8358 remove ggml automatic re-pull (#1856) 2024-01-08 14:41:01 -05:00
Bruce MacDonald
3f3eb19a3b document response in modelfile template variables (#1428) 2024-01-08 14:38:51 -05:00
Daniel Hiltgen
059ae4585e Merge pull request #1834 from dhiltgen/old_cuda
Detect very old CUDA GPUs and fall back to CPU
2024-01-07 10:39:49 -08:00
Daniel Hiltgen
6347f501ca Merge pull request #1828 from dhiltgen/fix_llava
Accept windows paths for image processing
2024-01-07 09:05:46 -08:00
Jeffrey Morgan
5feec959ad dont use -Wall in static build (#1833) 2024-01-07 10:39:19 -05:00
Jeffrey Morgan
dbdd50b283 add -DCMAKE_SYSTEM_NAME=Darwin cmake flag (#1832) 2024-01-07 00:46:17 -05:00
Daniel Hiltgen
d74ce6bd4f Detect very old CUDA GPUs and fall back to CPU
If we try to load the CUDA library on an old GPU, it panics and crashes
the server.  This checks the compute capability before we load the
library so we can gracefully fall back to CPU mode.
2024-01-06 21:40:29 -08:00
Guilherme Baptista
57942b4676 Update README.md - Community Integrations - Ollama for Ruby (#1830) 2024-01-06 22:31:39 -05:00
Daniel Hiltgen
e0d05b0f1e Accept windows paths for image processing
This enhances our regex to support windows style paths.  The regex will
match invalid path specifications, but we'll still validate file
existence and filter out mismatches
2024-01-06 10:50:27 -08:00
Daniel Hiltgen
2d9dd14f27 Merge pull request #1697 from dhiltgen/win_docs
Add windows native build instructions
2024-01-05 19:34:20 -08:00
Jeffrey Morgan
1caa56128f add cuda lib path for nvidia container toolkit 2024-01-05 21:10:37 -05:00
Michael Yang
0101e76dbe Merge pull request #1797 from sublimator/nd-allow-extension-origins-still-needs-explicit-listing-2024-01-05
fix: allow extension origins (still needs explicit listing), fixes #1686
2024-01-05 17:20:09 -08:00
Michael Yang
2ef9352b94 fix(cmd): history in alt mode 2024-01-05 16:20:02 -08:00
Michael Yang
5580ae2472 fix: set template without triple quotes 2024-01-05 15:51:33 -08:00
Bruce MacDonald
3a9f447141 only pull gguf model if already exists (#1817) 2024-01-05 18:50:00 -05:00
Patrick Devine
9c2941e61b switch api for ShowRequest to use the name field (#1816) 2024-01-05 15:06:43 -08:00
Patrick Devine
238ac5e765 Add unit tests for Parser (#1815) 2024-01-05 14:04:31 -08:00
Bruce MacDonald
4f4980b66b simplify ggml update logic (#1814)
- additional information is now available in show response, use this to pull gguf before running
- make gguf updates cancellable
2024-01-05 15:22:32 -05:00
Patrick Devine
22e93efa41 add show info command and fix the modelfile 2024-01-05 12:20:05 -08:00
Patrick Devine
2909dce894 split up interactive generation 2024-01-05 12:20:05 -08:00
Jeffrey Morgan
df32537312 gpu: read memory info from all cuda devices (#1802)
* gpu: read memory info from all cuda devices

* add `LOOKUP_SIZE` constant

* better constant name

* address comments
2024-01-05 11:25:58 -05:00
Bruce MacDonald
3367b5f3df remove unused generate patches (#1810) 2024-01-05 11:25:45 -05:00
Matt Williams
46edbbc518 Merge pull request #1801 from jmorganca/mattw/correctdockerlink 2024-01-04 19:20:45 -08:00
Michael Yang
d2ff18cd6b Merge pull request #1791 from jmorganca/mxyng/update-build
update Dockerfile.build
2024-01-04 19:13:44 -08:00
Matt Williams
df086d3c8c fix docker doc to point to hub
Signed-off-by: Matt Williams <m@technovangelist.com>
2024-01-04 18:42:23 -08:00
Nicholas Dudfield
8baaaa39c0 Allow extension origins (still needs explicit listing), fixes #1686 2024-01-05 09:06:47 +07:00
Michael Yang
f9961c70ae update build 2024-01-04 17:34:38 -08:00
Daniel Hiltgen
cd8fad3398 Merge pull request #1790 from dhiltgen/llm_code_shuffle
Cleaup stale submodule
2024-01-04 13:47:25 -08:00
Daniel Hiltgen
9983fa5f4e Cleaup stale submodule
If the tree has a stale submodule, make sure we clean it up first
2024-01-04 13:40:16 -08:00
Daniel Hiltgen
dfda91c2ee Merge pull request #1788 from dhiltgen/llm_code_shuffle
Revamp code layout for the llm directory and llama.cpp submodule
2024-01-04 13:14:28 -08:00
Daniel Hiltgen
fac9060da5 Init submodule with new path 2024-01-04 13:00:13 -08:00
Daniel Hiltgen
a554616f8e remove old llama.cpp submodule path 2024-01-04 12:12:21 -08:00
Daniel Hiltgen
77d96da94b Code shuffle to clean up the llm dir 2024-01-04 12:12:05 -08:00
Brian Murray
0d6e3565ae Add embeddings to API (#1773) 2024-01-04 15:00:52 -05:00
Daniel Hiltgen
b5939008a1 Merge pull request #1785 from dhiltgen/win_native_cli
Load dynamic cpu lib on windows
2024-01-04 08:55:01 -08:00
Daniel Hiltgen
e9ce91e9a6 Load dynamic cpu lib on windows
On linux, we link the CPU library in to the Go app and fall back to it
when no GPU match is found. On windows we do not link in the CPU library
so that we can better control our dependencies for the CLI.  This fixes
the logic so we correctly fallback to the dynamic CPU library
on windows.
2024-01-04 08:41:41 -08:00
Bruce MacDonald
4ad6c9b11f fix: pull either original model or from model on create (#1774) 2024-01-04 01:34:38 -05:00
Jeffrey Morgan
c0285158a9 tweak memory requirements error text 2024-01-03 19:47:18 -05:00
Jeffrey Morgan
77a66df72c add macOS memory check for 47B models 2024-01-03 19:46:16 -05:00
Jeffrey Morgan
5b4837f881 remove unused filetype check 2024-01-03 19:45:39 -05:00
Jeffrey Morgan
29340c2e62 update cmake flags for amd64 macOS (#1780)
* update cmake flags for intel macOS

* remove `LLAMA_K_QUANTS`

* put back `CMAKE_OSX_DEPLOYMENT_TARGET` and disable `LLAMA_F16C`
2024-01-03 19:22:15 -05:00
Daniel Hiltgen
d5ec730354 Merge pull request #1779 from dhiltgen/refined_amd_gpu_list
Improve maintainability of Radeon card list
2024-01-03 16:18:57 -08:00
Daniel Hiltgen
8bed487aba Merge pull request #1778 from dhiltgen/wsl1
Fail fast on WSL1 while allowing on WSL2
2024-01-03 16:18:41 -08:00
Daniel Hiltgen
c1a10a6e9b Merge pull request #1781 from dhiltgen/cpu_only_build
Fix CPU only builds
2024-01-03 16:18:25 -08:00
Daniel Hiltgen
ddbfa6fe31 Fix CPU only builds
Go embed doesn't like when there's no matching files, so put
a dummy placeholder in to allow building without any GPU support
If no "server" library is found, it's safely ignored at runtime.
2024-01-03 16:08:34 -08:00
Daniel Hiltgen
2fcd41ef81 Fail fast on WSL1 while allowing on WSL2
This prevents users from accidentally installing on WSL1 with instructions
guiding how to upgrade their WSL instance to version 2.  Once running WSL2
if you have an NVIDIA card, you can follow their instructions to set up
GPU passthrough and run models on the GPU.  This is not possible on WSL1.
2024-01-03 16:02:32 -08:00
Daniel Hiltgen
16f4603b67 Improve maintainability of Radeon card list
This moves the list of AMD GPUs to an easier to maintain list which
should make it easier to update over time.
2024-01-03 15:16:56 -08:00
Daniel Hiltgen
1184686649 Merge pull request #1776 from dhiltgen/render_group
Add ollama user to render group for Radeon support
2024-01-03 13:07:54 -08:00
Daniel Hiltgen
2588cb2daa Add ollama user to render group for Radeon support
For the ROCm libraries to access the driver, we need to add the ollama user
to the render group.
2024-01-03 12:56:31 -08:00
Jeffrey Morgan
c7ea8f237e set num_gpu to 1 only by default on darwin arm64 (#1771) 2024-01-03 14:10:29 -05:00
Bruce MacDonald
0b3118e0af fix: relay request opts to loaded llm prediction (#1761) 2024-01-03 12:01:42 -05:00
Daniel Hiltgen
05face44ef Merge pull request #1683 from dhiltgen/fix_windows_test
Fix windows system memory lookup
2024-01-03 09:00:39 -08:00
Daniel Hiltgen
a2ad952440 Fix windows system memory lookup
This refines the gpu package error handling and fixes a bug with the
system memory lookup on windows.
2024-01-03 08:50:01 -08:00
Daniel Hiltgen
5fea4410be Merge pull request #1680 from dhiltgen/better_patching
Refactor how we augment llama.cpp and refine windows native build
2024-01-03 08:10:17 -08:00
Bruce MacDonald
b846eb64d0 Fix template api doc description (#1661) 2024-01-03 11:00:59 -05:00
Cole Gillespie
3c5dd9ed1d Update README.md (#1766) 2024-01-03 10:44:22 -05:00
Jeffrey Morgan
b17ccd0542 Update import.md 2024-01-02 22:28:18 -05:00
Patrick Devine
d0409f772f keyboard shortcut help (#1764) 2024-01-02 18:04:12 -08:00
Jeffrey Morgan
ec261422af use docker build in build scripts 2024-01-02 19:32:54 -05:00
Daniel Hiltgen
0498f7ce56 Get rid of one-line llama.log
This one log line was triggering a single line llama.log to be generated
in the pwd of the server
2024-01-02 15:36:16 -08:00
Daniel Hiltgen
738a8d12eb Rename the ollama cmakefile 2024-01-02 15:36:16 -08:00
Daniel Hiltgen
d966b730ac Switch windows build to fully dynamic
Refactor where we store build outputs, and support a fully dynamic loading
model on windows so the base executable has no special dependencies thus
doesn't require a special PATH.
2024-01-02 15:36:16 -08:00
Daniel Hiltgen
9a70aecccb Refactor how we augment llama.cpp
This changes the model for llama.cpp inclusion so we're not applying a patch,
but instead have the C++ code directly in the ollama tree, which should make it
easier to refine and update over time.
2024-01-02 15:35:55 -08:00
Karim ElGhandour
22cd5eaab6 Added Ollama-SwiftUI to integrations (#1747) 2024-01-02 09:47:50 -05:00
Dane Madsen
304a8799ca Update README.md (#1757) 2024-01-02 09:47:08 -05:00
Jeffrey Morgan
2a2fa3c329 api.md cleanup & formatting 2023-12-27 14:32:35 -05:00
Jeffrey Morgan
55978c1dc9 clean up cache api option 2023-12-27 14:27:45 -05:00
Jeffrey Morgan
d4ebdadbe7 enable cache_prompt by default 2023-12-27 14:23:42 -05:00
Daniel Hiltgen
e201efa14b Add windows native build instructions 2023-12-25 08:31:34 -08:00
Icelain
c5f21f73a4 follow best practices by adding resp.Body.Close() (#1708) 2023-12-25 09:01:37 -05:00
Jeffrey Morgan
371bc73531 Update README.md 2023-12-24 11:54:08 -05:00
Jeffrey Morgan
c651d8b824 Update README.md 2023-12-23 11:18:12 -05:00
Daniel Hiltgen
cf50ef5b51 Merge pull request #1684 from dhiltgen/tag_integration_tests
Guard integration tests with a tag
2023-12-22 16:43:41 -08:00
Daniel Hiltgen
697bea6939 Guard integration tests with a tag
This should help CI avoid running the integration test logic in a
container where it's not currently possible.
2023-12-22 16:33:27 -08:00
K0IN
10da41d677 Add Cache flag to api (#1642) 2023-12-22 17:16:20 -05:00
Bruce MacDonald
db356c8519 post-response templating (#1427) 2023-12-22 17:07:05 -05:00
Jeffrey Morgan
b80081022f cache docker builds in build_linux.sh 2023-12-22 16:01:20 -05:00
Matt Williams
790457398a Merge pull request #1677 from jmorganca/mattw/docrunupdate
update where are models stored q
2023-12-22 09:56:27 -08:00
Matt Williams
511069a2a5 update where are models stored q
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-22 09:48:44 -08:00
Matt Williams
5a85070c22 Update readmes, requirements, packagejsons, etc for all examples (#1452)
Most of the examples needed updates of Readmes to show how to run them. Some of the requirements.txt files had extra content that wasn't needed, or missing altogether. Apparently some folks like to run npm start
to run typescript, so a script was added to all typescript examples which
hadn't been done before.

Basically just a lot of cleanup.

Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-22 09:10:41 -08:00
Matt Williams
291700c92d Clean up documentation (#1506)
* Clean up documentation

Will probably need to update with PRs for new release.

Signed-off-by: Matt Williams <m@technovangelist.com>

* Correcting to fit in 0.1.15 changes

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* addressing comments

Signed-off-by: Matt Williams <m@technovangelist.com>

* more api cleanup

Signed-off-by: Matt Williams <m@technovangelist.com>

* its llava not llama

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update docs/troubleshooting.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Updated hosting to server and documented all env vars

Signed-off-by: Matt Williams <m@technovangelist.com>

* remove last of the cli descriptions

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* update further per conversation with jeff earlier today

Signed-off-by: Matt Williams <m@technovangelist.com>

* cleanup the doc readme

Signed-off-by: Matt Williams <m@technovangelist.com>

* move upgrade to faq

Signed-off-by: Matt Williams <m@technovangelist.com>

* first change

Signed-off-by: Matt Williams <m@technovangelist.com>

* updated

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update docs/faq.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* examples in parent

Signed-off-by: Matt Williams <m@technovangelist.com>

* add exapmle for create model.

Signed-off-by: Matt Williams <m@technovangelist.com>

* update faq

Signed-off-by: Matt Williams <m@technovangelist.com>

* update create model api

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update docs/api.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/faq.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/troubleshooting.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* update the readme in docs

Signed-off-by: Matt Williams <m@technovangelist.com>

* update a few more things

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update docs/troubleshooting.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/faq.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update README.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/modelfile.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Update docs/troubleshooting.md

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

---------

Signed-off-by: Matt Williams <m@technovangelist.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-12-22 09:10:01 -08:00
Daniel Hiltgen
9db28af84e Merge pull request #1675 from dhiltgen/less_verbose
Quiet down llama.cpp logging by default
2023-12-22 08:57:17 -08:00
Daniel Hiltgen
e5202eb687 Quiet down llama.cpp logging by default
By default builds will now produce non-debug and non-verbose binaries.
To enable verbose logs in llama.cpp and debug symbols in the
native code, set `CGO_CFLAGS=-g`
2023-12-22 08:47:18 -08:00
Daniel Hiltgen
96fb441abd Merge pull request #1146 from dhiltgen/ext_server_cgo
Add cgo implementation for llama.cpp
2023-12-22 08:16:31 -08:00
Daniel Hiltgen
495c06e4a6 Fix doc glitch 2023-12-21 18:21:31 -08:00
Daniel Hiltgen
fa24e73b82 Remove CPU build, fixup linux build script 2023-12-21 18:21:31 -08:00
Daniel Hiltgen
325d74985b Fix CPU performance on hyperthreaded systems
The default thread count logic was broken and resulted in 2x the number
of threads as it should on a hyperthreading CPU
resulting in thrashing and poor performance.
2023-12-21 16:23:36 -08:00
Bruce MacDonald
fabf2f3467 allow for starting llava queries with filepath (#1549) 2023-12-21 13:20:59 -05:00
Daniel Hiltgen
d9cd3d9667 Revive windows build
The windows native setup still needs some more work, but this gets it building
again and if you set the PATH properly, you can run the resulting exe on a cuda system.
2023-12-20 17:21:54 -08:00
Patrick Devine
a607d922f0 add FAQ for slow networking in WSL2 (#1646) 2023-12-20 16:27:24 -08:00
Daniel Hiltgen
7555ea44f8 Revamp the dynamic library shim
This switches the default llama.cpp to be CPU based, and builds the GPU variants
as dynamically loaded libraries which we can select at runtime.

This also bumps the ROCm library to version 6 given 5.7 builds don't work
on the latest ROCm library that just shipped.
2023-12-20 14:45:57 -08:00
Jeffrey Morgan
df06812494 Update api.md 2023-12-20 08:47:53 -05:00
Daniel Hiltgen
1d1eb1688c Additional nvidial-ml path to check 2023-12-19 15:52:34 -08:00
Michael Yang
23dc179350 Merge pull request #1619 from jmorganca/mxyng/fix-version-test
fix(test): use real version string for comparison
2023-12-19 15:48:52 -08:00
Michael Yang
63aac0edc5 fix(test): use real version string for comparison 2023-12-19 15:03:02 -08:00
Daniel Hiltgen
6558f94ed0 Fix darwin intel build 2023-12-19 13:32:24 -08:00
Erick Ghaumez
1ca484f67e Add Langchain Dart library (#1564)
* Add Langchain Dart

* Update README.md

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-19 14:04:52 -05:00
Jeffrey Morgan
72b0c32fe9 Update README.md 2023-12-19 12:59:22 -05:00
Jeffrey Morgan
68c28224f8 Update README.md 2023-12-19 12:59:03 -05:00
Daniel Hiltgen
54dbfa4c4a Carry ggml-metal.metal as payload 2023-12-19 09:05:46 -08:00
Daniel Hiltgen
5646826a79 Add WSL2 path to nvidia-ml.so library 2023-12-19 09:05:46 -08:00
Daniel Hiltgen
3269535a4c Refine handling of shim presence
This allows the CPU only builds to work on systems with Radeon cards
2023-12-19 09:05:46 -08:00
Daniel Hiltgen
1b991d0ba9 Refine build to support CPU only
If someone checks out the ollama repo and doesn't install the CUDA
library, this will ensure they can build a CPU only version
2023-12-19 09:05:46 -08:00
Daniel Hiltgen
51082535e1 Add automated test for multimodal
A simple test case that verifies llava:7b can read text in an image
2023-12-19 09:05:46 -08:00
Daniel Hiltgen
9adca7f711 Bump llama.cpp to b1662 and set n_parallel=1 2023-12-19 09:05:46 -08:00
Daniel Hiltgen
89bbaafa64 Build linux using ubuntu 20.04
This changes the container-based linux build to use an older Ubuntu
distro to improve our compatibility matrix for older user machines
2023-12-19 09:05:46 -08:00
Daniel Hiltgen
35934b2e05 Adapted rocm support to cgo based llama.cpp 2023-12-19 09:05:46 -08:00
65a
f8ef4439e9 Use build tags to generate accelerated binaries for CUDA and ROCm on Linux.
The build tags rocm or cuda must be specified to both go generate and go build.
ROCm builds should have both ROCM_PATH set (and the ROCM SDK present) as well
as CLBlast installed (for GGML) and CLBlast_DIR set in the environment to the
CLBlast cmake directory (likely /usr/lib/cmake/CLBlast). Build tags are also
used to switch VRAM detection between cuda and rocm implementations, using
added "accelerator_foo.go" files which contain architecture specific functions
and variables. accelerator_none is used when no tags are set, and a helper
function addRunner will ignore it if it is the chosen accelerator. Fix go
generate commands, thanks @deadmeu for testing.
2023-12-19 09:05:46 -08:00
Daniel Hiltgen
d4cd695759 Add cgo implementation for llama.cpp
Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.
2023-12-19 09:05:46 -08:00
Bruce MacDonald
5e7fd6906f Update images.go 2023-12-19 09:05:46 -08:00
Bruce MacDonald
811b1f03c8 deprecate ggml
- remove ggml runner
- automatically pull gguf models when ggml detected
- tell users to update to gguf in the case automatic pull fails

Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>
2023-12-19 09:05:46 -08:00
Matt Williams
ed195f3562 Merge pull request #1595 from pgibler/main
Added cmdh to community section in README
2023-12-18 20:55:18 -08:00
Matt Williams
e0d0072ef1 Merge pull request #1592 from jmorganca/mattw/examplepruning
Lets get rid of these old modelfile examples
2023-12-18 20:29:48 -08:00
pgibler
620a2ffcfb Added cmdh to community section in README 2023-12-18 22:04:40 -05:00
Matt Williams
d287013f24 Lets get rid of these old modelfile examples
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-18 17:47:33 -08:00
Jeffrey Morgan
6b5bdfa6c9 update runner submodule 2023-12-18 17:33:46 -05:00
Jeffrey Morgan
c063ee4af0 update runner submodule to fix hipblas build 2023-12-18 15:41:13 -05:00
Bruce MacDonald
d99fa6ce0a send empty messages on last chat response (#1530) 2023-12-18 14:23:38 -05:00
Patrick Devine
3948c6ea06 add magic header for unit tests (#1558) 2023-12-18 10:41:02 -08:00
Jeffrey Morgan
b85982eb91 update runner submodule 2023-12-18 12:43:31 -05:00
Patrick Devine
86b0dd4b16 add API create/copy handlers (#1541) 2023-12-15 11:59:18 -08:00
Augustinas Malinauskas
f728738427 README with Enchanted iOS App (#1529)
* feat(docs): README with Enchanted iOS app

* Update README.md

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-15 14:37:29 -05:00
Ian Purton
115048a0d8 Added Bionic GPT as a front end. (#1463)
* Added Bionic GPT as a front end.

* Update README.md

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-15 14:33:04 -05:00
Bruce MacDonald
1b417a7836 use exp slices for go 1.20 compatibility (#1544) 2023-12-15 14:15:56 -05:00
Patrick Devine
0174665d0e add API tests for list handler (#1535) 2023-12-14 18:18:25 -08:00
Patrick Devine
630518f0d9 Add unit test of API routes (#1528) 2023-12-14 16:47:40 -08:00
Bruce MacDonald
6e16098a60 remove sample_count from docs (#1527)
this info has not been returned from these endpoints in some time
2023-12-14 17:49:00 -05:00
Bruce MacDonald
6ee8c80199 restore model load duration on generate response (#1524)
* restore model load duration on generate response

- set model load duration on generate and chat done response
- calculate createAt time when response created

* remove checkpoints predict opts

* Update routes.go
2023-12-14 12:15:50 -05:00
Jeffrey Morgan
31f0551dab Update runner to support mixtral and mixture of experts (MoE) (#1475) 2023-12-13 17:15:10 -05:00
Jeffrey Morgan
4a1abfe4fa fix tests 2023-12-13 14:42:30 -05:00
Jeffrey Morgan
bbd41494bf add multimodal to README.md 2023-12-13 14:38:47 -05:00
Jeffrey Morgan
fedba24a63 Docs for multimodal support (#1485)
* add multimodal docs

* add chat api docs

* consistency between `/api/generate` and `/api/chat`

* simplify docs
2023-12-13 13:59:33 -05:00
pepperoni21
e3b090dbc5 Added message format for chat api (#1488) 2023-12-13 11:21:23 -05:00
Patrick Devine
d9e60f634b add image support to the chat api (#1490) 2023-12-12 13:28:58 -08:00
Michael Yang
4251b342de Merge pull request #1469 from jmorganca/mxyng/model-types
remove per-model types
2023-12-12 12:27:03 -08:00
Jeffrey Morgan
0a9d348023 Fix issues with /set template and /set system (#1486) 2023-12-12 14:43:19 -05:00
Bruce MacDonald
3144e2a439 exponential back-off (#1484) 2023-12-12 12:33:02 -05:00
Bruce MacDonald
c0960e29b5 retry on concurrent request failure (#1483)
- remove parallel
2023-12-12 12:14:35 -05:00
ruecat
5314fc9b63 Fix Readme "Database -> MindsDB" link (#1479) 2023-12-12 10:26:13 -05:00
Jorge Torres
a36b5fef3b Update README.md (#1412) 2023-12-11 18:05:10 -05:00
Patrick Devine
910e9401d0 Multimodal support (#1216)
---------

Co-authored-by: Matt Apperson <mattapperson@Matts-MacBook-Pro.local>
2023-12-11 13:56:22 -08:00
Michael Yang
56ffc3023a remove per-model types
mostly replaced by decoding tensors except ggml models which only
support llama
2023-12-11 09:40:21 -08:00
Bruce MacDonald
7a1b37ac64 os specific ctrl-z (#1420) 2023-12-11 10:48:14 -05:00
Jeffrey Morgan
5d4d2e2c60 update docs with chat completion api 2023-12-10 13:53:36 -05:00
Jeffrey Morgan
7db5bcf73b fix go-staticcheck warning 2023-12-10 11:44:27 -05:00
Jeffrey Morgan
fa2f095bd9 fix model name returned by /api/generate being different than the model name provided 2023-12-10 11:42:15 -05:00
Jeffrey Morgan
045b855db9 fix error on accumulating final chat response 2023-12-10 11:24:39 -05:00
Jeffrey Morgan
32064a0646 fix empty response when receiving runner error 2023-12-10 10:53:38 -05:00
Jeffrey Morgan
d9a250e9b5 seek to end of file when decoding older model formats 2023-12-09 21:14:35 -05:00
Jeffrey Morgan
944519ed16 seek to eof for older model binaries 2023-12-09 20:48:57 -05:00
Jeffrey Morgan
2dd040d04c do not use --parallel 2 for old runners 2023-12-09 20:17:33 -05:00
Bruce MacDonald
bbe41ce41a fix: parallel queueing race condition caused silent failure (#1445)
* fix: queued request failures

- increase parallel requests to 2 to complete queued request, queueing is managed in ollama

* log steam errors
2023-12-09 14:14:02 -05:00
Jeffrey Morgan
9e1406e4ed Don't expose model information in /api/generate 2023-12-09 02:05:43 -08:00
Jeffrey Morgan
b74580c913 Update api.md 2023-12-08 16:02:07 -08:00
Bruce MacDonald
7e9405fd07 fix: encode full previous prompt in context (#1424) 2023-12-08 16:53:51 -05:00
Bruce MacDonald
3b0b8930d4 fix: only flush template in chat when current role encountered (#1426) 2023-12-08 16:44:24 -05:00
Bruce MacDonald
e3f925fc1b fix: restore modelfile system in prompt template (#1425) 2023-12-08 14:20:19 -05:00
Jeffrey Morgan
2a2289fb6b Update api.md 2023-12-08 09:36:45 -08:00
Matt Williams
dd427f499a Merge pull request #1419 from jmorganca/mattw/typescript-simplechat
Simple chat example for typescript
2023-12-07 14:42:24 -08:00
Michael Yang
2ae573c7ed Merge pull request #1421 from jmorganca/mxyng/fix-newline
fix redundant newline
2023-12-07 13:47:23 -08:00
Matt Williams
02fe26c44b update the readme as per bruce
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-07 13:46:30 -08:00
Michael Yang
16c7548460 fix redundant newline 2023-12-07 13:44:45 -08:00
Matt Williams
fa75998c0d Update examples/typescript-simplechat/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-07 13:40:54 -08:00
Matt Williams
5344f886c8 Update examples/typescript-simplechat/client.ts
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-07 13:40:37 -08:00
Matt Williams
6cc823c9b5 Update examples/typescript-simplechat/client.ts
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-07 13:39:59 -08:00
Matt Williams
b84d34e632 Update examples/typescript-simplechat/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-07 13:39:33 -08:00
Matt Williams
30229a913c Update examples/typescript-simplechat/client.ts
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-07 13:39:24 -08:00
Matt Williams
1ade380bd7 Simple chat example for typescript
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-07 11:48:25 -08:00
Jeffrey Morgan
ba264e9da8 add future version note to chat api docs 2023-12-07 09:42:15 -08:00
Matt Williams
a2405ec831 Merge pull request #1409 from jmorganca/mattw/python-simplechat
Simple chat example
2023-12-06 15:49:45 -08:00
Matt Williams
ce809bb529 Merge branch 'mattw/python-simplechat' of github.com:jmorganca/ollama into mattw/python-simplechat 2023-12-06 15:48:42 -08:00
Matt Williams
76bc4d0458 Cleanup as per Bruce
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-06 15:44:40 -08:00
Bruce MacDonald
4a02945a15 Update examples/python-simplechat/client.py 2023-12-06 18:36:45 -05:00
Matt Williams
aec742b6d2 Update examples/python-simplechat/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-06 15:30:45 -08:00
Matt Williams
f337642e94 Update examples/python-simplechat/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-06 15:30:35 -08:00
Matt Williams
51131cc6e2 Update examples/python-simplechat/client.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-12-06 15:30:10 -08:00
Matt Williams
43027789dc Simple chat example
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-06 14:35:58 -08:00
Xe Iaso
f9b7d65e2b docs/tutorials: add bit on how to use Fly GPUs on-demand with Ollama (#1406)
Signed-off-by: Xe Iaso <xe@camellia.finch-kitefin.ts.net>
2023-12-06 14:14:02 -08:00
Michael Yang
1f05d77110 Merge pull request #1244 from jmorganca/brucemacd/no-fail-template
do not fail on unsupported template variables
2023-12-06 13:23:04 -08:00
Michael Yang
c3ff36088b Merge pull request #774 from jmorganca/mxyng/server-version
add version api and show server version in cli
2023-12-06 13:22:55 -08:00
Samuel Calderon
13524b5e72 List "Send chat messages" in table of contents (#1399)
Thank you @calderonsamuel
2023-12-06 12:34:27 -08:00
Michael Yang
f1b049fed8 Merge pull request #1377 from jmorganca/mxyng/qwen
update for qwen
2023-12-06 12:31:51 -08:00
Jeffrey Morgan
97c5696945 fix base urls in chat examples 2023-12-06 12:10:20 -08:00
Bruce MacDonald
47d4e22673 use missingkey in set empty interface when missing 2023-12-05 15:49:05 -08:00
Michael Yang
32f62fbb8e Merge pull request #1334 from jmorganca/mxyng/load-projectors
load projectors
2023-12-05 14:40:53 -08:00
Michael Yang
5d75505ebd return model configuration in generate 2023-12-05 14:39:02 -08:00
Michael Yang
b9495ea162 load projectors 2023-12-05 14:36:12 -08:00
Michael Yang
409bb9674e Merge pull request #1308 from jmorganca/mxyng/split-from
split from into one or more models
2023-12-05 14:33:03 -08:00
Michael Yang
d3479c07a1 Merge pull request #1250 from jmorganca/mxyng/create-layer
refactor layer creation
2023-12-05 14:32:52 -08:00
Michael Yang
b12f1b984f Merge pull request #1393 from jmorganca/mxyng/fix-whitespace
fix: trim space in modelfile fields
2023-12-05 12:18:01 -08:00
Bruce MacDonald
195e3d9dbd chat api endpoint (#1392) 2023-12-05 14:57:33 -05:00
Michael Yang
38fe1a368b fix: trim space in modelfile fields 2023-12-05 11:57:29 -08:00
Michael Yang
4b77fcb2b9 comments 2023-12-05 09:43:50 -08:00
Michael Yang
cde13bcdea cmd: only print server version when different 2023-12-05 09:36:01 -08:00
Michael Yang
0f0cd265a7 cmd: add server version 2023-12-05 09:36:01 -08:00
Michael Yang
0db4706ec2 api: add version api handler 2023-12-05 09:36:01 -08:00
Michael Yang
1ebdbd9694 server: add version handler 2023-12-05 09:36:01 -08:00
Michael Yang
5c59455b59 cmd: use existing cmd context 2023-12-05 09:36:01 -08:00
Jeffrey Morgan
00d06619a1 Revert "chat api (#991)" while context variable is fixed
This reverts commit 7a0899d62d.
2023-12-04 21:16:27 -08:00
Matt Williams
f1ef3f9947 remove mention of gpt-neox in import (#1381)
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-12-04 20:58:10 -08:00
Michael Yang
5a5dca13b2 comments 2023-12-04 16:59:23 -08:00
Michael Yang
7232f1fa41 go mod tidy 2023-12-04 16:59:23 -08:00
Michael Yang
72e7a49aa9 seek instead of copyn 2023-12-04 16:59:23 -08:00
Michael Yang
a3737cbd33 use NewLayer for CreateBlobHandler 2023-12-04 16:59:23 -08:00
Michael Yang
998f1785b6 add modelfamilies 2023-12-04 16:59:23 -08:00
Michael Yang
70a93057cd refactor layer creation
previous layer creation was not ideal because:

1. it required reading the input file multiple times, once to calculate
   the sha256 checksum, another to write it to disk, and potentially one
   more to decode the underlying gguf
2. used io.ReadSeeker which is prone to user error. if the file isn't
   reset correctly or in the right place, it could end up reading an
   empty file

there are also some brittleness when reading existing layers else
writing the inherited layers will error reading an already closed file

this commit aims to fix these issues by restructuring layer creation.

1. it will now write the layer to a temporary file as well as the hash
   function and move it to the final location on Commit
2. layers are read once once when copied to the destination. exception
   is raw model files which still requires a second read to decode the
   model metadata
2023-12-04 16:59:23 -08:00
Michael Yang
2cb0fa7d40 split from into one or more models 2023-12-04 16:59:23 -08:00
Michael Yang
b2816bca67 unnecessary ReadSeeker for DecodeGGML 2023-12-04 16:59:23 -08:00
Patrick Devine
bf704423c5 revert cli to use /api/generate (#1383) 2023-12-04 16:35:29 -08:00
Bruce MacDonald
7a0899d62d chat api (#991)
- update chat docs
- add messages chat endpoint
- remove deprecated context and template generate parameters from docs
- context and template are still supported for the time being and will continue to work as expected
- add partial response to chat history
2023-12-04 18:01:06 -05:00
Michael Yang
0cca1486dd Merge pull request #1376 from jmorganca/mxyng/rocky-install
install: fix rocky kernel packages
2023-12-04 14:23:43 -08:00
Patrick Devine
2113c9d31a make linewrap still work when the terminal width has changed (#1350) 2023-12-04 14:14:56 -08:00
Michael Yang
6deebf2489 update for qwen 2023-12-04 11:38:05 -08:00
Michael Yang
95cb38ae47 install: fix rocky kernel packages 2023-12-04 11:10:42 -08:00
ruecat
1f126afb2d Ollama Telegram Bot (#1364)
* Add "ollama-telegram" to Extensions & Plugins

* Update README.md
2023-12-03 11:19:55 -08:00
Jeffrey Morgan
f6201a7a6c remove duplicate community integration in README.md 2023-12-02 21:18:13 -08:00
Michael Yang
b3f6c6598f Merge pull request #1349 from jmorganca/mxyng/ctrl-z
handle ctrl+z
2023-12-01 16:21:49 -08:00
Michael Yang
88620e983a handle ctrl+z 2023-12-01 16:15:20 -08:00
Michael Yang
cedae0d17a Merge pull request #1347 from jshph/adapter-hash
Fix adapter loading from SHA hash
2023-12-01 11:08:25 -08:00
Joshua Pham
bb80a597db Fix adapter loading from SHA hash 2023-12-01 13:50:55 -05:00
Patrick Devine
6681d37861 allow setting the system and template for prompts in the repl (#1335) 2023-12-01 09:28:35 -08:00
Michael Yang
0409c1fa59 docker: set PATH, LD_LIBRARY_PATH, and capabilities (#1336)
* docker: set PATH, LD_LIBRARY_PATH, and capabilities

* example: update k8s gpu manifest
2023-11-30 21:16:56 -08:00
Michael Yang
b56e92470a Merge pull request #1229 from jmorganca/mxyng/calculate-as-you-go
revert checksum calculation to calculate-as-you-go
2023-11-30 10:54:38 -08:00
Jeffrey Morgan
5687f1a0cf fix unexpected end of response errors when cancelling in ollama run 2023-11-30 00:30:21 -05:00
James Radtke
7eda3d0c55 Corrected transposed 129 to 192 for OLLAMA_ORIGINS example (#1325) 2023-11-29 22:44:17 -05:00
Bruce MacDonald
7194a07d4d Add chatd to example projects 2023-11-29 21:18:21 -05:00
Michael Yang
13efd5f218 upload: fix PUT retry 2023-11-29 16:38:35 -08:00
Michael Yang
c4bdfffd96 upload: separate progress tracking 2023-11-29 16:38:33 -08:00
Michael Yang
26c63418e0 new hasher 2023-11-29 14:52:41 -08:00
Michael Yang
2799784ac8 revert checksum calculation to calculate-as-you-go 2023-11-29 13:47:58 -08:00
Alec Hammond
91897a606f Add OllamaEmbeddings to python LangChain example (#994)
* Add OllamaEmbeddings to python LangChain example

* typo

---------

Co-authored-by: Alec Hammond <alechammond@fb.com>
2023-11-29 16:25:39 -05:00
Bruce MacDonald
96122b7271 validate model tags on copy (#1323) 2023-11-29 15:54:29 -05:00
jeremiahbuckley
39be7fdb98 fix rhel cuda install (#1321)
Co-authored-by: Cloud User <azureuser@testgpu2.hqzwom21okjenksna4y3c4ymjd.phxx.internal.cloudapp.net>
2023-11-29 14:55:15 -05:00
Timothy Jaeryang Baek
c2e3b89176 fix: disable ':' in tag names (#1280)
Co-authored-by: rootedbox
2023-11-29 13:33:45 -05:00
Patrick Devine
cde31cb220 Allow setting parameters in the REPL (#1294) 2023-11-29 09:56:42 -08:00
ToasterUwU
63097607b2 Correct MacOS Host port example (#1301) 2023-11-29 11:44:03 -05:00
Michael
2ae80e1e27 Update README.md
add new recent models as examples
2023-11-28 22:16:37 -05:00
Michael Yang
b173cfc558 Merge pull request #1195 from jmorganca/mxyng/fix-bar-rate
progress: fix bar rate
2023-11-28 11:55:23 -08:00
Michael Yang
424d53ac70 progress: fix bar rate 2023-11-28 11:44:56 -08:00
ftorto
e1a69d44c9 Update faq.md (#1299)
Fix a typo in the CA update command
2023-11-28 09:54:42 -05:00
Jason Jacobs
3d620f9462 ignore jetbrain ides (#1287) 2023-11-27 15:57:45 -05:00
Bruce MacDonald
928950fcc6 update python client create example (#1227)
* add remote create to python example client
2023-11-27 15:36:19 -05:00
Kasumi
39c6d949fc Add Amica to community integrations (#1281) 2023-11-27 10:44:37 -05:00
Jeffrey Morgan
16a9006306 add back f16c instructions on intel mac 2023-11-26 15:59:49 -05:00
Jeffrey Morgan
e9216ea459 fix readline history on linux 2023-11-26 15:59:04 -05:00
Jeffrey Morgan
9e4a316405 update submodule commit 2023-11-26 14:52:00 -05:00
Jeffrey Morgan
9fb5e8399c Fix issues with inputting and formatting multi line strings in ollama run
Co-authored-by: Wen Sun <iwendellsun@gmail.com>
2023-11-26 12:54:29 -05:00
Jing Zhang
82b9b329ff windows CUDA support (#1262)
* Support cuda build in Windows
* Enable dynamic NumGPU allocation for Windows
2023-11-24 17:16:36 -05:00
Jongwook Choi
12e8c12d2b Disable CUDA peer access as a workaround for multi-gpu inference bug (#1261)
When CUDA peer access is enabled, multi-gpu inference will produce
garbage output. This is a known bug of llama.cpp (or nvidia). Until the
upstream bug is fixed, we can disable CUDA peer access temporarily
to ensure correct output.

See #961.
2023-11-24 14:05:57 -05:00
Jeffrey Morgan
d77dde126b consistent cpu instructions on macos and linux 2023-11-22 16:26:46 -05:00
Michael Yang
c7e70cd3bb Merge pull request #1245 from jmorganca/mxyng/gguf-int
fix: gguf int type
2023-11-22 11:42:56 -08:00
Michael Yang
199941cd15 fix: gguf int type 2023-11-22 11:40:30 -08:00
Long Huynh
c9474f7f61 Update README.md - Community Integrations - Obsidian BMO Chatbot plugin (#1239) 2023-11-22 14:32:30 -05:00
Jeffrey Morgan
927e3ba4a4 tag image with correct version when building with build_docker script 2023-11-22 14:32:17 -05:00
Bruce MacDonald
37d95157df fix relative path on create (#1222) 2023-11-21 15:43:17 -05:00
Jeffrey Morgan
2eaa95b417 Update api.md 2023-11-21 15:32:05 -05:00
Kevin Cao
3cd07728f4 Make alt+backspace delete word (#1223) 2023-11-21 12:26:47 -08:00
Michael Yang
ecf8b793f0 Merge pull request #1224 from jmorganca/mxyng/update
update llama.cpp
2023-11-21 12:21:59 -08:00
Matt Williams
abf294826b Merge pull request #1221 from jmorganca/mattw/communityinstalls
add installation packages category to community
2023-11-21 12:12:23 -08:00
Steve Korshakov
ae06bb426b add Llama Coder (#1225)
* add Llama Coder
* Update README.md
2023-11-21 14:08:19 -05:00
Matt Williams
d8e0f62ebb Merge pull request #1159 from jmorganca/mattw/functioncalling
Example: Function Calling in Typescript
2023-11-21 10:06:55 -08:00
Michael Yang
a00fac4ec8 update llama.cpp 2023-11-21 09:50:02 -08:00
Jeffrey Morgan
f2113c1fc7 fix potential error in progress bar calculation 2023-11-21 12:48:20 -05:00
Jeffrey Morgan
6452e2ecb8 fix cases where progress bar would not be fixed size 2023-11-21 12:07:25 -05:00
Matt Williams
9a28e263a5 Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-21 07:25:32 -08:00
Matt Williams
0c066c9214 Update README.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-21 07:25:26 -08:00
Jeffrey Morgan
aabd71aede fix rendering and variable width issues on progress bar 2023-11-21 10:02:37 -05:00
Matt Williams
da4d7c9f9c add installation packages category to community
Moved the arch package and someone has added a pr for brew.
that needs to get updated to be a link.

Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-21 06:40:59 -08:00
Matt Williams
f321b13a03 Merge pull request #1178 from tusharhero/install-instructions-archlinux
Add Installation instructions for Archlinux
2023-11-21 06:33:22 -08:00
Matt Williams
5ebcde1541 Merge branch 'main' into install-instructions-archlinux 2023-11-21 06:32:50 -08:00
Matt Williams
45206cb7cc Merge pull request #1218 from danemadsen/main
Update Maid repo
2023-11-21 06:30:33 -08:00
Matt Williams
6e65b84f54 Merge pull request #1219 from dustinblackman/main
docs: Add Oatmeal to terminal integrations
2023-11-21 06:28:12 -08:00
Dustin Blackman
c00ce12e83 docs: Add Oatmeal to terminal integrations 2023-11-21 06:47:43 -05:00
tusharhero
e1cd3152c9 Move Archlinux package to Community Integrations section. 2023-11-21 16:28:50 +05:30
Dane Madsen
0bef3778c9 Update README.md 2023-11-21 21:02:13 +11:00
Dane Madsen
6ebab38b89 Merge branch 'jmorganca:main' into main 2023-11-21 20:01:13 +10:00
Dane Madsen
5d8e864d44 Update Maid repo 2023-11-21 21:00:54 +11:00
Matt Williams
5f7acd0bbd remove 'recent'
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-20 17:03:25 -08:00
Matt Williams
44b3a1ad42 Merge branch 'mattw/functioncalling' of github.com:jmorganca/ollama into mattw/functioncalling
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-20 17:01:41 -08:00
Matt Williams
0260be4414 remove 'recently'
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-20 16:57:07 -08:00
Jeffrey Morgan
a3fcecf943 only set main_gpu if value > 0 is provided 2023-11-20 19:54:04 -05:00
Jeffrey Morgan
df07e4a097 remove redundant filename parameter (#1213) 2023-11-20 17:05:36 -05:00
Michael Yang
0b7ade0d4c Merge pull request #1212 from jmorganca/mxyng/metal
enable metal for fp32, q5_0, q5_1
2023-11-20 13:56:39 -08:00
Michael Yang
19b7a4d715 recent llama.cpp update added kernels for fp32, q5_0, and q5_1 2023-11-20 13:44:31 -08:00
Bruce MacDonald
31ab453d37 resolve FROM path before sending modelfile (#1211) 2023-11-20 16:43:48 -05:00
Jeffrey Morgan
35c4b5ec16 calculate hash separately from http request 2023-11-20 15:45:11 -05:00
James Braza
f24741ff39 Documenting how to view Modelfiles (#723)
* Documented viewing Modelfiles in ollama.ai/library

* Moved Modelfile in ollama.ai down per request
2023-11-20 15:24:29 -05:00
Jeffrey Morgan
8c4022b06b fix initial progress stats 2023-11-20 14:33:46 -05:00
Jeffrey Morgan
433702f421 hide progress stats on completion 2023-11-20 14:22:39 -05:00
Matt Williams
48896f626c Update examples/typescript-functioncalling/extractwp.ts
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-20 10:12:10 -08:00
Matt Williams
c57aee6fba Update examples/typescript-functioncalling/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-20 10:10:42 -08:00
Jeffrey Morgan
6066c70edd restore progress messages for older endpoints 2023-11-20 11:37:17 -05:00
Jeffrey Morgan
f10ac5de19 restore stats updated every second to progress bar 2023-11-20 10:58:19 -05:00
Jeffrey Morgan
93a108214c only show decimal points for smaller file size numbers 2023-11-20 10:58:19 -05:00
Purinda Gunasekara
be61a81758 main-gpu argument is not getting passed to llamacpp, fixed. (#1192) 2023-11-20 10:52:52 -05:00
Toni Soriano
2fdf1b5ff8 add laravel package to README.md (#1208)
Co-authored-by: Toni <cloudstudio@Tonis-Mac-mini.local>
2023-11-20 10:48:35 -05:00
Huy Le
331068b964 Adding ogpt.nvim into the list of plugins! (#1190)
* adding ollama.nvim for visibility

* adding an ogpt.nvim neovim plugin
2023-11-20 10:39:14 -05:00
Andy Brenneke
0179d8eb6b Add Rivet to Community Integrations (#1183) 2023-11-20 10:36:47 -05:00
Eli Bendersky
be48741308 README: link to LangChainGo for talking to ollama, with an example (#1206) 2023-11-20 10:35:07 -05:00
Jeffrey Morgan
6bbd6e26fb fix temporary newline created and removed with spinner in ollama run 2023-11-20 00:49:08 -05:00
Jeffrey Morgan
e6ad4813d3 dont crash when redirecting stderr 2023-11-19 23:50:45 -05:00
Jeffrey Morgan
13ba6df5ab enable cpu instructions on intel macs 2023-11-19 23:20:26 -05:00
Jeffrey Morgan
9d73d3a6b5 add back part.Reset() 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
72cd336410 dont retry on upload complete context cancel 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
1bd594b2fa revert to using one open file for blob uploads 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
9a8c21ac3d use exponential everywhere 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
f6b317e8c9 fix sending too little data in chunk upload body 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
ac5076ce1e exponential backoff up to 30s 2023-11-19 14:32:19 -05:00
Michael Yang
42c2e3a624 upload: retry complete upload 2023-11-19 14:32:19 -05:00
Michael Yang
cb42589792 adjust download/upload parts 2023-11-19 14:32:19 -05:00
Jeffrey Morgan
258addc799 fix comment in progress.go 2023-11-19 13:46:19 -05:00
Jeffrey Morgan
c06b9b7304 update progress rendering to be closer to v0.1.10 2023-11-19 13:43:21 -05:00
Jeffrey Morgan
95b9acd324 improve pull percentage rendering 2023-11-19 11:00:43 -05:00
Jeffrey Morgan
04cbf5ccc0 progress bar styling improvements 2023-11-19 09:54:33 -05:00
Jeffrey Morgan
e1d7056496 update progress statuses 2023-11-19 09:21:13 -05:00
Jeffrey Morgan
02524a56ff check retry for authorization error 2023-11-19 00:19:53 -05:00
Jeffrey Morgan
1657c6abc7 add note to specify JSON in the prompt when using JSON mode 2023-11-18 22:59:26 -05:00
Jeffrey Morgan
12e046f12a remove unused function 2023-11-18 22:16:51 -05:00
Jeffrey Morgan
36a3bbf65f Update llm/llama.go 2023-11-18 21:25:07 -05:00
Bruce MacDonald
43a726149d fix potentially inaccurate error message 2023-11-18 21:25:07 -05:00
Jeffrey Morgan
984714f131 update status text when transfering blob on ollama create 2023-11-18 09:40:10 -05:00
Jeffrey Morgan
bab9494176 add - separator to temp file created on ollama create 2023-11-18 09:39:52 -05:00
Jeffrey Morgan
85e4441c6a cache docker builds 2023-11-18 08:51:38 -05:00
Michael Yang
42e43736a4 Merge pull request #1186 from jmorganca/mxyng/copy-blob
fix cross device rename
2023-11-17 21:54:53 -08:00
Michael Yang
c6e6c8ee7e fix cross device rename 2023-11-17 15:22:17 -08:00
Jeffrey Morgan
a185b29719 fix install script error on linux 2023-11-17 18:00:41 -05:00
Michael Yang
dc84b20d6b Merge pull request #1104 from jmorganca/mxyng/jupyter
add jupyter notebook example
2023-11-17 14:46:26 -08:00
Michael Yang
ad8659b980 Merge pull request #1161 from jmorganca/mxyng/systemd-placeholder
placeholder environment variables
2023-11-17 14:45:38 -08:00
Michael Yang
c1bbf5ddee Merge pull request #1134 from jmorganca/mxyng/progress
progress bar
2023-11-17 14:03:35 -08:00
Bruce MacDonald
0b19e24d81 only retry once on auth failure (#1175) 2023-11-17 14:22:35 -05:00
Michael Yang
3cb07d2773 simplify StopAndClear 2023-11-17 10:26:22 -08:00
Michael Yang
976068369b stop all spinners on progress stop 2023-11-17 10:06:19 -08:00
Michael Yang
4d677ee389 no divide by zero 2023-11-17 10:06:19 -08:00
Michael Yang
7ea905871a only move cursor up if pos > 0 2023-11-17 10:06:19 -08:00
Michael Yang
d6ecaa2cbf update progress responses 2023-11-17 10:06:19 -08:00
Michael Yang
4dcf7a59b1 generate progress 2023-11-17 10:06:19 -08:00
Michael Yang
1c0e092ead progress cmd 2023-11-17 10:06:19 -08:00
Michael Yang
c4a3ccd7ac progress 2023-11-17 10:06:19 -08:00
Michael Yang
9f04e5a8ea format bytes 2023-11-17 10:06:19 -08:00
Michael Yang
f91bb2f7f0 remove progressbar 2023-11-17 10:06:19 -08:00
Michael Yang
0813387414 Merge pull request #1177 from jmorganca/mxyng/faq
faq: fix heading and add more details
2023-11-17 10:05:21 -08:00
Michael Yang
4936b5bb37 add jupyter readme 2023-11-17 10:04:52 -08:00
tusharhero
786288829e Make Archlinux a sub-heading of Linux. 2023-11-17 23:17:36 +05:30
tusharhero
72dcc952b6 Add Installation instructions for Archlinux
Pacman is the recommended installation method. And the package is in
the official repository, so makes sense to mention it in the README.
2023-11-17 23:13:40 +05:30
Michael Yang
f7f6d6c693 Update examples/jupyter-notebook/ollama.ipynb
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-17 09:30:07 -08:00
Michael Yang
a3053b66d2 add jupyter notebook example 2023-11-17 09:30:07 -08:00
Michael Yang
c82ead4d01 faq: fix heading and add more details 2023-11-17 09:02:17 -08:00
Michael Yang
90860b6a7e update faq (#1176) 2023-11-17 11:42:58 -05:00
Jeffrey Morgan
81092147c4 remove unnecessary -X POST from example curl commands 2023-11-17 09:50:38 -05:00
Jeffrey Morgan
92656a74b7 Use llama2 as the model in api.md 2023-11-17 07:17:51 -05:00
Jeffrey Morgan
41434a7cdc build intel mac with correct binary and compile flags 2023-11-16 22:14:51 -05:00
Michael Yang
71687ab809 Merge pull request #1164 from jmorganca/mxyng/faq
update faq
2023-11-16 17:20:18 -08:00
Michael Yang
d8842b4d4b update faq 2023-11-16 17:07:36 -08:00
Michael Yang
32add8577d placeholder environment variables 2023-11-16 16:57:39 -08:00
Michael Yang
585f9c01fa Merge pull request #1160 from jmorganca/mxyng/faq
update faq
2023-11-16 16:48:51 -08:00
Michael Yang
c13bde962d Update docs/faq.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-16 16:48:38 -08:00
Michael Yang
ee307937fd update faq 2023-11-16 16:46:43 -08:00
Matt Williams
ab6639bc47 Merge pull request #1074 from jmorganca/mattw/loganalysisexample
Log Analysis Example
2023-11-16 16:33:07 -08:00
Matt Williams
fefae84c06 example: function calling
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-16 16:26:29 -08:00
Jeffrey Morgan
dbe6e77472 Update README.md 2023-11-16 16:46:38 -05:00
Bruce MacDonald
4b3f4bc7d9 return failure details when unauthorized to push (#1131)
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-16 16:44:18 -05:00
Michael Yang
a5ccf742c1 fix cross repo mounts 2023-11-16 16:33:30 -05:00
Michael Yang
e33ef391cd fix push scope error for inherited model 2023-11-16 16:33:30 -05:00
yanndegat
75295b9528 install: fix enable contrib on debian 12 (#1151)
On debian 12, sources definitions have moved from
/etc/apt/sources.list to /etc/apt/sources.list.d/debian.sources
2023-11-16 15:53:06 -05:00
Matt Williams
db5ef3004c Merge pull request #1079 from jmorganca/mattw/jsonexample
Add example using JSON format output
2023-11-16 09:13:34 -08:00
Michael Yang
b5f158f046 add faq for proxies (#1147) 2023-11-16 11:43:37 -05:00
Piero Savastano
30141b42e9 Add Cheshire Cat to community integrations (#1124) 2023-11-16 11:30:54 -05:00
Dane Madsen
5f301ece1d Add Maid to Community Integrations (#1120) 2023-11-16 11:27:53 -05:00
Michael Yang
77954bea0e Merge pull request #898 from jmorganca/mxyng/build-context
create remote models
2023-11-15 16:41:12 -08:00
Michael Yang
54f92f01cb update docs 2023-11-15 15:28:15 -08:00
Michael
30ae6e731e Update randomaddresses.py 2023-11-15 18:24:50 -05:00
Michael
b28a30f7ba Update examples/python-json-datagenerator/predefinedschema.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-15 18:23:36 -05:00
Jeffrey Morgan
ecd71347ab Update faq.md 2023-11-15 18:17:13 -05:00
Jeffrey Morgan
8ee4cbea0f Remove table of contents in faq.md 2023-11-15 18:16:27 -05:00
Michael Yang
652d90e1c7 Update server/images.go
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-15 15:16:23 -08:00
Michael Yang
bc22d5a38b no blob response 2023-11-15 15:16:23 -08:00
Michael Yang
71d71d0988 update docs 2023-11-15 15:16:23 -08:00
Michael Yang
1901044b07 use checksum reference 2023-11-15 15:16:23 -08:00
Michael Yang
d660eebf22 fix create from model tag 2023-11-15 15:16:23 -08:00
Michael Yang
cac11c9137 update api docs 2023-11-15 15:16:23 -08:00
Michael Yang
a07c935d34 ignore non blobs 2023-11-15 15:16:23 -08:00
Michael Yang
1552cee59f client create modelfile 2023-11-15 15:16:23 -08:00
Michael Yang
3ca56b5ada add create modelfile field 2023-11-15 15:16:23 -08:00
Michael Yang
b0d14ed51c refactor create model 2023-11-15 15:16:23 -08:00
Matt Williams
f61f340279 FAQ: answer a few faq questions (#1128)
* faq: does ollama share my prompts

Signed-off-by: Matt Williams <m@technovangelist.com>

* faq: ollama and openai

Signed-off-by: Matt Williams <m@technovangelist.com>

* faq: vscode plugins

Signed-off-by: Matt Williams <m@technovangelist.com>

* faq: send a doc to Ollama

Signed-off-by: Matt Williams <m@technovangelist.com>

* extra spacing

Signed-off-by: Matt Williams <m@technovangelist.com>

* Update faq.md

* Update faq.md

---------

Signed-off-by: Matt Williams <m@technovangelist.com>
Co-authored-by: Michael <mchiang0610@users.noreply.github.com>
2023-11-15 18:05:13 -05:00
Michael Yang
686f85d6ca Merge pull request #1132 from jmorganca/mxyng/human-bytes
replace go-humanize with format.HumanBytes
2023-11-15 09:46:21 -08:00
bnodnarb
85951d25ef Created tutorial for running Ollama on NVIDIA Jetson devices (#1098) 2023-11-15 12:32:37 -05:00
Dane Madsen
779e196ef6 Merge branch 'jmorganca:main' into main 2023-11-15 21:38:07 +10:00
Michael Yang
01ea6002c4 replace go-humanize with format.HumanBytes 2023-11-14 14:57:41 -08:00
Jeffrey Morgan
423862042a treat ollama run model < file as entire prompt, not prompt-per-line (#1126)
Previously, `ollama run` treated a non-terminal stdin (such as `ollama run model < file`) as containing one prompt per line. To run inference on a multi-line prompt, the only non-API workaround was to run `ollama run` interactively and wrap the prompt in `"""..."""`.

Now, `ollama run` treats a non-terminal stdin as containing a single prompt. For example, if `myprompt.txt` is a multi-line file, then `ollama run model < myprompt.txt` would treat `myprompt.txt`'s entire contents as the prompt.

Co-authored-by: Quinn Slack <quinn@slack.org>
2023-11-14 16:42:21 -05:00
Bruce MacDonald
df18486c35 Move /generate format to optional parameters (#1127)
This field is optional and should be under the `Advanced parameters` header
2023-11-14 16:12:30 -05:00
Jeffrey Morgan
4e612a2e92 use stdout fd for terminal size (#1125) 2023-11-14 16:09:09 -05:00
Matt Williams
47ffb81db7 Update examples/python-json-datagenerator/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:33:34 -08:00
Matt Williams
69795d2db0 Update examples/python-json-datagenerator/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:33:16 -08:00
Matt Williams
acde0819d9 Update examples/python-json-datagenerator/randomaddresses.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:33:02 -08:00
Matt Williams
f748331aa3 Update examples/python-json-datagenerator/predefinedschema.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:32:45 -08:00
Matt Williams
f4edc302a8 Update examples/python-loganalysis/readme.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:31:22 -08:00
Matt Williams
64b7e0c218 Update examples/python-loganalysis/loganalysis.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:31:05 -08:00
Matt Williams
eced0d52ab Update examples/python-loganalysis/loganalysis.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:30:30 -08:00
Matt Williams
96bf9cafa7 Update examples/python-loganalysis/loganalysis.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-14 10:30:17 -08:00
Jeffrey Morgan
6e0f686afa --format json should work in interactive mode 2023-11-14 10:22:03 -05:00
Dane Madsen
c1a5220860 Update README.md 2023-11-14 15:31:31 +10:00
Dane Madsen
3b15175a70 Add maid to community integrations 2023-11-14 15:30:03 +10:00
Jeffrey Morgan
c1844bbee2 add json mode to cli (#1095) 2023-11-13 21:54:02 -05:00
Huy Le
cb745965ce adding ollama.nvim for visibility (#1115) 2023-11-13 17:00:17 -05:00
Enrico Ros
8d29b6a2b6 New big-AGI integration (#1078)
* New big-AGI integration

Ollama works great in big-AGI, and this document explains how to link the two projects.

* Update README.md
2023-11-13 16:59:00 -05:00
Ilya Breitburg
724aa64bee Add Dart library to README.md (#1106) 2023-11-13 14:50:42 -05:00
Michael Yang
d91c103e74 Merge pull request #1055 from dansreis/946-fix-incorrect-base-model-name
Fixed incorrect base model name
2023-11-13 08:42:55 -08:00
Kevin Hermawan
98ec7d81e3 Add OllamaKit to the community integrations (#1085) 2023-11-11 14:41:42 -08:00
Matt Williams
b6817a83d8 Add gif and finish readme
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-10 16:41:48 -06:00
Matt Williams
73f3448ede add example showing use of JSON format
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-10 16:33:56 -06:00
Daniel Reis
7c438f2c53 Replaced method 2023-11-10 20:22:03 +00:00
Daniel Reis
6e46338d44 Reverting previous changes 2023-11-10 20:21:35 +00:00
Jeffrey Morgan
cdddd3df65 add format to example python client 2023-11-10 10:22:21 -08:00
Daniel Hiltgen
afa61bdf45 Merge pull request #1075 from jmorganca/dhiltgen/unexpected-eof
Resume chunk download on UnexpectedEOF errors
2023-11-10 08:48:27 -08:00
Daniel Hiltgen
cc54a416c6 Resume chunk download on UnexpectedEOF errors
If the chunk download is interrupted, resume from where we left off
2023-11-10 08:29:42 -08:00
Matt Williams
c819d7f68a Merge pull request #955 from jmorganca/mattw/example-bash-compare
docs: add examples using bash to compare models
2023-11-10 08:59:32 -06:00
Matt Williams
e4f59ba073 better streaming plus gif
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-10 08:55:17 -06:00
Matt Williams
5de568bffe Add a simple log analysis example
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-10 08:28:52 -06:00
Jeffrey Morgan
5cba29b9d6 JSON mode: add `"format" as an api parameter (#1051)
* add `"format": "json"` as an API parameter
---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-09 16:44:02 -08:00
Daniel Reis
d17730356a Removed inline parse model path 2023-11-09 22:44:26 +00:00
Daniel Reis
32d79a6eea Using 'GetShortTagname' method instead 2023-11-09 22:40:37 +00:00
Bruce MacDonald
5b39503bcd document specifying multiple stop params (#1061) 2023-11-09 13:16:26 -08:00
Bruce MacDonald
1ae84bc2a2 skip gpu if less than 2GB VRAM are available (#1059) 2023-11-09 13:16:16 -08:00
Bruce MacDonald
db8bf336fc Update README.md 2023-11-09 12:53:24 -08:00
Nick Anderson
d77e094a90 Added gptel to list of integrations (#1062) 2023-11-09 12:52:36 -08:00
Matt Williams
dd3dc47ddb Merge pull request #992 from aashish2057/aashish2057/langchainjs_doc_update 2023-11-09 05:08:31 -08:00
Michael Yang
c5e1bbabda instead of static number of parameters for each model family, get the real number from the tensors (#1022)
* parse tensor info

* refactor decoder

* return actual parameter count

* explicit rounding

* s/Human/HumanNumber/
2023-11-08 17:55:46 -08:00
Bruce MacDonald
a49d6acc1e add a complete /generate options example (#1035) 2023-11-08 16:44:36 -08:00
Moritz Poldrack
6e9bcdb9b3 progressbar: make start and end seamless (#1042) 2023-11-08 16:42:40 -08:00
Matt Williams
13086363bd Update as per bmacd
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-08 18:09:05 -06:00
Bruce MacDonald
ec2a31e9b3 support raw generation requests (#952)
- add the optional `raw` generate request parameter to bypass prompt formatting and response context
-add raw request to docs
2023-11-08 14:05:02 -08:00
Amith Koujalgi
ec84c02d54 Add Ollama4j Java library to the list of community libraries (#1044) 2023-11-08 11:04:32 -08:00
Kevin Hermawan
2a88b66bc9 Add Ollamac to community integrations (#1043) 2023-11-08 11:01:09 -08:00
Jeffrey Morgan
2d0faea96c clean up README.md 2023-11-08 00:03:29 -08:00
Jeffrey Morgan
637142181a clean up README.md 2023-11-07 23:52:31 -08:00
Matt Williams
bcbff421c9 Merge pull request #1023 from jmorganca/mattw/wherearemodelsfaq 2023-11-07 17:59:54 -08:00
thealhu
1359d6cf3b Fix sudo variable in install.sh (#1034)
It was forgotten to replace sudo at one place with the variable for sudo.
2023-11-07 09:59:57 -08:00
Omar Magdy
6e2d0224d9 Added logseq ollama plugin (#1029) 2023-11-07 09:58:13 -08:00
Ikko Eltociear Ashimine
921406f721 Update client.py (#1026)
recieve -> receive
2023-11-07 09:55:47 -08:00
Michael Yang
c7047d7353 Merge pull request #959 from jmorganca/mxyng/example-k8s 2023-11-07 10:43:21 -06:00
Matt Williams
1d155caba3 docs: clarify where the models are stored in the faq
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-06 14:38:49 -08:00
Michael Yang
866324b9a5 Merge pull request #943 from tjbck/patch-1
doc: categorised community integrations + added ollama-webui
2023-11-06 11:35:39 -08:00
Michael Yang
145e060855 Apply suggestions from code review
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-06 11:32:23 -08:00
Michael Yang
146072113d Merge pull request #993 from jmorganca/mxyng/cleanup
cleanup upload and download errors
2023-11-06 11:32:12 -08:00
Timothy Jaeryang Baek
33d31d1b56 Merge branch 'main' into patch-1 2023-11-06 14:27:02 -05:00
Dr. David A. Kunz
274c6cbf4c Added gen.nvim to community integrations (#996) 2023-11-06 10:51:41 -08:00
Elton Renda
7ebbd89bbf add hass-ollama-conversation (#999) 2023-11-06 10:50:35 -08:00
Lars Grammel
9079b1bb6d Add ModelFusion community integration (#1020) 2023-11-06 10:46:16 -08:00
Timothy Jaeryang Baek
6febde7200 Merge branch 'main' into patch-1 2023-11-04 19:12:18 -05:00
pepperoni21
325cfcd9ff Added ollama-rs to community integrations (#995)
Co-authored-by: pepperoni21 <pepperoni2100@gmail.com>
2023-11-04 14:51:29 -07:00
Jeffrey Morgan
639d0fd070 Update README.md 2023-11-04 12:24:24 -07:00
Jeffrey Morgan
e21579a0f1 Restore system prompt on requests 2023-11-03 17:26:45 -07:00
Jeffrey Morgan
c44b619428 remove unused fmt.Println 2023-11-03 17:24:58 -07:00
Michael Yang
434a6f9d46 return last error 2023-11-03 16:49:51 -07:00
aashish2057
b13586cc72 update langchainjs doc 2023-11-03 18:45:19 -05:00
Jeffrey Morgan
17678b7225 Restore system prompt on requests and default num_keep to 0 2023-11-03 13:25:25 -07:00
Michael Yang
84725ec7e3 refactor part reset 2023-11-03 09:20:32 -07:00
Bruce MacDonald
6109bebba6 reformat api docs for more examples (#972) 2023-11-03 10:57:00 -04:00
Noah Gitsham
8ae8c9fa8c Remove duplicate "install" in GPU support warning (#984) 2023-11-03 00:45:14 -07:00
Noah Gitsham
f39daff461 Add missing "be" to GPU support warning message (#983) 2023-11-02 18:37:12 -07:00
Jeffrey Morgan
c50b01bc21 check request.Context for initial system prompt 2023-11-02 18:17:00 -07:00
Bruce MacDonald
b9dc875401 remove modelfile context deprecated in v0.0.7 (#974) 2023-11-02 20:52:56 -04:00
Jeffrey Morgan
06589a3b30 Set NumKeep to 4 by default (#982) 2023-11-02 17:26:11 -07:00
Michael Yang
1fd511e661 Merge pull request #975 from jmorganca/mxyng/downloads
update downloads to use retry wrapper
2023-11-02 16:12:48 -07:00
Michael Yang
c01bbe94fd Merge pull request #979 from jmorganca/mxyng/num-keep
update default NumKeep
2023-11-02 15:48:44 -07:00
Jeffrey Morgan
1beb5645a9 only use system prompt if context is not provided (#978) 2023-11-02 15:48:02 -07:00
Michael Yang
6db3691b8f update default NumKeep 2023-11-02 15:47:35 -07:00
Michael Yang
fe5a872444 fix upload 2023-11-02 13:25:58 -07:00
Michael Yang
d39709260f download with retry 2023-11-02 13:16:11 -07:00
Michael Yang
60bb3c03a1 use http.Method 2023-11-02 13:12:45 -07:00
Jeffrey Morgan
2e53704685 default rope params to 0 for new models (#968) 2023-11-02 08:41:30 -07:00
Michael Yang
527f9a7975 Merge pull request #966 from jmorganca/mxyng/fix-log 2023-11-01 17:49:10 -07:00
Michael Yang
c4cc738cbf fix log 2023-11-01 17:18:11 -07:00
Michael Yang
2c6189f4fe Merge pull request #750 from jmorganca/mxyng/concurrent-uploads
concurrent uploads
2023-11-01 15:00:01 -07:00
Michael Yang
dccac8c8fa k8s example 2023-11-01 14:52:58 -07:00
Michael Yang
c05ab9a86e Merge pull request #965 from jmorganca/mxyng/go-mod-tidy
go mod tidy
2023-11-01 11:55:43 -07:00
Michael Yang
f42f3d9b27 go fmt 2023-11-01 11:55:08 -07:00
Michael Yang
341fb7e35f go mod tidy 2023-11-01 11:54:25 -07:00
Michael
f31961637f Update README.md 2023-11-01 12:20:55 -04:00
Michael Yang
ec3614812a Merge pull request #960 from jmorganca/mxyng/fix-tautology 2023-11-01 08:30:49 -07:00
Michael Yang
f14969314a Merge pull request #958 from jmorganca/mxyng/append-ld-library-path 2023-11-01 08:30:38 -07:00
Bruce MacDonald
1fb9288661 notify that the ollama api is available after linux install (#954) 2023-11-01 11:28:26 -04:00
Matt Williams
01a03caa20 Merge pull request #956 from jmorganca/mattw/apidocupdate 2023-10-31 21:43:11 -07:00
Michael Yang
bf6786bb39 fix tautology 2023-10-31 20:49:48 -07:00
Michael Yang
642128b75a append LD_LIBRARY_PATH 2023-10-31 15:54:49 -07:00
Matt Williams
f21bd6210d docs: clarify and clean up API docs
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-10-31 13:11:33 -07:00
Matt Williams
80362fedce better readme
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-10-31 12:40:46 -07:00
Matt Williams
5757925060 add a gif
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-10-31 11:52:01 -07:00
Michael
4512301756 Update README.md 2023-10-31 13:25:36 -04:00
Matt Williams
2236a93efc docs: add examples using bash to compare models
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-10-31 09:12:39 -07:00
Matt Williams
ad88799411 Merge pull request #949 from jmorganca/matt/fixPrivateGPT
fix: private gpt example was broken due to changes in chroma
2023-10-30 17:17:00 -07:00
Bruce MacDonald
0818b5e318 readline windows terminal support (#950)
- update the readline package to have basic support on windows, this is not full feature parity with the unix cli yet
2023-10-30 16:18:12 -04:00
Matt Williams
1df6100c77 Update examples/langchain-python-rag-privategpt/privateGPT.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-10-30 12:48:17 -07:00
Matt Williams
5c48fe1fb0 Update examples/langchain-python-rag-privategpt/constants.py
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-10-30 12:47:56 -07:00
Dirk Loss
874bb31986 Fix conversion command for gptneox (#948) 2023-10-30 14:34:29 -04:00
Matt Williams
f7856a57eb fix: private gpt example was broken due to changes in chroma
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-10-30 10:56:25 -07:00
Bruce MacDonald
f9a4281124 clean up: remove server functions from client (#937) 2023-10-30 11:10:18 -04:00
Timothy Jaeryang Baek
96da0792e6 doc: OllamaSharp for .NET moved to libraries 2023-10-28 16:18:38 -05:00
Timothy Jaeryang Baek
95d24262fc doc: categorised community integrations + added web-ui 2023-10-28 16:02:13 -05:00
Jeffrey Morgan
8d03bd7b54 remove +build directive in term.go 2023-10-28 09:56:03 -07:00
Michael Yang
115fc56eb7 calculate and verify md5 checksum 2023-10-27 17:07:33 -07:00
Michael Yang
186f685224 retry PUT 2023-10-27 17:07:33 -07:00
Michael Yang
12efcbb057 comments 2023-10-27 17:07:33 -07:00
Michael Yang
4e09aab8b9 concurrent uploads 2023-10-27 17:07:33 -07:00
326 changed files with 63323 additions and 25716 deletions

View File

@@ -1,8 +1,9 @@
.vscode
ollama
app
macapp
dist
scripts
llm/llama.cpp/ggml
llm/llama.cpp/gguf
llm/llama.cpp
.env
.cache
test_data

1
.gitattributes vendored Normal file
View File

@@ -0,0 +1 @@
llm/ext_server/* linguist-vendored

View File

@@ -0,0 +1,60 @@
name: Bug report
labels: [bug]
description: Something isn't working right.
body:
- type: textarea
id: description
attributes:
label: What is the issue?
description: What happened? What did you expect to happen?
validations:
required: true
- type: dropdown
id: os
attributes:
label: OS
description: Which operating system are you using?
multiple: true
options:
- Linux
- macOS
- Windows
- Docker
- WSL2
validations:
required: false
- type: dropdown
id: gpu
attributes:
label: GPU
description: Which GPU are you using?
multiple: true
options:
- Nvidia
- AMD
- Intel
- Apple
- Other
validations:
required: false
- type: dropdown
id: cpu
attributes:
label: CPU
description: Which CPU are you using?
multiple: true
options:
- Intel
- AMD
- Apple
- Other
validations:
required: false
- type: input
id: version
attributes:
label: Ollama version
description: What version of Ollama are you using? (`ollama --version`)
placeholder: e.g., 0.1.32
validations:
required: false

View File

@@ -0,0 +1,6 @@
---
name: Feature request
about: Request a new feature
labels: feature request
---

View File

@@ -0,0 +1,5 @@
---
name: Model request
about: Request support for a new model to be added to Ollama
labels: model request
---

8
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

@@ -0,0 +1,8 @@
blank_issues_enabled: true
contact_links:
- name: Help
url: https://discord.com/invite/ollama
about: Please join our Discord server for help using Ollama
- name: Troubleshooting
url: https://github.com/ollama/ollama/blob/main/docs/faq.md#faq
about: See the FAQ for common issues and solutions

24
.github/workflows/latest.yaml vendored Normal file
View File

@@ -0,0 +1,24 @@
name: latest
on:
release:
types: [released]
jobs:
update-latest:
environment: release
runs-on: linux
steps:
- uses: actions/checkout@v4
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ vars.DOCKER_USER }}
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
- name: Tag images as latest
env:
PUSH: "1"
shell: bash
run: |
export "VERSION=${GITHUB_REF_NAME#v}"
./scripts/tag_latest.sh

473
.github/workflows/release.yaml vendored Normal file
View File

@@ -0,0 +1,473 @@
name: release
on:
push:
tags:
- 'v*'
jobs:
# Full build of the Mac assets
build-darwin:
runs-on: macos-12
environment: release
steps:
- uses: actions/checkout@v4
- name: Set Version
shell: bash
run: |
echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
echo "RELEASE_VERSION=$(echo ${GITHUB_REF_NAME} | cut -f1 -d-)" >> $GITHUB_ENV
- name: key
env:
MACOS_SIGNING_KEY: ${{ secrets.MACOS_SIGNING_KEY }}
MACOS_SIGNING_KEY_PASSWORD: ${{ secrets.MACOS_SIGNING_KEY_PASSWORD }}
run: |
echo $MACOS_SIGNING_KEY | base64 --decode > certificate.p12
security create-keychain -p password build.keychain
security default-keychain -s build.keychain
security unlock-keychain -p password build.keychain
security import certificate.p12 -k build.keychain -P $MACOS_SIGNING_KEY_PASSWORD -T /usr/bin/codesign
security set-key-partition-list -S apple-tool:,apple:,codesign: -s -k password build.keychain
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- name: Build Darwin
env:
APPLE_IDENTITY: ${{ secrets.APPLE_IDENTITY }}
APPLE_PASSWORD: ${{ secrets.APPLE_PASSWORD }}
APPLE_TEAM_ID: ${{ vars.APPLE_TEAM_ID }}
APPLE_ID: ${{ vars.APPLE_ID }}
SDKROOT: /Applications/Xcode_13.4.1.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk
DEVELOPER_DIR: /Applications/Xcode_13.4.1.app/Contents/Developer
run: |
./scripts/build_darwin.sh
- uses: actions/upload-artifact@v4
with:
name: dist-darwin
path: |
dist/*arwin*
!dist/*-cov
# Windows builds take a long time to both install the dependencies and build, so parallelize
# CPU generation step
generate-windows-cpu:
environment: release
runs-on: windows
env:
KEY_CONTAINER: ${{ vars.KEY_CONTAINER }}
steps:
- uses: actions/checkout@v4
- name: Set Version
shell: bash
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- uses: 'google-github-actions/auth@v2'
with:
project_id: 'ollama'
credentials_json: '${{ secrets.GOOGLE_SIGNING_CREDENTIALS }}'
- run: echo "${{ vars.OLLAMA_CERT }}" > ollama_inc.crt
- name: install Windows SDK 8.1 to get signtool
run: |
$ErrorActionPreference = "Stop"
write-host "downloading SDK"
Invoke-WebRequest -Uri "https://go.microsoft.com/fwlink/p/?LinkId=323507" -OutFile "${env:RUNNER_TEMP}\sdksetup.exe"
Start-Process "${env:RUNNER_TEMP}\sdksetup.exe" -ArgumentList @("/q") -NoNewWindow -Wait
write-host "Win SDK 8.1 installed"
gci -path 'C:\Program Files (x86)\Windows Kits\' -r -fi 'signtool.exe'
- name: install signing plugin
run: |
$ErrorActionPreference = "Stop"
write-host "downloading plugin"
Invoke-WebRequest -Uri "https://github.com/GoogleCloudPlatform/kms-integrations/releases/download/cng-v1.0/kmscng-1.0-windows-amd64.zip" -OutFile "${env:RUNNER_TEMP}\plugin.zip"
Expand-Archive -Path "${env:RUNNER_TEMP}\plugin.zip" -DestinationPath ${env:RUNNER_TEMP}\plugin\
write-host "Installing plugin"
& "${env:RUNNER_TEMP}\plugin\*\kmscng.msi" /quiet
write-host "plugin installed"
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- run: go get ./...
- run: |
$gopath=(get-command go).source | split-path -parent
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$env:PATH"
go generate -x ./...
name: go generate
- uses: actions/upload-artifact@v4
with:
name: generate-windows-cpu
path: |
llm/build/**/bin/*
llm/build/**/*.a
dist/windows-amd64/**
# ROCm generation step
generate-windows-rocm:
environment: release
runs-on: windows
env:
KEY_CONTAINER: ${{ vars.KEY_CONTAINER }}
steps:
- uses: actions/checkout@v4
- name: Set Version
shell: bash
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- uses: 'google-github-actions/auth@v2'
with:
project_id: 'ollama'
credentials_json: '${{ secrets.GOOGLE_SIGNING_CREDENTIALS }}'
- run: echo "${{ vars.OLLAMA_CERT }}" > ollama_inc.crt
- name: install Windows SDK 8.1 to get signtool
run: |
$ErrorActionPreference = "Stop"
write-host "downloading SDK"
Invoke-WebRequest -Uri "https://go.microsoft.com/fwlink/p/?LinkId=323507" -OutFile "${env:RUNNER_TEMP}\sdksetup.exe"
Start-Process "${env:RUNNER_TEMP}\sdksetup.exe" -ArgumentList @("/q") -NoNewWindow -Wait
write-host "Win SDK 8.1 installed"
gci -path 'C:\Program Files (x86)\Windows Kits\' -r -fi 'signtool.exe'
- name: install signing plugin
run: |
$ErrorActionPreference = "Stop"
write-host "downloading plugin"
Invoke-WebRequest -Uri "https://github.com/GoogleCloudPlatform/kms-integrations/releases/download/cng-v1.0/kmscng-1.0-windows-amd64.zip" -OutFile "${env:RUNNER_TEMP}\plugin.zip"
Expand-Archive -Path "${env:RUNNER_TEMP}\plugin.zip" -DestinationPath ${env:RUNNER_TEMP}\plugin\
write-host "Installing plugin"
& "${env:RUNNER_TEMP}\plugin\*\kmscng.msi" /quiet
write-host "plugin installed"
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- name: 'Install ROCm'
run: |
$ErrorActionPreference = "Stop"
write-host "downloading AMD HIP Installer"
Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-23.Q4-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
write-host "Installing AMD HIP"
Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait
write-host "Completed AMD HIP"
- name: 'Verify ROCm'
run: |
& 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version
- run: go get ./...
- run: |
$gopath=(get-command go).source | split-path -parent
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$env:PATH"
$env:OLLAMA_SKIP_CPU_GENERATE="1"
$env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
go generate -x ./...
name: go generate
- name: 'gather rocm dependencies'
run: |
$HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
md "dist\deps\bin\rocblas\library"
cp "${HIP_PATH}\bin\hipblas.dll" "dist\deps\bin\"
cp "${HIP_PATH}\bin\rocblas.dll" "dist\deps\bin\"
cp "${HIP_PATH}\bin\rocblas\library\*" "dist\deps\bin\rocblas\library\"
- uses: actions/upload-artifact@v4
with:
name: generate-windows-rocm
path: |
llm/build/**/bin/*
dist/windows-amd64/**
- uses: actions/upload-artifact@v4
with:
name: windows-rocm-deps
path: dist/deps/*
# CUDA generation step
generate-windows-cuda:
environment: release
runs-on: windows
env:
KEY_CONTAINER: ${{ vars.KEY_CONTAINER }}
steps:
- uses: actions/checkout@v4
- name: Set Version
shell: bash
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- uses: 'google-github-actions/auth@v2'
with:
project_id: 'ollama'
credentials_json: '${{ secrets.GOOGLE_SIGNING_CREDENTIALS }}'
- run: echo "${{ vars.OLLAMA_CERT }}" > ollama_inc.crt
- name: install Windows SDK 8.1 to get signtool
run: |
$ErrorActionPreference = "Stop"
write-host "downloading SDK"
Invoke-WebRequest -Uri "https://go.microsoft.com/fwlink/p/?LinkId=323507" -OutFile "${env:RUNNER_TEMP}\sdksetup.exe"
Start-Process "${env:RUNNER_TEMP}\sdksetup.exe" -ArgumentList @("/q") -NoNewWindow -Wait
write-host "Win SDK 8.1 installed"
gci -path 'C:\Program Files (x86)\Windows Kits\' -r -fi 'signtool.exe'
- name: install signing plugin
run: |
$ErrorActionPreference = "Stop"
write-host "downloading plugin"
Invoke-WebRequest -Uri "https://github.com/GoogleCloudPlatform/kms-integrations/releases/download/cng-v1.0/kmscng-1.0-windows-amd64.zip" -OutFile "${env:RUNNER_TEMP}\plugin.zip"
Expand-Archive -Path "${env:RUNNER_TEMP}\plugin.zip" -DestinationPath ${env:RUNNER_TEMP}\plugin\
write-host "Installing plugin"
& "${env:RUNNER_TEMP}\plugin\*\kmscng.msi" /quiet
write-host "plugin installed"
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- name: 'Install CUDA'
run: |
$ErrorActionPreference = "Stop"
write-host "downloading CUDA Installer"
Invoke-WebRequest -Uri "https://developer.download.nvidia.com/compute/cuda/11.3.1/local_installers/cuda_11.3.1_465.89_win10.exe" -OutFile "${env:RUNNER_TEMP}\cuda-install.exe"
write-host "Installing CUDA"
Start-Process "${env:RUNNER_TEMP}\cuda-install.exe" -ArgumentList '-s' -NoNewWindow -Wait
write-host "Completed CUDA"
$cudaPath=((resolve-path "c:\Program Files\NVIDIA*\CUDA\v*\bin\nvcc.exe")[0].path | split-path | split-path)
$cudaVer=($cudaPath | split-path -leaf ) -replace 'v(\d+).(\d+)', '$1_$2'
echo "$cudaPath\bin" >> $env:GITHUB_PATH
echo "CUDA_PATH=$cudaPath" >> $env:GITHUB_ENV
echo "CUDA_PATH_V${cudaVer}=$cudaPath" >> $env:GITHUB_ENV
echo "CUDA_PATH_VX_Y=CUDA_PATH_V${cudaVer}" >> $env:GITHUB_ENV
- name: 'Verify CUDA'
run: nvcc -V
- run: go get ./...
- name: go generate
run: |
$gopath=(get-command go).source | split-path -parent
$cudabin=(get-command nvcc).source | split-path
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$cudabin;$env:PATH"
$env:OLLAMA_SKIP_CPU_GENERATE="1"
go generate -x ./...
- name: 'gather cuda dependencies'
run: |
$NVIDIA_DIR=(resolve-path 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\*\bin\')[0]
md "dist\deps"
cp "${NVIDIA_DIR}\cudart64_*.dll" "dist\deps\"
cp "${NVIDIA_DIR}\cublas64_*.dll" "dist\deps\"
cp "${NVIDIA_DIR}\cublasLt64_*.dll" "dist\deps\"
- uses: actions/upload-artifact@v4
with:
name: generate-windows-cuda
path: |
llm/build/**/bin/*
dist/windows-amd64/**
- uses: actions/upload-artifact@v4
with:
name: windows-cuda-deps
path: dist/deps/*
# Import the prior generation steps and build the final windows assets
build-windows:
environment: release
runs-on: windows
needs:
- generate-windows-cuda
- generate-windows-rocm
- generate-windows-cpu
env:
KEY_CONTAINER: ${{ vars.KEY_CONTAINER }}
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Set Version
shell: bash
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- uses: 'google-github-actions/auth@v2'
with:
project_id: 'ollama'
credentials_json: '${{ secrets.GOOGLE_SIGNING_CREDENTIALS }}'
- run: echo "${{ vars.OLLAMA_CERT }}" > ollama_inc.crt
- name: install Windows SDK 8.1 to get signtool
run: |
$ErrorActionPreference = "Stop"
write-host "downloading SDK"
Invoke-WebRequest -Uri "https://go.microsoft.com/fwlink/p/?LinkId=323507" -OutFile "${env:RUNNER_TEMP}\sdksetup.exe"
Start-Process "${env:RUNNER_TEMP}\sdksetup.exe" -ArgumentList @("/q") -NoNewWindow -Wait
write-host "Win SDK 8.1 installed"
gci -path 'C:\Program Files (x86)\Windows Kits\' -r -fi 'signtool.exe'
- name: install signing plugin
run: |
$ErrorActionPreference = "Stop"
write-host "downloading plugin"
Invoke-WebRequest -Uri "https://github.com/GoogleCloudPlatform/kms-integrations/releases/download/cng-v1.0/kmscng-1.0-windows-amd64.zip" -OutFile "${env:RUNNER_TEMP}\plugin.zip"
Expand-Archive -Path "${env:RUNNER_TEMP}\plugin.zip" -DestinationPath ${env:RUNNER_TEMP}\plugin\
write-host "Installing plugin"
& "${env:RUNNER_TEMP}\plugin\*\kmscng.msi" /quiet
write-host "plugin installed"
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- run: go get
- uses: actions/download-artifact@v4
with:
name: generate-windows-cpu
- uses: actions/download-artifact@v4
with:
name: generate-windows-cuda
- uses: actions/download-artifact@v4
with:
name: windows-cuda-deps
- uses: actions/download-artifact@v4
with:
name: windows-rocm-deps
- uses: actions/download-artifact@v4
with:
name: generate-windows-rocm
- run: dir llm/build
- run: |
$gopath=(get-command go).source | split-path -parent
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$env:PATH"
$env:OLLAMA_SKIP_GENERATE="1"
& .\scripts\build_windows.ps1
- uses: actions/upload-artifact@v4
with:
name: dist-windows
path: |
dist/OllamaSetup.exe
dist/ollama-windows-*.zip
# Linux x86 assets built using the container based build
build-linux-amd64:
environment: release
runs-on: linux
env:
OLLAMA_SKIP_MANIFEST_CREATE: '1'
BUILD_ARCH: amd64
PUSH: '1'
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Set Version
shell: bash
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ vars.DOCKER_USER }}
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
- run: |
./scripts/build_linux.sh
./scripts/build_docker.sh
mv dist/deps/* dist/
- uses: actions/upload-artifact@v4
with:
name: dist-linux-amd64
path: |
dist/*linux*
!dist/*-cov
# Linux ARM assets built using the container based build
# (at present, docker isn't pre-installed on arm ubunutu images)
build-linux-arm64:
environment: release
runs-on: linux-arm64
env:
OLLAMA_SKIP_MANIFEST_CREATE: '1'
BUILD_ARCH: arm64
PUSH: '1'
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Set Version
shell: bash
run: echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
- name: 'Install Docker'
run: |
# Add Docker's official GPG key:
env
uname -a
sudo apt-get update
sudo apt-get install -y ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc
# Add the repository to Apt sources:
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io
sudo usermod -aG docker $USER
sudo apt-get install acl
sudo setfacl --modify user:$USER:rw /var/run/docker.sock
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ vars.DOCKER_USER }}
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
- run: |
./scripts/build_linux.sh
./scripts/build_docker.sh
- uses: actions/upload-artifact@v4
with:
name: dist-linux-arm64
path: |
dist/*linux*
!dist/*-cov
# Aggregate all the assets and ship a release
release:
needs:
- build-darwin
- build-windows
- build-linux-amd64
- build-linux-arm64
runs-on: linux
environment: release
permissions:
contents: write
env:
OLLAMA_SKIP_IMAGE_BUILD: '1'
PUSH: '1'
steps:
- uses: actions/checkout@v4
- name: Set Version
shell: bash
run: |
echo "VERSION=${GITHUB_REF_NAME#v}" >> $GITHUB_ENV
echo "RELEASE_VERSION=$(echo ${GITHUB_REF_NAME} | cut -f1 -d-)" >> $GITHUB_ENV
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ vars.DOCKER_USER }}
password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
- run: ./scripts/build_docker.sh
- name: Retrieve built artifact
uses: actions/download-artifact@v4
with:
path: dist
pattern: dist-*
merge-multiple: true
- run: |
ls -lh dist/
(cd dist; sha256sum * > sha256sum.txt)
cat dist/sha256sum.txt
- uses: ncipollo/release-action@v1
with:
name: ${{ env.RELEASE_VERSION }}
allowUpdates: true
artifacts: 'dist/*'
draft: true
prerelease: true
omitBodyDuringUpdate: true
generateReleaseNotes: true
omitDraftDuringUpdate: true
omitPrereleaseDuringUpdate: true
replacesArtifacts: true

319
.github/workflows/test.yaml vendored Normal file
View File

@@ -0,0 +1,319 @@
name: test
concurrency:
# For PRs, later CI runs preempt previous ones. e.g. a force push on a PR
# cancels running CI jobs and starts all new ones.
#
# For non-PR pushes, concurrency.group needs to be unique for every distinct
# CI run we want to have happen. Use run_id, which in practice means all
# non-PR CI runs will be allowed to run without preempting each other.
group: ${{ github.workflow }}-$${{ github.pull_request.number || github.run_id }}
cancel-in-progress: true
on:
pull_request:
paths:
- '**/*'
- '!docs/**'
- '!README.md'
jobs:
changes:
runs-on: ubuntu-latest
outputs:
GENERATE: ${{ steps.changes.outputs.GENERATE }}
GENERATE_CUDA: ${{ steps.changes.outputs.GENERATE_CUDA }}
GENERATE_ROCM: ${{ steps.changes.outputs.GENERATE_ROCM }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- id: changes
run: |
changed() {
git diff-tree -r --no-commit-id --name-only \
$(git merge-base ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }}) \
${{ github.event.pull_request.head.sha }} \
| xargs python3 -c "import sys; print(any([x.startswith('$1') for x in sys.argv[1:]]))"
}
{
echo GENERATE=$(changed llm/)
echo GENERATE_CUDA=$(changed llm/)
echo GENERATE_ROCM=$(changed llm/)
} >>$GITHUB_OUTPUT
generate:
needs: [changes]
if: ${{ needs.changes.outputs.GENERATE == 'True' }}
strategy:
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
arch: [amd64, arm64]
exclude:
- os: ubuntu-latest
arch: arm64
- os: windows-2019
arch: arm64
runs-on: ${{ matrix.os }}
env:
GOARCH: ${{ matrix.arch }}
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- run: go get ./...
- run: |
$gopath=(get-command go).source | split-path -parent
$gccpath=(get-command gcc).source | split-path -parent
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$gccpath;$env:PATH"
echo $env:PATH
go generate -x ./...
if: ${{ startsWith(matrix.os, 'windows-') }}
name: 'Windows Go Generate'
- run: go generate -x ./...
if: ${{ ! startsWith(matrix.os, 'windows-') }}
name: 'Unix Go Generate'
- uses: actions/upload-artifact@v4
with:
name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
path: |
llm/build/**/bin/*
llm/build/**/*.a
generate-cuda:
needs: [changes]
if: ${{ needs.changes.outputs.GENERATE_CUDA == 'True' }}
strategy:
matrix:
cuda-version:
- '11.8.0'
runs-on: linux
container: nvidia/cuda:${{ matrix.cuda-version }}-devel-ubuntu20.04
steps:
- run: |
apt-get update && apt-get install -y git build-essential curl
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
| tar -zx -C /usr --strip-components 1
env:
DEBIAN_FRONTEND: noninteractive
- uses: actions/checkout@v4
- uses: actions/setup-go@v4
with:
go-version-file: go.mod
cache: true
- run: go get ./...
- run: |
git config --global --add safe.directory /__w/ollama/ollama
go generate -x ./...
env:
OLLAMA_SKIP_CPU_GENERATE: '1'
- uses: actions/upload-artifact@v4
with:
name: cuda-${{ matrix.cuda-version }}-libraries
path: |
llm/build/**/bin/*
dist/windows-amd64/**
generate-rocm:
needs: [changes]
if: ${{ needs.changes.outputs.GENERATE_ROCM == 'True' }}
strategy:
matrix:
rocm-version:
- '6.0.2'
runs-on: linux
container: rocm/dev-ubuntu-20.04:${{ matrix.rocm-version }}
steps:
- run: |
apt-get update && apt-get install -y git build-essential curl rocm-libs
curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
| tar -zx -C /usr --strip-components 1
env:
DEBIAN_FRONTEND: noninteractive
- uses: actions/checkout@v4
- uses: actions/setup-go@v4
with:
go-version-file: go.mod
cache: true
- run: go get ./...
- run: |
git config --global --add safe.directory /__w/ollama/ollama
go generate -x ./...
env:
OLLAMA_SKIP_CPU_GENERATE: '1'
- uses: actions/upload-artifact@v4
with:
name: rocm-${{ matrix.rocm-version }}-libraries
path: |
llm/build/**/bin/*
dist/windows-amd64/**
# ROCm generation step
generate-windows-rocm:
needs: [changes]
if: ${{ needs.changes.outputs.GENERATE_ROCM == 'True' }}
runs-on: windows
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- name: 'Install ROCm'
run: |
$ErrorActionPreference = "Stop"
write-host "downloading AMD HIP Installer"
Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-23.Q4-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
write-host "Installing AMD HIP"
Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -Wait
write-host "Completed AMD HIP"
- name: 'Verify ROCm'
run: |
& 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' --version
- run: go get ./...
- run: |
$gopath=(get-command go).source | split-path -parent
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$env:PATH"
$env:OLLAMA_SKIP_CPU_GENERATE="1"
$env:HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)
go generate -x ./...
name: go generate
env:
OLLAMA_SKIP_CPU_GENERATE: '1'
# TODO - do we need any artifacts?
# CUDA generation step
generate-windows-cuda:
needs: [changes]
if: ${{ needs.changes.outputs.GENERATE_CUDA == 'True' }}
runs-on: windows
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- name: 'Install CUDA'
run: |
$ErrorActionPreference = "Stop"
write-host "downloading CUDA Installer"
Invoke-WebRequest -Uri "https://developer.download.nvidia.com/compute/cuda/11.3.1/local_installers/cuda_11.3.1_465.89_win10.exe" -OutFile "${env:RUNNER_TEMP}\cuda-install.exe"
write-host "Installing CUDA"
Start-Process "${env:RUNNER_TEMP}\cuda-install.exe" -ArgumentList '-s' -NoNewWindow -Wait
write-host "Completed CUDA"
$cudaPath=((resolve-path "c:\Program Files\NVIDIA*\CUDA\v*\bin\nvcc.exe")[0].path | split-path | split-path)
$cudaVer=($cudaPath | split-path -leaf ) -replace 'v(\d+).(\d+)', '$1_$2'
echo "$cudaPath\bin" >> $env:GITHUB_PATH
echo "CUDA_PATH=$cudaPath" >> $env:GITHUB_ENV
echo "CUDA_PATH_V${cudaVer}=$cudaPath" >> $env:GITHUB_ENV
echo "CUDA_PATH_VX_Y=CUDA_PATH_V${cudaVer}" >> $env:GITHUB_ENV
- name: 'Verify CUDA'
run: nvcc -V
- run: go get ./...
- name: go generate
run: |
$gopath=(get-command go).source | split-path -parent
$cudabin=(get-command nvcc).source | split-path
& "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
cd $env:GITHUB_WORKSPACE
$env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
$env:PATH="$gopath;$cudabin;$env:PATH"
$env:OLLAMA_SKIP_CPU_GENERATE="1"
go generate -x ./...
env:
OLLAMA_SKIP_CPU_GENERATE: '1'
# TODO - do we need any artifacts?
lint:
strategy:
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
arch: [amd64, arm64]
exclude:
- os: ubuntu-latest
arch: arm64
- os: windows-2019
arch: arm64
- os: macos-latest
arch: amd64
runs-on: ${{ matrix.os }}
env:
GOARCH: ${{ matrix.arch }}
CGO_ENABLED: '1'
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: false
- run: |
case ${{ matrix.arch }} in
amd64) echo ARCH=x86_64 ;;
arm64) echo ARCH=arm64 ;;
esac >>$GITHUB_ENV
shell: bash
- run: |
mkdir -p llm/build/linux/$ARCH/stub/bin
touch llm/build/linux/$ARCH/stub/bin/ollama_llama_server
if: ${{ startsWith(matrix.os, 'ubuntu-') }}
- run: |
mkdir -p llm/build/darwin/$ARCH/stub/bin
touch llm/build/darwin/$ARCH/stub/bin/ollama_llama_server
if: ${{ startsWith(matrix.os, 'macos-') }}
- uses: golangci/golangci-lint-action@v4
with:
args: --timeout 8m0s -v
test:
strategy:
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
arch: [amd64]
exclude:
- os: ubuntu-latest
arch: arm64
- os: windows-2019
arch: arm64
runs-on: ${{ matrix.os }}
env:
GOARCH: ${{ matrix.arch }}
CGO_ENABLED: '1'
OLLAMA_CPU_TARGET: 'static'
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: true
- run: |
case ${{ matrix.arch }} in
amd64) echo ARCH=x86_64 ;;
arm64) echo ARCH=arm64 ;;
esac >>$GITHUB_ENV
shell: bash
- run: |
mkdir -p llm/build/linux/$ARCH/stub/bin
touch llm/build/linux/$ARCH/stub/bin/ollama_llama_server
if: ${{ startsWith(matrix.os, 'ubuntu-') }}
- run: |
mkdir -p llm/build/darwin/$ARCH/stub/bin
touch llm/build/darwin/$ARCH/stub/bin/ollama_llama_server
if: ${{ startsWith(matrix.os, 'macos-') }}
shell: bash
- run: go generate ./...
- run: go build
- run: go test -v ./...
- uses: actions/upload-artifact@v4
with:
name: ${{ matrix.os }}-binaries
path: ollama

6
.gitignore vendored
View File

@@ -6,3 +6,9 @@
dist
ollama
ggml-metal.metal
.cache
*.exe
.idea
test_data
*.crt
llm/build

14
.gitmodules vendored
View File

@@ -1,10 +1,4 @@
[submodule "llm/llama.cpp/ggml"]
path = llm/llama.cpp/ggml
url = https://github.com/ggerganov/llama.cpp.git
ignore = dirty
shallow = true
[submodule "llm/llama.cpp/gguf"]
path = llm/llama.cpp/gguf
url = https://github.com/ggerganov/llama.cpp.git
ignore = dirty
shallow = true
[submodule "llama.cpp"]
path = llm/llama.cpp
url = https://github.com/ggerganov/llama.cpp.git
shallow = true

17
.golangci.yaml Normal file
View File

@@ -0,0 +1,17 @@
run:
timeout: 5m
linters:
enable:
- asasalint
- bidichk
- bodyclose
- containedctx
- contextcheck
- exportloopref
- gocheckcompilerdirectives
# FIXME: for some reason this errors on windows
# - gofmt
# - goimports
- misspell
- nilerr
- unused

View File

@@ -1,23 +1,144 @@
FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
ARG GOLANG_VERSION=1.22.1
ARG CMAKE_VERSION=3.22.1
# this CUDA_VERSION corresponds with the one specified in docs/gpu.md
ARG CUDA_VERSION=11.3.1
ARG ROCM_VERSION=6.0.2
ARG TARGETARCH
ARG GOFLAGS="'-ldflags=-w -s'"
# Copy the minimal context we need to run the generate scripts
FROM scratch AS llm-code
COPY .git .git
COPY .gitmodules .gitmodules
COPY llm llm
WORKDIR /go/src/github.com/jmorganca/ollama
RUN apt-get update && apt-get install -y git build-essential cmake
ADD https://dl.google.com/go/go1.21.3.linux-$TARGETARCH.tar.gz /tmp/go1.21.3.tar.gz
RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.3.tar.gz
FROM --platform=linux/amd64 nvidia/cuda:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/ollama/ollama/
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
ARG CGO_CFLAGS
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/gcc-toolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/ollama/ollama/
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
ARG CGO_CFLAGS
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCM_VERSION}-complete AS rocm-build-amd64
ARG CMAKE_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
ENV LIBRARY_PATH /opt/amdgpu/lib64
COPY --from=llm-code / /go/src/github.com/ollama/ollama/
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
ARG CGO_CFLAGS
ARG AMDGPU_TARGETS
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
RUN mkdir /tmp/scratch && \
for dep in $(zcat /go/src/github.com/ollama/ollama/llm/build/linux/x86_64/rocm*/bin/deps.txt.gz) ; do \
cp ${dep} /tmp/scratch/ || exit 1 ; \
done && \
(cd /opt/rocm/lib && tar cf - rocblas/library) | (cd /tmp/scratch/ && tar xf - ) && \
mkdir -p /go/src/github.com/ollama/ollama/dist/deps/ && \
(cd /tmp/scratch/ && tar czvf /go/src/github.com/ollama/ollama/dist/deps/ollama-linux-amd64-rocm.tgz . )
FROM --platform=linux/amd64 centos:7 AS cpu-builder-amd64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/ollama/ollama/
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
FROM --platform=linux/amd64 cpu-builder-amd64 AS static-build-amd64
RUN OLLAMA_CPU_TARGET="static" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu-build-amd64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx-build-amd64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu_avx" sh gen_linux.sh
FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx2-build-amd64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu_avx2" sh gen_linux.sh
FROM --platform=linux/arm64 centos:7 AS cpu-builder-arm64
ARG CMAKE_VERSION
ARG GOLANG_VERSION
COPY ./scripts/rh_linux_deps.sh /
RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
COPY --from=llm-code / /go/src/github.com/ollama/ollama/
ARG OLLAMA_CUSTOM_CPU_DEFS
ARG CGO_CFLAGS
WORKDIR /go/src/github.com/ollama/ollama/llm/generate
FROM --platform=linux/arm64 cpu-builder-arm64 AS static-build-arm64
RUN OLLAMA_CPU_TARGET="static" sh gen_linux.sh
FROM --platform=linux/arm64 cpu-builder-arm64 AS cpu-build-arm64
RUN OLLAMA_SKIP_STATIC_GENERATE=1 OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
ENV CGO_ENABLED 1
WORKDIR /go/src/github.com/ollama/ollama
COPY . .
ENV GOARCH=$TARGETARCH
ENV GOFLAGS=$GOFLAGS
RUN /usr/local/go/bin/go generate ./... \
&& /usr/local/go/bin/go build .
COPY --from=static-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cpu_avx-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cpu_avx2-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=rocm-build-amd64 /go/src/github.com/ollama/ollama/dist/deps/ ./dist/deps/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build -trimpath .
FROM ubuntu:22.04
# Intermediate stage used for ./scripts/build_linux.sh
FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
ENV CGO_ENABLED 1
ARG GOLANG_VERSION
WORKDIR /go/src/github.com/ollama/ollama
COPY . .
COPY --from=static-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
COPY --from=cuda-build-arm64 /go/src/github.com/ollama/ollama/llm/build/linux/ llm/build/linux/
ARG GOFLAGS
ARG CGO_CFLAGS
RUN go build -trimpath .
# Runtime stages
FROM --platform=linux/amd64 ubuntu:22.04 as runtime-amd64
RUN apt-get update && apt-get install -y ca-certificates
COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
COPY --from=build-amd64 /go/src/github.com/ollama/ollama/ollama /bin/ollama
FROM --platform=linux/arm64 ubuntu:22.04 as runtime-arm64
RUN apt-get update && apt-get install -y ca-certificates
COPY --from=build-arm64 /go/src/github.com/ollama/ollama/ollama /bin/ollama
# Radeon images are much larger so we keep it distinct from the CPU/CUDA image
FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCM_VERSION}-complete as runtime-rocm
RUN update-pciids
COPY --from=build-amd64 /go/src/github.com/ollama/ollama/ollama /bin/ollama
EXPOSE 11434
ENV OLLAMA_HOST 0.0.0.0
ENTRYPOINT ["/bin/ollama"]
CMD ["serve"]
FROM runtime-$TARGETARCH
EXPOSE 11434
ENV OLLAMA_HOST 0.0.0.0
ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENV NVIDIA_VISIBLE_DEVICES=all
ENTRYPOINT ["/bin/ollama"]
CMD ["serve"]

View File

@@ -1,31 +0,0 @@
# centos7 amd64 dependencies
FROM --platform=linux/amd64 nvidia/cuda:11.3.1-devel-centos7 AS base-amd64
RUN yum install -y https://repo.ius.io/ius-release-el7.rpm centos-release-scl && \
yum update -y && \
yum install -y devtoolset-10-gcc devtoolset-10-gcc-c++ git236 wget
RUN wget "https://github.com/Kitware/CMake/releases/download/v3.27.6/cmake-3.27.6-linux-x86_64.sh" -O cmake-installer.sh && chmod +x cmake-installer.sh && ./cmake-installer.sh --skip-license --prefix=/usr/local
ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
# centos8 arm64 dependencies
FROM --platform=linux/arm64 nvidia/cuda-arm64:11.3.1-devel-centos8 AS base-arm64
RUN sed -i -e 's/mirrorlist/#mirrorlist/g' -e 's|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g' /etc/yum.repos.d/CentOS-*
RUN yum install -y git cmake
FROM base-${TARGETARCH}
ARG TARGETARCH
ARG GOFLAGS="'-ldflags -w -s'"
# install go
ADD https://dl.google.com/go/go1.21.3.linux-$TARGETARCH.tar.gz /tmp/go1.21.3.tar.gz
RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.3.tar.gz
# build the final binary
WORKDIR /go/src/github.com/jmorganca/ollama
COPY . .
ENV GOOS=linux
ENV GOARCH=$TARGETARCH
ENV GOFLAGS=$GOFLAGS
RUN /usr/local/go/bin/go generate ./... && \
/usr/local/go/bin/go build .

242
README.md
View File

@@ -1,8 +1,5 @@
<div align="center">
<picture>
<source media="(prefers-color-scheme: dark)" height="200px" srcset="https://github.com/jmorganca/ollama/assets/3325447/56ea1849-1284-4645-8970-956de6e51c3c">
<img alt="logo" height="200px" src="https://github.com/jmorganca/ollama/assets/3325447/0d0b44e2-8f4a-4e99-9b52-a5c1c741c8f7">
</picture>
<img alt="ollama" height="200px" src="https://github.com/ollama/ollama/assets/3325447/0d0b44e2-8f4a-4e99-9b52-a5c1c741c8f7">
</div>
# Ollama
@@ -13,53 +10,61 @@ Get up and running with large language models locally.
### macOS
[Download](https://ollama.ai/download/Ollama-darwin.zip)
[Download](https://ollama.com/download/Ollama-darwin.zip)
### Windows
### Windows preview
Coming soon!
[Download](https://ollama.com/download/OllamaSetup.exe)
### Linux & WSL2
### Linux
```
curl https://ollama.ai/install.sh | sh
curl -fsSL https://ollama.com/install.sh | sh
```
[Manual install instructions](https://github.com/jmorganca/ollama/blob/main/docs/linux.md)
[Manual install instructions](https://github.com/ollama/ollama/blob/main/docs/linux.md)
### Docker
The official [Ollama Docker image `ollama/ollama`](https://hub.docker.com/r/ollama/ollama)
is available on Docker Hub.
The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama` is available on Docker Hub.
### Libraries
- [ollama-python](https://github.com/ollama/ollama-python)
- [ollama-js](https://github.com/ollama/ollama-js)
## Quickstart
To run and chat with [Llama 2](https://ollama.ai/library/llama2):
To run and chat with [Llama 3](https://ollama.com/library/llama3):
```
ollama run llama2
ollama run llama3
```
## Model library
Ollama supports a list of open-source models available on [ollama.ai/library](https://ollama.ai/library 'ollama model library')
Ollama supports a list of models available on [ollama.com/library](https://ollama.com/library 'ollama model library')
Here are some example open-source models that can be downloaded:
Here are some example models that can be downloaded:
| Model | Parameters | Size | Download |
| ------------------ | ---------- | ----- | ------------------------------ |
| Llama 3 | 8B | 4.7GB | `ollama run llama3` |
| Llama 3 | 70B | 40GB | `ollama run llama3:70b` |
| Phi-3 | 3,8B | 2.3GB | `ollama run phi3` |
| Mistral | 7B | 4.1GB | `ollama run mistral` |
| Llama 2 | 7B | 3.8GB | `ollama run llama2` |
| Neural Chat | 7B | 4.1GB | `ollama run neural-chat` |
| Starling | 7B | 4.1GB | `ollama run starling-lm` |
| Code Llama | 7B | 3.8GB | `ollama run codellama` |
| Llama 2 Uncensored | 7B | 3.8GB | `ollama run llama2-uncensored` |
| Llama 2 13B | 13B | 7.3GB | `ollama run llama2:13b` |
| Llama 2 70B | 70B | 39GB | `ollama run llama2:70b` |
| Orca Mini | 3B | 1.9GB | `ollama run orca-mini` |
| Vicuna | 7B | 3.8GB | `ollama run vicuna` |
| LLaVA | 7B | 4.5GB | `ollama run llava` |
| Gemma | 2B | 1.4GB | `ollama run gemma:2b` |
| Gemma | 7B | 4.8GB | `ollama run gemma:7b` |
| Solar | 10.7B | 6.1GB | `ollama run solar` |
> Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.
> Note: You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.
## Customize your own model
## Customize a model
### Import from GGUF
@@ -89,21 +94,21 @@ See the [guide](docs/import.md) on importing models for more information.
### Customize a prompt
Models from the Ollama library can be customized with a prompt. For example, to customize the `llama2` model:
Models from the Ollama library can be customized with a prompt. For example, to customize the `llama3` model:
```
ollama pull llama2
ollama pull llama3
```
Create a `Modelfile`:
```
FROM llama2
FROM llama3
# set the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1
# set the system prompt
# set the system message
SYSTEM """
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
"""
@@ -126,10 +131,14 @@ For more examples, see the [examples](examples) directory. For more information
`ollama create` is used to create a model from a Modelfile.
```
ollama create mymodel -f ./Modelfile
```
### Pull a model
```
ollama pull llama2
ollama pull llama3
```
> This command can also be used to update a local model. Only the diff will be pulled.
@@ -137,13 +146,13 @@ ollama pull llama2
### Remove a model
```
ollama rm llama2
ollama rm llama3
```
### Copy a model
```
ollama cp llama2 my-llama2
ollama cp llama3 my-model
```
### Multiline input
@@ -157,10 +166,17 @@ For multiline input, you can wrap text with `"""`:
I'm a basic program that prints the famous "Hello, world!" message to the console.
```
### Multimodal models
```
>>> What's in this image? /Users/jmorgan/Desktop/smile.png
The image features a yellow smiley face, which is likely the central focus of the picture.
```
### Pass in prompt as arguments
```
$ ollama run llama2 "summarize this file:" "$(cat README.md)"
$ ollama run llama3 "Summarize this file: $(cat README.md)"
Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.
```
@@ -182,13 +198,22 @@ Install `cmake` and `go`:
brew install cmake go
```
Then generate dependencies and build:
Then generate dependencies:
```
go generate ./...
```
Then build the binary:
```
go build .
```
More detailed instructions can be found in the [developer guide](https://github.com/ollama/ollama/blob/main/docs/development.md)
### Running local builds
Next, start the server:
```
@@ -198,40 +223,165 @@ Next, start the server:
Finally, in a separate shell, run a model:
```
./ollama run llama2
./ollama run llama3
```
## REST API
Ollama has a REST API for running and managing models.
For example, to generate text from a model:
### Generate a response
```
curl -X POST http://localhost:11434/api/generate -d '{
"model": "llama2",
curl http://localhost:11434/api/generate -d '{
"model": "llama3",
"prompt":"Why is the sky blue?"
}'
```
### Chat with a model
```
curl http://localhost:11434/api/chat -d '{
"model": "llama3",
"messages": [
{ "role": "user", "content": "why is the sky blue?" }
]
}'
```
See the [API documentation](./docs/api.md) for all endpoints.
## Community Integrations
### Web & Desktop
- [Open WebUI](https://github.com/open-webui/open-webui)
- [Enchanted (macOS native)](https://github.com/AugustDev/enchanted)
- [Lollms-Webui](https://github.com/ParisNeo/lollms-webui)
- [LibreChat](https://github.com/danny-avila/LibreChat)
- [Bionic GPT](https://github.com/bionic-gpt/bionic-gpt)
- [HTML UI](https://github.com/rtcfirefly/ollama-ui)
- [Saddle](https://github.com/jikkuatwork/saddle)
- [Chatbot UI](https://github.com/ivanfioravanti/chatbot-ollama)
- [Chatbot UI v2](https://github.com/mckaywrigley/chatbot-ui)
- [Typescript UI](https://github.com/ollama-interface/Ollama-Gui?tab=readme-ov-file)
- [Minimalistic React UI for Ollama Models](https://github.com/richawo/minimal-llm-ui)
- [Ollamac](https://github.com/kevinhermawan/Ollamac)
- [big-AGI](https://github.com/enricoros/big-AGI/blob/main/docs/config-local-ollama.md)
- [Cheshire Cat assistant framework](https://github.com/cheshire-cat-ai/core)
- [Amica](https://github.com/semperai/amica)
- [chatd](https://github.com/BruceMacD/chatd)
- [Ollama-SwiftUI](https://github.com/kghandour/Ollama-SwiftUI)
- [Dify.AI](https://github.com/langgenius/dify)
- [MindMac](https://mindmac.app)
- [NextJS Web Interface for Ollama](https://github.com/jakobhoeg/nextjs-ollama-llm-ui)
- [Msty](https://msty.app)
- [Chatbox](https://github.com/Bin-Huang/Chatbox)
- [WinForm Ollama Copilot](https://github.com/tgraupmann/WinForm_Ollama_Copilot)
- [NextChat](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web) with [Get Started Doc](https://docs.nextchat.dev/models/ollama)
- [Alpaca WebUI](https://github.com/mmo80/alpaca-webui)
- [OllamaGUI](https://github.com/enoch1118/ollamaGUI)
- [OpenAOE](https://github.com/InternLM/OpenAOE)
- [Odin Runes](https://github.com/leonid20000/OdinRunes)
- [LLM-X: Progressive Web App](https://github.com/mrdjohnson/llm-x)
- [AnythingLLM (Docker + MacOs/Windows/Linux native app)](https://github.com/Mintplex-Labs/anything-llm)
- [Ollama Basic Chat: Uses HyperDiv Reactive UI](https://github.com/rapidarchitect/ollama_basic_chat)
- [Ollama-chats RPG](https://github.com/drazdra/ollama-chats)
- [QA-Pilot: Chat with Code Repository](https://github.com/reid41/QA-Pilot)
- [ChatOllama: Open Source Chatbot based on Ollama with Knowledge Bases](https://github.com/sugarforever/chat-ollama)
- [CRAG Ollama Chat: Simple Web Search with Corrective RAG](https://github.com/Nagi-ovo/CRAG-Ollama-Chat)
- [RAGFlow: Open-source Retrieval-Augmented Generation engine based on deep document understanding](https://github.com/infiniflow/ragflow)
- [chat: chat web app for teams](https://github.com/swuecho/chat)
- [Lobe Chat](https://github.com/lobehub/lobe-chat) with [Integrating Doc](https://lobehub.com/docs/self-hosting/examples/ollama)
- [Ollama RAG Chatbot: Local Chat with multiples PDFs using Ollama and RAG.](https://github.com/datvodinh/rag-chatbot.git)
### Terminal
- [oterm](https://github.com/ggozad/oterm)
- [Ellama Emacs client](https://github.com/s-kostyaev/ellama)
- [Emacs client](https://github.com/zweifisch/ollama)
- [gen.nvim](https://github.com/David-Kunz/gen.nvim)
- [ollama.nvim](https://github.com/nomnivore/ollama.nvim)
- [ollero.nvim](https://github.com/marco-souza/ollero.nvim)
- [ollama-chat.nvim](https://github.com/gerazov/ollama-chat.nvim)
- [ogpt.nvim](https://github.com/huynle/ogpt.nvim)
- [gptel Emacs client](https://github.com/karthink/gptel)
- [Oatmeal](https://github.com/dustinblackman/oatmeal)
- [cmdh](https://github.com/pgibler/cmdh)
- [ooo](https://github.com/npahlfer/ooo)
- [shell-pilot](https://github.com/reid41/shell-pilot)
- [tenere](https://github.com/pythops/tenere)
- [llm-ollama](https://github.com/taketwo/llm-ollama) for [Datasette's LLM CLI](https://llm.datasette.io/en/stable/).
- [typechat-cli](https://github.com/anaisbetts/typechat-cli)
- [ShellOracle](https://github.com/djcopley/ShellOracle)
- [tlm](https://github.com/yusufcanb/tlm)
- [podman-ollama](https://github.com/ericcurtin/podman-ollama)
### Database
- [MindsDB](https://github.com/mindsdb/mindsdb/blob/staging/mindsdb/integrations/handlers/ollama_handler/README.md) (Connects Ollama models with nearly 200 data platforms and apps)
- [chromem-go](https://github.com/philippgille/chromem-go/blob/v0.5.0/embed_ollama.go) with [example](https://github.com/philippgille/chromem-go/tree/v0.5.0/examples/rag-wikipedia-ollama)
### Package managers
- [Pacman](https://archlinux.org/packages/extra/x86_64/ollama/)
- [Helm Chart](https://artifacthub.io/packages/helm/ollama-helm/ollama)
### Libraries
- [LangChain](https://python.langchain.com/docs/integrations/llms/ollama) and [LangChain.js](https://js.langchain.com/docs/modules/model_io/models/llms/integrations/ollama) with [example](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa)
- [LangChainGo](https://github.com/tmc/langchaingo/) with [example](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example)
- [LangChain4j](https://github.com/langchain4j/langchain4j) with [example](https://github.com/langchain4j/langchain4j-examples/tree/main/ollama-examples/src/main/java)
- [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/llm/ollama.html)
- [LiteLLM](https://github.com/BerriAI/litellm)
- [OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp)
- [Ollama for Ruby](https://github.com/gbaptista/ollama-ai)
- [Ollama-rs for Rust](https://github.com/pepperoni21/ollama-rs)
- [Ollama4j for Java](https://github.com/amithkoujalgi/ollama4j)
- [ModelFusion Typescript Library](https://modelfusion.dev/integration/model-provider/ollama)
- [OllamaKit for Swift](https://github.com/kevinhermawan/OllamaKit)
- [Ollama for Dart](https://github.com/breitburg/dart-ollama)
- [Ollama for Laravel](https://github.com/cloudstudio/ollama-laravel)
- [LangChainDart](https://github.com/davidmigloz/langchain_dart)
- [Semantic Kernel - Python](https://github.com/microsoft/semantic-kernel/tree/main/python/semantic_kernel/connectors/ai/ollama)
- [Haystack](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/ollama.md)
- [Elixir LangChain](https://github.com/brainlid/langchain)
- [Ollama for R - rollama](https://github.com/JBGruber/rollama)
- [Ollama-ex for Elixir](https://github.com/lebrunel/ollama-ex)
- [Ollama Connector for SAP ABAP](https://github.com/b-tocs/abap_btocs_ollama)
- [Testcontainers](https://testcontainers.com/modules/ollama/)
### Mobile
- [Enchanted](https://github.com/AugustDev/enchanted)
- [Maid](https://github.com/Mobile-Artificial-Intelligence/maid)
### Extensions & Plugins
- [Raycast extension](https://github.com/MassimilianoPasquini97/raycast_ollama)
- [Discollama](https://github.com/mxyng/discollama) (Discord bot inside the Ollama discord channel)
- [Continue](https://github.com/continuedev/continue)
- [Obsidian Ollama plugin](https://github.com/hinterdupfinger/obsidian-ollama)
- [Logseq Ollama plugin](https://github.com/omagdy7/ollama-logseq)
- [NotesOllama](https://github.com/andersrex/notesollama) (Apple Notes Ollama plugin)
- [Dagger Chatbot](https://github.com/samalba/dagger-chatbot)
- [LiteLLM](https://github.com/BerriAI/litellm)
- [Discord AI Bot](https://github.com/mekb-turtle/discord-ai-bot)
- [Chatbot UI](https://github.com/ivanfioravanti/chatbot-ollama)
- [HTML UI](https://github.com/rtcfirefly/ollama-ui)
- [Typescript UI](https://github.com/ollama-interface/Ollama-Gui?tab=readme-ov-file)
- [Dumbar](https://github.com/JerrySievert/Dumbar)
- [Emacs client](https://github.com/zweifisch/ollama)
- [oterm](https://github.com/ggozad/oterm)
- [Ellama Emacs client](https://github.com/s-kostyaev/ellama)
- [OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp)
- [Minimalistic React UI for Ollama Models](https://github.com/richawo/minimal-llm-ui)
- [Ollama Telegram Bot](https://github.com/ruecat/ollama-telegram)
- [Hass Ollama Conversation](https://github.com/ej52/hass-ollama-conversation)
- [Rivet plugin](https://github.com/abrenneke/rivet-plugin-ollama)
- [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama)
- [Obsidian BMO Chatbot plugin](https://github.com/longy2k/obsidian-bmo-chatbot)
- [Cliobot](https://github.com/herval/cliobot) (Telegram bot with Ollama support)
- [Copilot for Obsidian plugin](https://github.com/logancyang/obsidian-copilot)
- [Obsidian Local GPT plugin](https://github.com/pfrankov/obsidian-local-gpt)
- [Open Interpreter](https://docs.openinterpreter.com/language-model-setup/local-models/ollama)
- [twinny](https://github.com/rjmacarthy/twinny) (Copilot and Copilot chat alternative using Ollama)
- [Wingman-AI](https://github.com/RussellCanfield/wingman-ai) (Copilot code and chat alternative using Ollama and HuggingFace)
- [Page Assist](https://github.com/n4ze3m/page-assist) (Chrome Extension)
- [AI Telegram Bot](https://github.com/tusharhero/aitelegrambot) (Telegram bot using Ollama in backend)
- [AI ST Completion](https://github.com/yaroslavyaroslav/OpenAI-sublime-text) (Sublime Text 4 AI assistant plugin with Ollama support)
- [Discord-Ollama Chat Bot](https://github.com/kevinthedang/discord-ollama) (Generalized TypeScript Discord Bot w/ Tuning Documentation)
### Supported backends
- [llama.cpp](https://github.com/ggerganov/llama.cpp) project founded by Georgi Gerganov.

View File

@@ -1,3 +1,9 @@
// Package api implements the client-side API for code wishing to interact
// with the ollama service. The methods of the [Client] type correspond to
// the ollama REST API as described in https://github.com/ollama/ollama/blob/main/docs/api.md
//
// The ollama command-line client itself uses this package to interact with
// the backend service.
package api
import (
@@ -14,13 +20,15 @@ import (
"runtime"
"strings"
"github.com/jmorganca/ollama/format"
"github.com/jmorganca/ollama/version"
"github.com/ollama/ollama/format"
"github.com/ollama/ollama/version"
)
// Client encapsulates client state for interacting with the ollama
// service. Use [ClientFromEnvironment] to create new Clients.
type Client struct {
base *url.URL
http http.Client
http *http.Client
}
func checkError(resp *http.Response, body []byte) error {
@@ -39,6 +47,15 @@ func checkError(resp *http.Response, body []byte) error {
return apiError
}
// ClientFromEnvironment creates a new [Client] using configuration from the
// environment variable OLLAMA_HOST, which points to the network host and
// port on which the ollama service is listenting. The format of this variable
// is:
//
// <scheme>://<host>:<port>
//
// If the variable is not specified, a default ollama host and port will be
// used.
func ClientFromEnvironment() (*Client, error) {
defaultPort := "11434"
@@ -65,41 +82,39 @@ func ClientFromEnvironment() (*Client, error) {
}
}
client := Client{
return &Client{
base: &url.URL{
Scheme: scheme,
Host: net.JoinHostPort(host, port),
},
}
http: http.DefaultClient,
}, nil
}
mockRequest, err := http.NewRequest("HEAD", client.base.String(), nil)
if err != nil {
return nil, err
func NewClient(base *url.URL, http *http.Client) *Client {
return &Client{
base: base,
http: http,
}
proxyURL, err := http.ProxyFromEnvironment(mockRequest)
if err != nil {
return nil, err
}
client.http = http.Client{
Transport: &http.Transport{
Proxy: http.ProxyURL(proxyURL),
},
}
return &client, nil
}
func (c *Client) do(ctx context.Context, method, path string, reqData, respData any) error {
var reqBody io.Reader
var data []byte
var err error
if reqData != nil {
switch reqData := reqData.(type) {
case io.Reader:
// reqData is already an io.Reader
reqBody = reqData
case nil:
// noop
default:
data, err = json.Marshal(reqData)
if err != nil {
return err
}
reqBody = bytes.NewReader(data)
}
@@ -199,8 +214,14 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
return nil
}
// GenerateResponseFunc is a function that [Client.Generate] invokes every time
// a response is received from the service. If this function returns an error,
// [Client.Generate] will stop generating and return this error.
type GenerateResponseFunc func(GenerateResponse) error
// Generate generates a response for a given prompt. The req parameter should
// be populated with prompt details. fn is called for each response (there may
// be multiple responses, e.g. in case streaming is enabled).
func (c *Client) Generate(ctx context.Context, req *GenerateRequest, fn GenerateResponseFunc) error {
return c.stream(ctx, http.MethodPost, "/api/generate", req, func(bts []byte) error {
var resp GenerateResponse
@@ -212,8 +233,34 @@ func (c *Client) Generate(ctx context.Context, req *GenerateRequest, fn Generate
})
}
// ChatResponseFunc is a function that [Client.Chat] invokes every time
// a response is received from the service. If this function returns an error,
// [Client.Chat] will stop generating and return this error.
type ChatResponseFunc func(ChatResponse) error
// Chat generates the next message in a chat. [ChatRequest] may contain a
// sequence of messages which can be used to maintain chat history with a model.
// fn is called for each response (there may be multiple responses, e.g. if case
// streaming is enabled).
func (c *Client) Chat(ctx context.Context, req *ChatRequest, fn ChatResponseFunc) error {
return c.stream(ctx, http.MethodPost, "/api/chat", req, func(bts []byte) error {
var resp ChatResponse
if err := json.Unmarshal(bts, &resp); err != nil {
return err
}
return fn(resp)
})
}
// PullProgressFunc is a function that [Client.Pull] invokes every time there
// is progress with a "pull" request sent to the service. If this function
// returns an error, [Client.Pull] will stop the process and return this error.
type PullProgressFunc func(ProgressResponse) error
// Pull downloads a model from the ollama library. fn is called each time
// progress is made on the request and can be used to display a progress bar,
// etc.
func (c *Client) Pull(ctx context.Context, req *PullRequest, fn PullProgressFunc) error {
return c.stream(ctx, http.MethodPost, "/api/pull", req, func(bts []byte) error {
var resp ProgressResponse
@@ -287,3 +334,26 @@ func (c *Client) Heartbeat(ctx context.Context) error {
}
return nil
}
func (c *Client) Embeddings(ctx context.Context, req *EmbeddingRequest) (*EmbeddingResponse, error) {
var resp EmbeddingResponse
if err := c.do(ctx, http.MethodPost, "/api/embeddings", req, &resp); err != nil {
return nil, err
}
return &resp, nil
}
func (c *Client) CreateBlob(ctx context.Context, digest string, r io.Reader) error {
return c.do(ctx, http.MethodPost, fmt.Sprintf("/api/blobs/%s", digest), r, nil)
}
func (c *Client) Version(ctx context.Context) (string, error) {
var version struct {
Version string `json:"version"`
}
if err := c.do(ctx, http.MethodGet, "/api/version", nil, &version); err != nil {
return "", err
}
return version.Version, nil
}

View File

@@ -1,225 +0,0 @@
import os
import json
import requests
BASE_URL = os.environ.get('OLLAMA_HOST', 'http://localhost:11434')
# Generate a response for a given prompt with a provided model. This is a streaming endpoint, so will be a series of responses.
# The final response object will include statistics and additional data from the request. Use the callback function to override
# the default handler.
def generate(model_name, prompt, system=None, template=None, context=None, options=None, callback=None):
try:
url = f"{BASE_URL}/api/generate"
payload = {
"model": model_name,
"prompt": prompt,
"system": system,
"template": template,
"context": context,
"options": options
}
# Remove keys with None values
payload = {k: v for k, v in payload.items() if v is not None}
with requests.post(url, json=payload, stream=True) as response:
response.raise_for_status()
# Creating a variable to hold the context history of the final chunk
final_context = None
# Variable to hold concatenated response strings if no callback is provided
full_response = ""
# Iterating over the response line by line and displaying the details
for line in response.iter_lines():
if line:
# Parsing each line (JSON chunk) and extracting the details
chunk = json.loads(line)
# If a callback function is provided, call it with the chunk
if callback:
callback(chunk)
else:
# If this is not the last chunk, add the "response" field value to full_response and print it
if not chunk.get("done"):
response_piece = chunk.get("response", "")
full_response += response_piece
print(response_piece, end="", flush=True)
# Check if it's the last chunk (done is true)
if chunk.get("done"):
final_context = chunk.get("context")
# Return the full response and the final context
return full_response, final_context
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
return None, None
# Create a model from a Modelfile. Use the callback function to override the default handler.
def create(model_name, model_path, callback=None):
try:
url = f"{BASE_URL}/api/create"
payload = {"name": model_name, "path": model_path}
# Making a POST request with the stream parameter set to True to handle streaming responses
with requests.post(url, json=payload, stream=True) as response:
response.raise_for_status()
# Iterating over the response line by line and displaying the status
for line in response.iter_lines():
if line:
# Parsing each line (JSON chunk) and extracting the status
chunk = json.loads(line)
if callback:
callback(chunk)
else:
print(f"Status: {chunk.get('status')}")
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
# Pull a model from a the model registry. Cancelled pulls are resumed from where they left off, and multiple
# calls to will share the same download progress. Use the callback function to override the default handler.
def pull(model_name, insecure=False, callback=None):
try:
url = f"{BASE_URL}/api/pull"
payload = {
"name": model_name,
"insecure": insecure
}
# Making a POST request with the stream parameter set to True to handle streaming responses
with requests.post(url, json=payload, stream=True) as response:
response.raise_for_status()
# Iterating over the response line by line and displaying the details
for line in response.iter_lines():
if line:
# Parsing each line (JSON chunk) and extracting the details
chunk = json.loads(line)
# If a callback function is provided, call it with the chunk
if callback:
callback(chunk)
else:
# Print the status message directly to the console
print(chunk.get('status', ''), end='', flush=True)
# If there's layer data, you might also want to print that (adjust as necessary)
if 'digest' in chunk:
print(f" - Digest: {chunk['digest']}", end='', flush=True)
print(f" - Total: {chunk['total']}", end='', flush=True)
print(f" - Completed: {chunk['completed']}", end='\n', flush=True)
else:
print()
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
# Push a model to the model registry. Use the callback function to override the default handler.
def push(model_name, insecure=False, callback=None):
try:
url = f"{BASE_URL}/api/push"
payload = {
"name": model_name,
"insecure": insecure
}
# Making a POST request with the stream parameter set to True to handle streaming responses
with requests.post(url, json=payload, stream=True) as response:
response.raise_for_status()
# Iterating over the response line by line and displaying the details
for line in response.iter_lines():
if line:
# Parsing each line (JSON chunk) and extracting the details
chunk = json.loads(line)
# If a callback function is provided, call it with the chunk
if callback:
callback(chunk)
else:
# Print the status message directly to the console
print(chunk.get('status', ''), end='', flush=True)
# If there's layer data, you might also want to print that (adjust as necessary)
if 'digest' in chunk:
print(f" - Digest: {chunk['digest']}", end='', flush=True)
print(f" - Total: {chunk['total']}", end='', flush=True)
print(f" - Completed: {chunk['completed']}", end='\n', flush=True)
else:
print()
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
# List models that are available locally.
def list():
try:
response = requests.get(f"{BASE_URL}/api/tags")
response.raise_for_status()
data = response.json()
models = data.get('models', [])
return models
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
return None
# Copy a model. Creates a model with another name from an existing model.
def copy(source, destination):
try:
# Create the JSON payload
payload = {
"source": source,
"destination": destination
}
response = requests.post(f"{BASE_URL}/api/copy", json=payload)
response.raise_for_status()
# If the request was successful, return a message indicating that the copy was successful
return "Copy successful"
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
return None
# Delete a model and its data.
def delete(model_name):
try:
url = f"{BASE_URL}/api/delete"
payload = {"name": model_name}
response = requests.delete(url, json=payload)
response.raise_for_status()
return "Delete successful"
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
return None
# Show info about a model.
def show(model_name):
try:
url = f"{BASE_URL}/api/show"
payload = {"name": model_name}
response = requests.post(url, json=payload)
response.raise_for_status()
# Parse the JSON response and return it
data = response.json()
return data
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
return None
def heartbeat():
try:
url = f"{BASE_URL}/"
response = requests.head(url)
response.raise_for_status()
return "Ollama is running"
except requests.exceptions.RequestException as e:
print(f"An error occurred: {e}")
return "Ollama is not running"

View File

@@ -2,10 +2,12 @@ package api
import (
"encoding/json"
"errors"
"fmt"
"math"
"os"
"reflect"
"strconv"
"strings"
"time"
)
@@ -30,101 +32,78 @@ func (e StatusError) Error() string {
}
}
type ImageData []byte
// GenerateRequest describes a request sent by [Client.Generate]. While you
// have to specify the Model and Prompt fields, all the other fields have
// reasonable defaults for basic uses.
type GenerateRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
System string `json:"system"`
Template string `json:"template"`
Context []int `json:"context,omitempty"`
Stream *bool `json:"stream,omitempty"`
// Model is the model name; it should be a name familiar to Ollama from
// the library at https://ollama.com/library
Model string `json:"model"`
Options map[string]interface{} `json:"options"`
}
type EmbeddingRequest struct {
Model string `json:"model"`
// Prompt is the textual prompt to send to the model.
Prompt string `json:"prompt"`
// System overrides the model's default system message/prompt.
System string `json:"system"`
// Template overrides the model's default prompt template.
Template string `json:"template"`
// Context is the context parameter returned from a previous call to
// Generate call. It can be used to keep a short conversational memory.
Context []int `json:"context,omitempty"`
// Stream specifies whether the response is streaming; it is true by default.
Stream *bool `json:"stream,omitempty"`
// Raw set to true means that no formatting will be applied to the prompt.
Raw bool `json:"raw,omitempty"`
// Format specifies the format to return a response in.
Format string `json:"format"`
// KeepAlive controls how long the model will stay loaded in memory following
// this request.
KeepAlive *Duration `json:"keep_alive,omitempty"`
// Images is an optional list of base64-encoded images accompanying this
// request, for multimodal models.
Images []ImageData `json:"images,omitempty"`
// Options lists model-specific options. For example, temperature can be
// set through this field, if the model supports it.
Options map[string]interface{} `json:"options"`
}
type EmbeddingResponse struct {
Embedding []float64 `json:"embedding"`
type ChatRequest struct {
Model string `json:"model"`
Messages []Message `json:"messages"`
Stream *bool `json:"stream,omitempty"`
Format string `json:"format"`
KeepAlive *Duration `json:"keep_alive,omitempty"`
Options map[string]interface{} `json:"options"`
}
type CreateRequest struct {
Name string `json:"name"`
Path string `json:"path"`
Stream *bool `json:"stream,omitempty"`
type Message struct {
Role string `json:"role"` // one of ["system", "user", "assistant"]
Content string `json:"content"`
Images []ImageData `json:"images,omitempty"`
}
type DeleteRequest struct {
Name string `json:"name"`
}
type ShowRequest struct {
Name string `json:"name"`
}
type ShowResponse struct {
License string `json:"license,omitempty"`
Modelfile string `json:"modelfile,omitempty"`
Parameters string `json:"parameters,omitempty"`
Template string `json:"template,omitempty"`
System string `json:"system,omitempty"`
}
type CopyRequest struct {
Source string `json:"source"`
Destination string `json:"destination"`
}
type PullRequest struct {
Name string `json:"name"`
Insecure bool `json:"insecure,omitempty"`
Username string `json:"username"`
Password string `json:"password"`
Stream *bool `json:"stream,omitempty"`
}
type ProgressResponse struct {
Status string `json:"status"`
Digest string `json:"digest,omitempty"`
Total int64 `json:"total,omitempty"`
Completed int64 `json:"completed,omitempty"`
}
type PushRequest struct {
Name string `json:"name"`
Insecure bool `json:"insecure,omitempty"`
Username string `json:"username"`
Password string `json:"password"`
Stream *bool `json:"stream,omitempty"`
}
type ListResponse struct {
Models []ModelResponse `json:"models"`
}
type ModelResponse struct {
Name string `json:"name"`
ModifiedAt time.Time `json:"modified_at"`
Size int64 `json:"size"`
Digest string `json:"digest"`
}
type TokenResponse struct {
Token string `json:"token"`
}
type GenerateResponse struct {
type ChatResponse struct {
Model string `json:"model"`
CreatedAt time.Time `json:"created_at"`
Response string `json:"response"`
Message Message `json:"message"`
Done bool `json:"done"`
Context []int `json:"context,omitempty"`
Done bool `json:"done"`
Metrics
}
type Metrics struct {
TotalDuration time.Duration `json:"total_duration,omitempty"`
LoadDuration time.Duration `json:"load_duration,omitempty"`
PromptEvalCount int `json:"prompt_eval_count,omitempty"`
@@ -133,54 +112,7 @@ type GenerateResponse struct {
EvalDuration time.Duration `json:"eval_duration,omitempty"`
}
func (r *GenerateResponse) Summary() {
if r.TotalDuration > 0 {
fmt.Fprintf(os.Stderr, "total duration: %v\n", r.TotalDuration)
}
if r.LoadDuration > 0 {
fmt.Fprintf(os.Stderr, "load duration: %v\n", r.LoadDuration)
}
if r.PromptEvalCount > 0 {
fmt.Fprintf(os.Stderr, "prompt eval count: %d token(s)\n", r.PromptEvalCount)
}
if r.PromptEvalDuration > 0 {
fmt.Fprintf(os.Stderr, "prompt eval duration: %s\n", r.PromptEvalDuration)
fmt.Fprintf(os.Stderr, "prompt eval rate: %.2f tokens/s\n", float64(r.PromptEvalCount)/r.PromptEvalDuration.Seconds())
}
if r.EvalCount > 0 {
fmt.Fprintf(os.Stderr, "eval count: %d token(s)\n", r.EvalCount)
}
if r.EvalDuration > 0 {
fmt.Fprintf(os.Stderr, "eval duration: %s\n", r.EvalDuration)
fmt.Fprintf(os.Stderr, "eval rate: %.2f tokens/s\n", float64(r.EvalCount)/r.EvalDuration.Seconds())
}
}
// Runner options which must be set when the model is loaded into memory
type Runner struct {
UseNUMA bool `json:"numa,omitempty"`
NumCtx int `json:"num_ctx,omitempty"`
NumBatch int `json:"num_batch,omitempty"`
NumGQA int `json:"num_gqa,omitempty"`
NumGPU int `json:"num_gpu,omitempty"`
MainGPU int `json:"main_gpu,omitempty"`
LowVRAM bool `json:"low_vram,omitempty"`
F16KV bool `json:"f16_kv,omitempty"`
LogitsAll bool `json:"logits_all,omitempty"`
VocabOnly bool `json:"vocab_only,omitempty"`
UseMMap bool `json:"use_mmap,omitempty"`
UseMLock bool `json:"use_mlock,omitempty"`
EmbeddingOnly bool `json:"embedding_only,omitempty"`
RopeFrequencyBase float32 `json:"rope_frequency_base,omitempty"`
RopeFrequencyScale float32 `json:"rope_frequency_scale,omitempty"`
NumThread int `json:"num_thread,omitempty"`
}
// Options specified in GenerateRequest, if you add a new option here add it to the API docs also
type Options struct {
Runner
@@ -204,7 +136,179 @@ type Options struct {
Stop []string `json:"stop,omitempty"`
}
var ErrInvalidOpts = fmt.Errorf("invalid options")
// Runner options which must be set when the model is loaded into memory
type Runner struct {
UseNUMA bool `json:"numa,omitempty"`
NumCtx int `json:"num_ctx,omitempty"`
NumBatch int `json:"num_batch,omitempty"`
NumGQA int `json:"num_gqa,omitempty"`
NumGPU int `json:"num_gpu,omitempty"`
MainGPU int `json:"main_gpu,omitempty"`
LowVRAM bool `json:"low_vram,omitempty"`
F16KV bool `json:"f16_kv,omitempty"`
LogitsAll bool `json:"logits_all,omitempty"`
VocabOnly bool `json:"vocab_only,omitempty"`
UseMMap bool `json:"use_mmap,omitempty"`
UseMLock bool `json:"use_mlock,omitempty"`
NumThread int `json:"num_thread,omitempty"`
// Unused: RopeFrequencyBase is ignored. Instead the value in the model will be used
RopeFrequencyBase float32 `json:"rope_frequency_base,omitempty"`
// Unused: RopeFrequencyScale is ignored. Instead the value in the model will be used
RopeFrequencyScale float32 `json:"rope_frequency_scale,omitempty"`
}
type EmbeddingRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
KeepAlive *Duration `json:"keep_alive,omitempty"`
Options map[string]interface{} `json:"options"`
}
type EmbeddingResponse struct {
Embedding []float64 `json:"embedding"`
}
type CreateRequest struct {
Model string `json:"model"`
Path string `json:"path"`
Modelfile string `json:"modelfile"`
Stream *bool `json:"stream,omitempty"`
Quantization string `json:"quantization,omitempty"`
// Name is deprecated, see Model
Name string `json:"name"`
}
type DeleteRequest struct {
Model string `json:"model"`
// Name is deprecated, see Model
Name string `json:"name"`
}
type ShowRequest struct {
Model string `json:"model"`
System string `json:"system"`
Template string `json:"template"`
Options map[string]interface{} `json:"options"`
// Name is deprecated, see Model
Name string `json:"name"`
}
type ShowResponse struct {
License string `json:"license,omitempty"`
Modelfile string `json:"modelfile,omitempty"`
Parameters string `json:"parameters,omitempty"`
Template string `json:"template,omitempty"`
System string `json:"system,omitempty"`
Details ModelDetails `json:"details,omitempty"`
Messages []Message `json:"messages,omitempty"`
}
type CopyRequest struct {
Source string `json:"source"`
Destination string `json:"destination"`
}
type PullRequest struct {
Model string `json:"model"`
Insecure bool `json:"insecure,omitempty"`
Username string `json:"username"`
Password string `json:"password"`
Stream *bool `json:"stream,omitempty"`
// Name is deprecated, see Model
Name string `json:"name"`
}
type ProgressResponse struct {
Status string `json:"status"`
Digest string `json:"digest,omitempty"`
Total int64 `json:"total,omitempty"`
Completed int64 `json:"completed,omitempty"`
}
type PushRequest struct {
Model string `json:"model"`
Insecure bool `json:"insecure,omitempty"`
Username string `json:"username"`
Password string `json:"password"`
Stream *bool `json:"stream,omitempty"`
// Name is deprecated, see Model
Name string `json:"name"`
}
type ListResponse struct {
Models []ModelResponse `json:"models"`
}
type ModelResponse struct {
Name string `json:"name"`
Model string `json:"model"`
ModifiedAt time.Time `json:"modified_at"`
Size int64 `json:"size"`
Digest string `json:"digest"`
Details ModelDetails `json:"details,omitempty"`
}
type TokenResponse struct {
Token string `json:"token"`
}
type GenerateResponse struct {
Model string `json:"model"`
CreatedAt time.Time `json:"created_at"`
Response string `json:"response"`
Done bool `json:"done"`
Context []int `json:"context,omitempty"`
Metrics
}
type ModelDetails struct {
ParentModel string `json:"parent_model"`
Format string `json:"format"`
Family string `json:"family"`
Families []string `json:"families"`
ParameterSize string `json:"parameter_size"`
QuantizationLevel string `json:"quantization_level"`
}
func (m *Metrics) Summary() {
if m.TotalDuration > 0 {
fmt.Fprintf(os.Stderr, "total duration: %v\n", m.TotalDuration)
}
if m.LoadDuration > 0 {
fmt.Fprintf(os.Stderr, "load duration: %v\n", m.LoadDuration)
}
if m.PromptEvalCount > 0 {
fmt.Fprintf(os.Stderr, "prompt eval count: %d token(s)\n", m.PromptEvalCount)
}
if m.PromptEvalDuration > 0 {
fmt.Fprintf(os.Stderr, "prompt eval duration: %s\n", m.PromptEvalDuration)
fmt.Fprintf(os.Stderr, "prompt eval rate: %.2f tokens/s\n", float64(m.PromptEvalCount)/m.PromptEvalDuration.Seconds())
}
if m.EvalCount > 0 {
fmt.Fprintf(os.Stderr, "eval count: %d token(s)\n", m.EvalCount)
}
if m.EvalDuration > 0 {
fmt.Fprintf(os.Stderr, "eval duration: %s\n", m.EvalDuration)
fmt.Fprintf(os.Stderr, "eval rate: %.2f tokens/s\n", float64(m.EvalCount)/m.EvalDuration.Seconds())
}
}
var ErrInvalidOpts = errors.New("invalid options")
func (opts *Options) FromMap(m map[string]interface{}) error {
valueOpts := reflect.ValueOf(opts).Elem() // names of the fields in the options struct
@@ -292,8 +396,10 @@ func (opts *Options) FromMap(m map[string]interface{}) error {
func DefaultOptions() Options {
return Options{
// options set on request to runner
NumPredict: -1,
NumKeep: -1,
NumPredict: -1,
// set a minimal num_keep to avoid issues on context shifts
NumKeep: 4,
Temperature: 0.8,
TopK: 40,
TopP: 0.9,
@@ -311,19 +417,16 @@ func DefaultOptions() Options {
Runner: Runner{
// options set when the model is loaded
NumCtx: 2048,
RopeFrequencyBase: 10000.0,
RopeFrequencyScale: 1.0,
NumBatch: 512,
NumGPU: -1, // -1 here indicates that NumGPU should be set dynamically
NumGQA: 1,
NumThread: 0, // let the runtime decide
LowVRAM: false,
F16KV: true,
UseMLock: false,
UseMMap: true,
UseNUMA: false,
EmbeddingOnly: true,
NumCtx: 2048,
NumBatch: 512,
NumGPU: -1, // -1 here indicates that NumGPU should be set dynamically
NumGQA: 1,
NumThread: 0, // let the runtime decide
LowVRAM: false,
F16KV: true,
UseMLock: false,
UseMMap: true,
UseNUMA: false,
},
}
}
@@ -343,16 +446,79 @@ func (d *Duration) UnmarshalJSON(b []byte) (err error) {
switch t := v.(type) {
case float64:
if t < 0 {
t = math.MaxFloat64
d.Duration = time.Duration(math.MaxInt64)
} else {
d.Duration = time.Duration(t * float64(time.Second))
}
d.Duration = time.Duration(t)
case string:
d.Duration, err = time.ParseDuration(t)
if err != nil {
return err
}
if d.Duration < 0 {
d.Duration = time.Duration(math.MaxInt64)
}
}
return nil
}
// FormatParams converts specified parameter options to their correct types
func FormatParams(params map[string][]string) (map[string]interface{}, error) {
opts := Options{}
valueOpts := reflect.ValueOf(&opts).Elem() // names of the fields in the options struct
typeOpts := reflect.TypeOf(opts) // types of the fields in the options struct
// build map of json struct tags to their types
jsonOpts := make(map[string]reflect.StructField)
for _, field := range reflect.VisibleFields(typeOpts) {
jsonTag := strings.Split(field.Tag.Get("json"), ",")[0]
if jsonTag != "" {
jsonOpts[jsonTag] = field
}
}
out := make(map[string]interface{})
// iterate params and set values based on json struct tags
for key, vals := range params {
if opt, ok := jsonOpts[key]; !ok {
return nil, fmt.Errorf("unknown parameter '%s'", key)
} else {
field := valueOpts.FieldByName(opt.Name)
if field.IsValid() && field.CanSet() {
switch field.Kind() {
case reflect.Float32:
floatVal, err := strconv.ParseFloat(vals[0], 32)
if err != nil {
return nil, fmt.Errorf("invalid float value %s", vals)
}
out[key] = float32(floatVal)
case reflect.Int:
intVal, err := strconv.ParseInt(vals[0], 10, 64)
if err != nil {
return nil, fmt.Errorf("invalid int value %s", vals)
}
out[key] = intVal
case reflect.Bool:
boolVal, err := strconv.ParseBool(vals[0])
if err != nil {
return nil, fmt.Errorf("invalid bool value %s", vals)
}
out[key] = boolVal
case reflect.String:
out[key] = vals[0]
case reflect.Slice:
// TODO: only string slices are supported right now
out[key] = vals
default:
return nil, fmt.Errorf("unknown type %s for %s", field.Kind(), key)
}
}
}
}
return out, nil
}

50
api/types_test.go Normal file
View File

@@ -0,0 +1,50 @@
package api
import (
"encoding/json"
"math"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestKeepAliveParsingFromJSON(t *testing.T) {
tests := []struct {
name string
req string
exp *Duration
}{
{
name: "Positive Integer",
req: `{ "keep_alive": 42 }`,
exp: &Duration{42 * time.Second},
},
{
name: "Positive Integer String",
req: `{ "keep_alive": "42m" }`,
exp: &Duration{42 * time.Minute},
},
{
name: "Negative Integer",
req: `{ "keep_alive": -1 }`,
exp: &Duration{math.MaxInt64},
},
{
name: "Negative Integer String",
req: `{ "keep_alive": "-1m" }`,
exp: &Duration{math.MaxInt64},
},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
var dec ChatRequest
err := json.Unmarshal([]byte(test.req), &dec)
require.NoError(t, err)
assert.Equal(t, test.exp, dec.KeepAlive)
})
}
}

View File

@@ -1,16 +0,0 @@
{
"env": {
"browser": true,
"es6": true,
"node": true
},
"extends": [
"eslint:recommended",
"plugin:@typescript-eslint/eslint-recommended",
"plugin:@typescript-eslint/recommended",
"plugin:import/recommended",
"plugin:import/electron",
"plugin:import/typescript"
],
"parser": "@typescript-eslint/parser"
}

94
app/.gitignore vendored
View File

@@ -1,92 +1,2 @@
# Logs
logs
*.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
lerna-debug.log*
# Diagnostic reports (https://nodejs.org/api/report.html)
report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
# Runtime data
pids
*.pid
*.seed
*.pid.lock
.DS_Store
# Directory for instrumented libs generated by jscoverage/JSCover
lib-cov
# Coverage directory used by tools like istanbul
coverage
*.lcov
# nyc test coverage
.nyc_output
# node-waf configuration
.lock-wscript
# Compiled binary addons (https://nodejs.org/api/addons.html)
build/Release
# Dependency directories
node_modules/
jspm_packages/
# TypeScript v1 declaration files
typings/
# TypeScript cache
*.tsbuildinfo
# Optional npm cache directory
.npm
# Optional eslint cache
.eslintcache
# Optional REPL history
.node_repl_history
# Output of 'npm pack'
*.tgz
# Yarn Integrity file
.yarn-integrity
# dotenv environment variables file
.env
.env.test
# parcel-bundler cache (https://parceljs.org/)
.cache
# next.js build output
.next
# nuxt.js build output
.nuxt
# vuepress build output
.vuepress/dist
# Serverless directories
.serverless/
# FuseBox cache
.fusebox/
# DynamoDB Local files
.dynamodb/
# Webpack
.webpack/
# Vite
.vite/
# Electron-Forge
out/
ollama.syso
app

7
app/AppDelegate.h Normal file
View File

@@ -0,0 +1,7 @@
#import <Cocoa/Cocoa.h>
@interface AppDelegate : NSObject <NSApplicationDelegate>
- (void)applicationDidFinishLaunching:(NSNotification *)aNotification;
@end

View File

@@ -1,21 +1,18 @@
# Desktop
# Ollama App
This app builds upon Ollama to provide a desktop experience for running models.
## macOS
## Developing
TODO
First, build the `ollama` binary:
## Windows
If you want to build the installer, youll need to install
- https://jrsoftware.org/isinfo.php
In the top directory of this repo, run the following powershell script
to build the ollama CLI, ollama app, and ollama installer.
```
cd ..
go build .
powershell -ExecutionPolicy Bypass -File .\scripts\build_windows.ps1
```
Then run the desktop app with `npm start`:
```
cd app
npm install
npm start
```

76
app/app_darwin.go Normal file
View File

@@ -0,0 +1,76 @@
package main
// #cgo CFLAGS: -x objective-c
// #cgo LDFLAGS: -framework Cocoa -framework LocalAuthentication -framework ServiceManagement
// #include "app_darwin.h"
import "C"
import (
"context"
"fmt"
"log/slog"
"os"
"path/filepath"
"syscall"
)
func init() {
home, err := os.UserHomeDir()
if err != nil {
panic(err)
}
ServerLogFile = filepath.Join(home, ".ollama", "logs", "server.log")
}
func run() {
initLogging()
slog.Info("ollama macOS app started")
// Ask to move to applications directory
moving := C.askToMoveToApplications()
if moving {
return
}
C.killOtherInstances()
code := C.installSymlink()
if code != 0 {
slog.Error("Failed to install symlink")
}
exe, err := os.Executable()
if err != nil {
panic(err)
}
var options ServerOptions
ctx, cancel := context.WithCancel(context.Background())
var done chan int
done, err = SpawnServer(ctx, filepath.Join(filepath.Dir(exe), "..", "Resources", "ollama"), options)
if err != nil {
slog.Error(fmt.Sprintf("Failed to spawn ollama server %s", err))
done = make(chan int, 1)
done <- 1
}
// Run the native macOS app
// Note: this will block until the app is closed
C.run()
slog.Info("ollama macOS app closed")
cancel()
slog.Info("Waiting for ollama server to shutdown...")
if done != nil {
<-done
}
slog.Info("Ollama app exiting")
}
//export Quit
func Quit() {
syscall.Kill(os.Getpid(), syscall.SIGTERM)
}

13
app/app_darwin.h Normal file
View File

@@ -0,0 +1,13 @@
#import <Cocoa/Cocoa.h>
@interface AppDelegate : NSObject <NSApplicationDelegate>
- (void)applicationDidFinishLaunching:(NSNotification *)aNotification;
@end
void run();
void killOtherInstances();
bool askToMoveToApplications();
int createSymlinkWithAuthorization();
int installSymlink();
extern void Restart();
extern void Quit();

282
app/app_darwin.m Normal file
View File

@@ -0,0 +1,282 @@
#import <AppKit/AppKit.h>
#import <Cocoa/Cocoa.h>
#import <CoreServices/CoreServices.h>
#import <Security/Security.h>
#import <ServiceManagement/ServiceManagement.h>
#import "app_darwin.h"
@interface AppDelegate ()
@property (strong, nonatomic) NSStatusItem *statusItem;
@end
@implementation AppDelegate
- (void)applicationDidFinishLaunching:(NSNotification *)aNotification {
// show status menu
NSMenu *menu = [[NSMenu alloc] init];
NSMenuItem *aboutMenuItem = [[NSMenuItem alloc] initWithTitle:@"About Ollama" action:@selector(aboutOllama) keyEquivalent:@""];
[aboutMenuItem setTarget:self];
[menu addItem:aboutMenuItem];
// Settings submenu
NSMenu *settingsMenu = [[NSMenu alloc] initWithTitle:@"Settings"];
// Submenu items
NSMenuItem *chooseModelDirectoryItem = [[NSMenuItem alloc] initWithTitle:@"Choose model directory..." action:@selector(chooseModelDirectory) keyEquivalent:@""];
[chooseModelDirectoryItem setTarget:self];
[chooseModelDirectoryItem setEnabled:YES];
[settingsMenu addItem:chooseModelDirectoryItem];
NSMenuItem *exposeExternallyItem = [[NSMenuItem alloc] initWithTitle:@"Allow external connections" action:@selector(toggleExposeExternally:) keyEquivalent:@""];
[exposeExternallyItem setTarget:self];
[exposeExternallyItem setState:NSOffState]; // Set initial state to off
[exposeExternallyItem setEnabled:YES];
[settingsMenu addItem:exposeExternallyItem];
NSMenuItem *allowCrossOriginItem = [[NSMenuItem alloc] initWithTitle:@"Allow browser requests" action:@selector(toggleCrossOrigin:) keyEquivalent:@""];
[allowCrossOriginItem setTarget:self];
[allowCrossOriginItem setState:NSOffState]; // Set initial state to off
[allowCrossOriginItem setEnabled:YES];
[settingsMenu addItem:allowCrossOriginItem];
NSMenuItem *settingsMenuItem = [[NSMenuItem alloc] initWithTitle:@"Settings" action:nil keyEquivalent:@""];
[settingsMenuItem setSubmenu:settingsMenu];
[menu addItem:settingsMenuItem];
[menu addItemWithTitle:@"Quit Ollama" action:@selector(quit) keyEquivalent:@"q"];
self.statusItem = [[NSStatusBar systemStatusBar] statusItemWithLength:NSVariableStatusItemLength];
[self.statusItem addObserver:self forKeyPath:@"button.effectiveAppearance" options:NSKeyValueObservingOptionNew|NSKeyValueObservingOptionInitial context:nil];
self.statusItem.menu = menu;
[self showIcon];
}
- (void)aboutOllama {
[[NSApplication sharedApplication] orderFrontStandardAboutPanel:nil];
}
- (void)toggleCrossOrigin:(id)sender {
NSMenuItem *item = (NSMenuItem *)sender;
if ([item state] == NSOffState) {
// Do something when cross-origin requests are allowed
[item setState:NSOnState];
} else {
// Do something when cross-origin requests are disallowed
[item setState:NSOffState];
}
}
- (void)toggleExposeExternally:(id)sender {
NSMenuItem *item = (NSMenuItem *)sender;
if ([item state] == NSOffState) {
// Do something when Ollama is exposed externally
[item setState:NSOnState];
} else {
// Do something when Ollama is not exposed externally
[item setState:NSOffState];
}
}
- (void)chooseModelDirectory {
NSOpenPanel *openPanel = [NSOpenPanel openPanel];
[openPanel setCanChooseFiles:NO];
[openPanel setCanChooseDirectories:YES];
[openPanel setAllowsMultipleSelection:NO];
NSInteger result = [openPanel runModal];
if (result == NSModalResponseOK) {
NSURL *selectedDirectoryURL = [openPanel URLs].firstObject;
// Do something with the selected directory URL
}
}
-(void) showIcon {
NSAppearance* appearance = self.statusItem.button.effectiveAppearance;
NSString* appearanceName = (NSString*)(appearance.name);
NSString* iconName = [[appearanceName lowercaseString] containsString:@"dark"] ? @"iconDark" : @"icon";
NSImage* statusImage = [NSImage imageNamed:iconName];
[statusImage setTemplate:YES];
self.statusItem.button.image = statusImage;
}
-(void)observeValueForKeyPath:(NSString *)keyPath ofObject:(id)object change:(NSDictionary<NSKeyValueChangeKey,id> *)change context:(void *)context {
[self showIcon];
}
- (void)quit {
[NSApp stop:nil];
}
@end
void run() {
@autoreleasepool {
[NSApplication sharedApplication];
AppDelegate *appDelegate = [[AppDelegate alloc] init];
[NSApp setDelegate:appDelegate];
[NSApp run];
}
}
// killOtherInstances kills all other instances of the app currently
// running. This way we can ensure that only the most recently started
// instance of Ollama is running
void killOtherInstances() {
pid_t pid = getpid();
NSArray *all = [[NSWorkspace sharedWorkspace] runningApplications];
NSMutableArray *apps = [NSMutableArray array];
for (NSRunningApplication *app in all) {
if ([app.bundleIdentifier isEqualToString:[[NSBundle mainBundle] bundleIdentifier]] ||
[app.bundleIdentifier isEqualToString:@"ai.ollama.ollama"] ||
[app.bundleIdentifier isEqualToString:@"com.electron.ollama"]) {
if (app.processIdentifier != pid) {
[apps addObject:app];
}
}
}
for (NSRunningApplication *app in apps) {
kill(app.processIdentifier, SIGTERM);
}
NSDate *startTime = [NSDate date];
for (NSRunningApplication *app in apps) {
while (!app.terminated) {
if (-[startTime timeIntervalSinceNow] >= 5) {
kill(app.processIdentifier, SIGKILL);
break;
}
[[NSRunLoop currentRunLoop] runUntilDate:[NSDate dateWithTimeIntervalSinceNow:0.1]];
}
}
}
bool askToMoveToApplications() {
NSString *bundlePath = [[NSBundle mainBundle] bundlePath];
if ([bundlePath hasPrefix:@"/Applications"]) {
return false;
}
NSAlert *alert = [[NSAlert alloc] init];
[alert setMessageText:@"Move to Applications?"];
[alert setInformativeText:@"Ollama works best when run from the Applications directory."];
[alert addButtonWithTitle:@"Move to Applications"];
[alert addButtonWithTitle:@"Don't move"];
[NSApp activateIgnoringOtherApps:YES];
if ([alert runModal] != NSAlertFirstButtonReturn) {
return false;
}
// move to applications
NSString *applicationsPath = @"/Applications";
NSString *newPath = [applicationsPath stringByAppendingPathComponent:@"Ollama.app"];
NSFileManager *fileManager = [NSFileManager defaultManager];
// Check if the newPath already exists
if ([fileManager fileExistsAtPath:newPath]) {
NSError *removeError = nil;
[fileManager removeItemAtPath:newPath error:&removeError];
if (removeError) {
NSLog(@"Error removing file at %@: %@", newPath, removeError);
return false; // or handle the error
}
}
NSError *moveError = nil;
[fileManager moveItemAtPath:bundlePath toPath:newPath error:&moveError];
if (moveError) {
NSLog(@"Error moving file from %@ to %@: %@", bundlePath, newPath, moveError);
return false;
}
NSLog(@"Opening %@", newPath);
NSError *error = nil;
NSWorkspace *workspace = [NSWorkspace sharedWorkspace];
#pragma clang diagnostic ignored "-Wdeprecated-declarations"
[workspace launchApplicationAtURL:[NSURL fileURLWithPath:newPath]
options:NSWorkspaceLaunchNewInstance | NSWorkspaceLaunchDefault
configuration:@{}
error:&error];
return true;
}
int installSymlink() {
NSString *linkPath = @"/usr/local/bin/ollama";
NSError *error = nil;
NSFileManager *fileManager = [NSFileManager defaultManager];
NSString *symlinkPath = [fileManager destinationOfSymbolicLinkAtPath:linkPath error:&error];
NSString *bundlePath = [[NSBundle mainBundle] bundlePath];
NSString *execPath = [[NSBundle mainBundle] executablePath];
NSString *resPath = [[NSBundle mainBundle] pathForResource:@"ollama" ofType:nil];
// if the symlink already exists and points to the right place, don't prompt
if ([symlinkPath isEqualToString:resPath]) {
NSLog(@"symbolic link already exists and points to the right place");
return 0;
}
NSString *authorizationPrompt = @"Ollama is trying to install its command line interface (CLI) tool.";
AuthorizationRef auth = NULL;
OSStatus createStatus = AuthorizationCreate(NULL, kAuthorizationEmptyEnvironment, kAuthorizationFlagDefaults, &auth);
if (createStatus != errAuthorizationSuccess) {
NSLog(@"Error creating authorization");
return -1;
}
NSString * bundleIdentifier = [[NSBundle mainBundle] bundleIdentifier];
NSString *rightNameString = [NSString stringWithFormat:@"%@.%@", bundleIdentifier, @"auth3"];
const char *rightName = rightNameString.UTF8String;
OSStatus getRightResult = AuthorizationRightGet(rightName, NULL);
if (getRightResult == errAuthorizationDenied) {
if (AuthorizationRightSet(auth, rightName, (__bridge CFTypeRef _Nonnull)(@(kAuthorizationRuleAuthenticateAsAdmin)), (__bridge CFStringRef _Nullable)(authorizationPrompt), NULL, NULL) != errAuthorizationSuccess) {
NSLog(@"Failed to set right");
return -1;
}
}
AuthorizationItem right = { .name = rightName, .valueLength = 0, .value = NULL, .flags = 0 };
AuthorizationRights rights = { .count = 1, .items = &right };
AuthorizationFlags flags = (AuthorizationFlags)(kAuthorizationFlagExtendRights | kAuthorizationFlagInteractionAllowed);
AuthorizationItem iconAuthorizationItem = {.name = kAuthorizationEnvironmentIcon, .valueLength = 0, .value = NULL, .flags = 0};
AuthorizationEnvironment authorizationEnvironment = {.count = 0, .items = NULL};
BOOL failedToUseSystemDomain = NO;
OSStatus copyStatus = AuthorizationCopyRights(auth, &rights, &authorizationEnvironment, flags, NULL);
if (copyStatus != errAuthorizationSuccess) {
failedToUseSystemDomain = YES;
if (copyStatus == errAuthorizationCanceled) {
NSLog(@"User cancelled authorization");
return -1;
} else {
NSLog(@"Failed copying system domain rights: %d", copyStatus);
return -1;
}
}
const char *toolPath = "/bin/ln";
const char *args[] = {"-s", "-F", [resPath UTF8String], "/usr/local/bin/ollama", NULL};
FILE *pipe = NULL;
#pragma clang diagnostic ignored "-Wdeprecated-declarations"
OSStatus status = AuthorizationExecuteWithPrivileges(auth, toolPath, kAuthorizationFlagDefaults, (char *const *)args, &pipe);
if (status != errAuthorizationSuccess) {
NSLog(@"Failed to create symlink");
return -1;
}
AuthorizationFree(auth, kAuthorizationFlagDestroyRights);
return 0;
}

166
app/app_windows.go Normal file
View File

@@ -0,0 +1,166 @@
package main
import (
"context"
"errors"
"fmt"
"log"
"log/slog"
"os"
"os/exec"
"os/signal"
"path/filepath"
"strings"
"syscall"
"github.com/ollama/ollama/app/lifecycle"
"github.com/ollama/ollama/app/store"
"github.com/ollama/ollama/app/tray"
"github.com/ollama/ollama/app/updater"
)
func init() {
AppName += ".exe"
CLIName += ".exe"
// Logs, configs, downloads go to LOCALAPPDATA
localAppData := os.Getenv("LOCALAPPDATA")
AppDataDir = filepath.Join(localAppData, "Ollama")
AppLogFile = filepath.Join(AppDataDir, "app.log")
ServerLogFile = filepath.Join(AppDataDir, "server.log")
// Executables are stored in APPDATA
AppDir = filepath.Join(localAppData, "Programs", "Ollama")
// Make sure we have PATH set correctly for any spawned children
paths := strings.Split(os.Getenv("PATH"), ";")
// Start with whatever we find in the PATH/LD_LIBRARY_PATH
found := false
for _, path := range paths {
d, err := filepath.Abs(path)
if err != nil {
continue
}
if strings.EqualFold(AppDir, d) {
found = true
}
}
if !found {
paths = append(paths, AppDir)
pathVal := strings.Join(paths, ";")
slog.Debug("setting PATH=" + pathVal)
err := os.Setenv("PATH", pathVal)
if err != nil {
slog.Error(fmt.Sprintf("failed to update PATH: %s", err))
}
}
// Make sure our logging dir exists
_, err := os.Stat(AppDataDir)
if errors.Is(err, os.ErrNotExist) {
if err := os.MkdirAll(AppDataDir, 0o755); err != nil {
slog.Error(fmt.Sprintf("create ollama dir %s: %v", AppDataDir, err))
}
}
}
func ShowLogs() {
cmd_path := "c:\\Windows\\system32\\cmd.exe"
slog.Debug(fmt.Sprintf("viewing logs with start %s", AppDataDir))
cmd := exec.Command(cmd_path, "/c", "start", AppDataDir)
cmd.SysProcAttr = &syscall.SysProcAttr{HideWindow: false, CreationFlags: 0x08000000}
err := cmd.Start()
if err != nil {
slog.Error(fmt.Sprintf("Failed to open log dir: %s", err))
}
}
func Start() {
cmd_path := "c:\\Windows\\system32\\cmd.exe"
slog.Debug(fmt.Sprintf("viewing logs with start %s", AppDataDir))
cmd := exec.Command(cmd_path, "/c", "start", AppDataDir)
cmd.SysProcAttr = &syscall.SysProcAttr{HideWindow: false, CreationFlags: 0x08000000}
err := cmd.Start()
if err != nil {
slog.Error(fmt.Sprintf("Failed to open log dir: %s", err))
}
}
func run() {
initLogging()
slog.Info("ollama windows app started")
ctx, cancel := context.WithCancel(context.Background())
var done chan int
t, err := tray.NewTray()
if err != nil {
log.Fatalf("Failed to start: %s", err)
}
callbacks := t.GetCallbacks()
signals := make(chan os.Signal, 1)
signal.Notify(signals, syscall.SIGINT, syscall.SIGTERM)
go func() {
slog.Debug("starting callback loop")
for {
select {
case <-callbacks.Quit:
slog.Debug("quit called")
t.Quit()
case <-signals:
slog.Debug("shutting down due to signal")
t.Quit()
case <-callbacks.Update:
err := updater.DoUpgrade(cancel, done)
if err != nil {
slog.Warn(fmt.Sprintf("upgrade attempt failed: %s", err))
}
case <-callbacks.ShowLogs:
ShowLogs()
case <-callbacks.DoFirstUse:
err := lifecycle.GetStarted()
if err != nil {
slog.Warn(fmt.Sprintf("Failed to launch getting started shell: %s", err))
}
}
}
}()
if !store.GetFirstTimeRun() {
slog.Debug("First time run")
err = t.DisplayFirstUseNotification()
if err != nil {
slog.Debug(fmt.Sprintf("XXX failed to display first use notification %v", err))
}
store.SetFirstTimeRun(true)
} else {
slog.Debug("Not first time, skipping first run notification")
}
if isServerRunning(ctx) {
slog.Info("Detected another instance of ollama running, exiting")
os.Exit(1)
}
done, err = SpawnServer(ctx, CLIName)
if err != nil {
// TODO - should we retry in a backoff loop?
// TODO - should we pop up a warning and maybe add a menu item to view application logs?
slog.Error(fmt.Sprintf("Failed to spawn ollama server %s", err))
done = make(chan int, 1)
done <- 1
}
updater.StartBackgroundUpdaterChecker(ctx, t.UpdateAvailable)
t.Run()
cancel()
slog.Info("Waiting for ollama server to shutdown...")
if done != nil {
<-done
}
slog.Info("Ollama app exiting")
}

BIN
app/assets/app.ico Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.3 KiB

17
app/assets/assets.go Normal file
View File

@@ -0,0 +1,17 @@
package assets
import (
"embed"
"io/fs"
)
//go:embed *.ico
var icons embed.FS
func ListIcons() ([]string, error) {
return fs.Glob(icons, "*")
}
func GetIcon(filename string) ([]byte, error) {
return icons.ReadFile(filename)
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 402 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 741 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 440 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 763 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 447 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 891 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 443 B

Binary file not shown.

Before

Width:  |  Height:  |  Size: 844 B

BIN
app/assets/setup.bmp Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 76 KiB

BIN
app/assets/tray.ico Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 89 KiB

BIN
app/assets/tray_upgrade.ico Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 91 KiB

View File

@@ -0,0 +1,40 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>CFBundleDisplayName</key>
<string>Ollama</string>
<key>CFBundleExecutable</key>
<string>Ollama</string>
<key>CFBundleIconFile</key>
<string>icon.icns</string>
<key>CFBundleIdentifier</key>
<string>com.ollama.ollama</string>
<key>CFBundleInfoDictionaryVersion</key>
<string>6.0</string>
<key>CFBundleName</key>
<string>Ollama</string>
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>0.0.0</string>
<key>CFBundleVersion</key>
<string>0.0.0</string>
<key>DTCompiler</key>
<string>com.apple.compilers.llvm.clang.1_0</string>
<key>DTSDKBuild</key>
<string>22E245</string>
<key>DTSDKName</key>
<string>macosx13.3</string>
<key>DTXcode</key>
<string>1431</string>
<key>DTXcodeBuild</key>
<string>14E300c</string>
<key>LSApplicationCategoryType</key>
<string>public.app-category.developer-tools</string>
<key>LSMinimumSystemVersion</key>
<string>11.0</string>
<key>LSUIElement</key>
<true/>
</dict>
</plist>

Binary file not shown.

After

Width:  |  Height:  |  Size: 382 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 691 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 382 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 721 B

View File

@@ -1,78 +0,0 @@
import type { ForgeConfig } from '@electron-forge/shared-types'
import { MakerSquirrel } from '@electron-forge/maker-squirrel'
import { MakerZIP } from '@electron-forge/maker-zip'
import { PublisherGithub } from '@electron-forge/publisher-github'
import { AutoUnpackNativesPlugin } from '@electron-forge/plugin-auto-unpack-natives'
import { WebpackPlugin } from '@electron-forge/plugin-webpack'
import * as path from 'path'
import * as fs from 'fs'
import { mainConfig } from './webpack.main.config'
import { rendererConfig } from './webpack.renderer.config'
const packageJson = JSON.parse(fs.readFileSync(path.resolve(__dirname, './package.json'), 'utf8'))
const config: ForgeConfig = {
packagerConfig: {
appVersion: process.env.VERSION || packageJson.version,
asar: true,
icon: './assets/icon.icns',
extraResource: [
'../dist/ollama',
path.join(__dirname, './assets/iconTemplate.png'),
path.join(__dirname, './assets/iconTemplate@2x.png'),
path.join(__dirname, './assets/iconUpdateTemplate.png'),
path.join(__dirname, './assets/iconUpdateTemplate@2x.png'),
path.join(__dirname, './assets/iconDarkTemplate.png'),
path.join(__dirname, './assets/iconDarkTemplate@2x.png'),
path.join(__dirname, './assets/iconDarkUpdateTemplate.png'),
path.join(__dirname, './assets/iconDarkUpdateTemplate@2x.png'),
],
...(process.env.SIGN
? {
osxSign: {
identity: process.env.APPLE_IDENTITY,
},
osxNotarize: {
tool: 'notarytool',
appleId: process.env.APPLE_ID || '',
appleIdPassword: process.env.APPLE_PASSWORD || '',
teamId: process.env.APPLE_TEAM_ID || '',
},
}
: {}),
osxUniversal: {
x64ArchFiles: '**/ollama',
},
},
rebuildConfig: {},
makers: [new MakerSquirrel({}), new MakerZIP({}, ['darwin'])],
hooks: {
readPackageJson: async (_, packageJson) => {
return { ...packageJson, version: process.env.VERSION || packageJson.version }
},
},
plugins: [
new AutoUnpackNativesPlugin({}),
new WebpackPlugin({
mainConfig,
devContentSecurityPolicy: `default-src * 'unsafe-eval' 'unsafe-inline'; img-src data: 'self'`,
renderer: {
config: rendererConfig,
nodeIntegration: true,
entryPoints: [
{
html: './src/index.html',
js: './src/renderer.tsx',
name: 'main_window',
preload: {
js: './src/preload.ts',
},
},
],
},
}),
],
}
export default config

View File

@@ -0,0 +1,7 @@
package lifecycle
import "fmt"
func GetStarted() error {
return fmt.Errorf("GetStarted not implemented")
}

View File

@@ -0,0 +1,44 @@
package lifecycle
import (
"fmt"
"log/slog"
"os"
"os/exec"
"path/filepath"
"syscall"
)
func GetStarted() error {
const CREATE_NEW_CONSOLE = 0x00000010
var err error
bannerScript := filepath.Join(AppDir, "ollama_welcome.ps1")
args := []string{
// TODO once we're signed, the execution policy bypass should be removed
"powershell", "-noexit", "-ExecutionPolicy", "Bypass", "-nologo", "-file", bannerScript,
}
args[0], err = exec.LookPath(args[0])
if err != nil {
return err
}
// Make sure the script actually exists
_, err = os.Stat(bannerScript)
if err != nil {
return fmt.Errorf("getting started banner script error %s", err)
}
slog.Info(fmt.Sprintf("opening getting started terminal with %v", args))
attrs := &os.ProcAttr{
Files: []*os.File{os.Stdin, os.Stdout, os.Stderr},
Sys: &syscall.SysProcAttr{CreationFlags: CREATE_NEW_CONSOLE, HideWindow: false},
}
proc, err := os.StartProcess(args[0], args, attrs)
if err != nil {
return fmt.Errorf("unable to start getting started shell %w", err)
}
slog.Debug(fmt.Sprintf("getting started terminal PID: %d", proc.Pid))
return proc.Release()
}

74
app/lifecycle/paths.go Normal file
View File

@@ -0,0 +1,74 @@
package lifecycle
import (
"errors"
"fmt"
"log/slog"
"os"
"path/filepath"
"runtime"
"strings"
)
var (
AppName = "ollama app"
CLIName = "ollama"
AppDir = "/opt/Ollama"
AppDataDir = "/opt/Ollama"
// TODO - should there be a distinct log dir?
UpdateStageDir = "/tmp"
AppLogFile = "/tmp/ollama_app.log"
ServerLogFile = "/tmp/ollama.log"
UpgradeLogFile = "/tmp/ollama_update.log"
Installer = "OllamaSetup.exe"
)
func init() {
if runtime.GOOS == "windows" {
AppName += ".exe"
CLIName += ".exe"
// Logs, configs, downloads go to LOCALAPPDATA
localAppData := os.Getenv("LOCALAPPDATA")
AppDataDir = filepath.Join(localAppData, "Ollama")
UpdateStageDir = filepath.Join(AppDataDir, "updates")
AppLogFile = filepath.Join(AppDataDir, "app.log")
ServerLogFile = filepath.Join(AppDataDir, "server.log")
UpgradeLogFile = filepath.Join(AppDataDir, "upgrade.log")
// Executables are stored in APPDATA
AppDir = filepath.Join(localAppData, "Programs", "Ollama")
// Make sure we have PATH set correctly for any spawned children
paths := strings.Split(os.Getenv("PATH"), ";")
// Start with whatever we find in the PATH/LD_LIBRARY_PATH
found := false
for _, path := range paths {
d, err := filepath.Abs(path)
if err != nil {
continue
}
if strings.EqualFold(AppDir, d) {
found = true
}
}
if !found {
paths = append(paths, AppDir)
pathVal := strings.Join(paths, ";")
slog.Debug("setting PATH=" + pathVal)
err := os.Setenv("PATH", pathVal)
if err != nil {
slog.Error(fmt.Sprintf("failed to update PATH: %s", err))
}
}
// Make sure our logging dir exists
_, err := os.Stat(AppDataDir)
if errors.Is(err, os.ErrNotExist) {
if err := os.MkdirAll(AppDataDir, 0o755); err != nil {
slog.Error(fmt.Sprintf("create ollama dir %s: %v", AppDataDir, err))
}
}
}
}

44
app/log.go Normal file
View File

@@ -0,0 +1,44 @@
package main
import (
"fmt"
"log/slog"
"os"
"path/filepath"
)
func initLogging() {
level := slog.LevelInfo
if debug := os.Getenv("OLLAMA_DEBUG"); debug != "" {
level = slog.LevelDebug
}
var logFile *os.File
var err error
// Detect if we're a GUI app on windows, and if not, send logs to console
if os.Stderr.Fd() != 0 {
// Console app detected
logFile = os.Stderr
// TODO - write one-line to the app.log file saying we're running in console mode to help avoid confusion
} else {
logFile, err = os.OpenFile(AppLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0755)
if err != nil {
slog.Error(fmt.Sprintf("failed to create server log %v", err))
return
}
}
handler := slog.NewTextHandler(logFile, &slog.HandlerOptions{
Level: level,
AddSource: true,
ReplaceAttr: func(_ []string, attr slog.Attr) slog.Attr {
if attr.Key == slog.SourceKey {
source := attr.Value.Any().(*slog.Source)
source.File = filepath.Base(source.File)
}
return attr
},
})
slog.SetDefault(slog.New(handler))
}

16
app/main.go Normal file
View File

@@ -0,0 +1,16 @@
package main
// Compile with the following to get rid of the cmd pop up on windows
// go build -ldflags="-H windowsgui" .
var (
AppName string
CLIName string
AppDir string
AppDataDir string
AppLogFile string
ServerLogFile string
)
func main() {
run()
}

16695
app/package-lock.json generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,84 +0,0 @@
{
"name": "ollama",
"productName": "Ollama",
"version": "0.0.0",
"description": "ollama",
"main": ".webpack/main",
"scripts": {
"start": "electron-forge start",
"package": "electron-forge package --arch universal",
"package:sign": "SIGN=1 electron-forge package --arch universal",
"make": "electron-forge make --arch universal",
"make:sign": "SIGN=1 electron-forge make --arch universal",
"publish": "SIGN=1 electron-forge publish",
"lint": "eslint --ext .ts,.tsx .",
"format": "prettier --check . --ignore-path .gitignore",
"format:fix": "prettier --write . --ignore-path .gitignore"
},
"keywords": [],
"author": {
"name": "Jeffrey Morgan",
"email": "jmorganca@gmail.com"
},
"license": "MIT",
"devDependencies": {
"@babel/core": "^7.22.5",
"@babel/preset-react": "^7.22.5",
"@electron-forge/cli": "^6.2.1",
"@electron-forge/maker-deb": "^6.2.1",
"@electron-forge/maker-rpm": "^6.2.1",
"@electron-forge/maker-squirrel": "^6.2.1",
"@electron-forge/maker-zip": "^6.2.1",
"@electron-forge/plugin-auto-unpack-natives": "^6.2.1",
"@electron-forge/plugin-webpack": "^6.2.1",
"@electron-forge/publisher-github": "^6.2.1",
"@electron/universal": "^1.4.1",
"@svgr/webpack": "^8.0.1",
"@types/chmodr": "^1.0.0",
"@types/node": "^20.4.0",
"@types/react": "^18.2.14",
"@types/react-dom": "^18.2.6",
"@types/uuid": "^9.0.2",
"@typescript-eslint/eslint-plugin": "^5.60.0",
"@typescript-eslint/parser": "^5.60.0",
"@vercel/webpack-asset-relocator-loader": "^1.7.3",
"babel-loader": "^9.1.2",
"chmodr": "^1.2.0",
"copy-webpack-plugin": "^11.0.0",
"css-loader": "^6.8.1",
"electron": "25.9.2",
"eslint": "^8.43.0",
"eslint-plugin-import": "^2.27.5",
"fork-ts-checker-webpack-plugin": "^7.3.0",
"node-loader": "^2.0.0",
"postcss": "^8.4.24",
"postcss-import": "^15.1.0",
"postcss-loader": "^7.3.3",
"postcss-preset-env": "^8.5.1",
"prettier": "^2.8.8",
"prettier-plugin-tailwindcss": "^0.3.0",
"style-loader": "^3.3.3",
"svg-inline-loader": "^0.8.2",
"tailwindcss": "^3.3.2",
"ts-loader": "^9.4.3",
"ts-node": "^10.9.1",
"typescript": "~4.5.4",
"url-loader": "^4.1.1",
"webpack": "^5.88.0",
"webpack-cli": "^5.1.4",
"webpack-dev-server": "^4.15.1"
},
"dependencies": {
"@electron/remote": "^2.0.10",
"@heroicons/react": "^2.0.18",
"@segment/analytics-node": "^1.0.0",
"copy-to-clipboard": "^3.3.3",
"electron-squirrel-startup": "^1.0.0",
"electron-store": "^8.1.0",
"react": "^18.2.0",
"react-dom": "^18.2.0",
"uuid": "^9.0.0",
"winston": "^3.10.0",
"winston-daily-rotate-file": "^4.7.1"
}
}

View File

@@ -1,7 +0,0 @@
module.exports = {
plugins: {
'postcss-import': {},
tailwindcss: {},
autoprefixer: {},
},
}

163
app/server.go Normal file
View File

@@ -0,0 +1,163 @@
package main
import (
"context"
"errors"
"fmt"
"io"
"log/slog"
"os"
"os/exec"
"path/filepath"
"time"
"github.com/ollama/ollama/api"
)
type ServerOptions struct {
Cors bool
Expose bool
ModelsPath string
}
func start(ctx context.Context, command string, options ServerOptions) (*exec.Cmd, error) {
cmd := getCmd(ctx, command)
// set environment variables
if options.ModelsPath != "" {
cmd.Env = append(cmd.Env, fmt.Sprintf("OLLAMA_MODELS=%s", options.ModelsPath))
}
if options.Cors {
cmd.Env = append(cmd.Env, "OLLAMA_ORIGINS=*")
}
if options.Expose {
cmd.Env = append(cmd.Env, "OLLAMA_HOST=0.0.0.0")
}
stdout, err := cmd.StdoutPipe()
if err != nil {
return nil, fmt.Errorf("failed to spawn server stdout pipe: %w", err)
}
stderr, err := cmd.StderrPipe()
if err != nil {
return nil, fmt.Errorf("failed to spawn server stderr pipe: %w", err)
}
// TODO - rotation
logFile, err := os.OpenFile(ServerLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0755)
if err != nil {
return nil, fmt.Errorf("failed to create server log: %w", err)
}
go func() {
defer logFile.Close()
io.Copy(logFile, stdout) //nolint:errcheck
}()
go func() {
defer logFile.Close()
io.Copy(logFile, stderr) //nolint:errcheck
}()
// Re-wire context done behavior to attempt a graceful shutdown of the server
cmd.Cancel = func() error {
if cmd.Process != nil {
err := terminate(cmd)
if err != nil {
slog.Warn("error trying to gracefully terminate server", "err", err)
return cmd.Process.Kill()
}
tick := time.NewTicker(10 * time.Millisecond)
defer tick.Stop()
for {
select {
case <-tick.C:
exited, err := isProcessExited(cmd.Process.Pid)
if err != nil {
return err
}
if exited {
return nil
}
case <-time.After(5 * time.Second):
slog.Warn("graceful server shutdown timeout, killing", "pid", cmd.Process.Pid)
return cmd.Process.Kill()
}
}
}
return nil
}
// run the command and wait for it to finish
if err := cmd.Start(); err != nil {
return nil, fmt.Errorf("failed to start server %w", err)
}
if cmd.Process != nil {
slog.Info(fmt.Sprintf("started ollama server with pid %d", cmd.Process.Pid))
}
slog.Info(fmt.Sprintf("ollama server logs %s", ServerLogFile))
return cmd, nil
}
func SpawnServer(ctx context.Context, command string, options ServerOptions) (chan int, error) {
logDir := filepath.Dir(ServerLogFile)
_, err := os.Stat(logDir)
if errors.Is(err, os.ErrNotExist) {
if err := os.MkdirAll(logDir, 0o755); err != nil {
return nil, fmt.Errorf("create ollama server log dir %s: %v", logDir, err)
}
}
done := make(chan int)
go func() {
// Keep the server running unless we're shuttind down the app
crashCount := 0
for {
slog.Info(fmt.Sprintf("starting server..."))
cmd, err := start(ctx, command, options)
if err != nil {
slog.Error(fmt.Sprintf("failed to start server %s", err))
}
cmd.Wait() //nolint:errcheck
var code int
if cmd.ProcessState != nil {
code = cmd.ProcessState.ExitCode()
}
select {
case <-ctx.Done():
slog.Info(fmt.Sprintf("server shutdown with exit code %d", code))
done <- code
return
default:
crashCount++
slog.Warn(fmt.Sprintf("server crash %d - exit code %d - respawning", crashCount, code))
time.Sleep(500 * time.Millisecond * time.Duration(crashCount))
break
}
}
}()
return done, nil
}
func isServerRunning(ctx context.Context) bool {
client, err := api.ClientFromEnvironment()
if err != nil {
slog.Info("unable to connect to server")
return false
}
err = client.Heartbeat(ctx)
if err != nil {
slog.Debug(fmt.Sprintf("heartbeat from server: %s", err))
slog.Info("unable to connect to server")
return false
}
return true
}

36
app/server_darwin.go Normal file
View File

@@ -0,0 +1,36 @@
package main
import (
"context"
"errors"
"fmt"
"os"
"os/exec"
"syscall"
)
func getCmd(ctx context.Context, cmd string) *exec.Cmd {
return exec.CommandContext(ctx, cmd, "serve")
}
func terminate(cmd *exec.Cmd) error {
return cmd.Process.Signal(os.Interrupt)
}
func isProcessExited(pid int) (bool, error) {
proc, err := os.FindProcess(pid)
if err != nil {
return false, fmt.Errorf("failed to find process: %v", err)
}
err = proc.Signal(syscall.Signal(0))
if err != nil {
if errors.Is(err, os.ErrProcessDone) || errors.Is(err, syscall.ESRCH) {
return true, nil
}
return false, fmt.Errorf("error signaling process: %v", err)
}
return false, nil
}

89
app/server_windows.go Normal file
View File

@@ -0,0 +1,89 @@
package main
import (
"context"
"fmt"
"os/exec"
"syscall"
"golang.org/x/sys/windows"
)
func getCmd(ctx context.Context, exePath string) *exec.Cmd {
cmd := exec.CommandContext(ctx, exePath, "serve")
cmd.SysProcAttr = &syscall.SysProcAttr{
HideWindow: true,
CreationFlags: windows.CREATE_NEW_PROCESS_GROUP,
}
return cmd
}
func terminate(cmd *exec.Cmd) error {
dll, err := windows.LoadDLL("kernel32.dll")
if err != nil {
return err
}
defer dll.Release() // nolint: errcheck
pid := cmd.Process.Pid
f, err := dll.FindProc("AttachConsole")
if err != nil {
return err
}
r1, _, err := f.Call(uintptr(pid))
if r1 == 0 && err != syscall.ERROR_ACCESS_DENIED {
return err
}
f, err = dll.FindProc("SetConsoleCtrlHandler")
if err != nil {
return err
}
r1, _, err = f.Call(0, 1)
if r1 == 0 {
return err
}
f, err = dll.FindProc("GenerateConsoleCtrlEvent")
if err != nil {
return err
}
r1, _, err = f.Call(windows.CTRL_BREAK_EVENT, uintptr(pid))
if r1 == 0 {
return err
}
r1, _, err = f.Call(windows.CTRL_C_EVENT, uintptr(pid))
if r1 == 0 {
return err
}
return nil
}
const STILL_ACTIVE = 259
func isProcessExited(pid int) (bool, error) {
hProcess, err := windows.OpenProcess(windows.PROCESS_QUERY_INFORMATION, false, uint32(pid))
if err != nil {
return false, fmt.Errorf("failed to open process: %v", err)
}
defer windows.CloseHandle(hProcess) // nolint: errcheck
var exitCode uint32
err = windows.GetExitCodeProcess(hProcess, &exitCode)
if err != nil {
return false, fmt.Errorf("failed to get exit code: %v", err)
}
if exitCode == STILL_ACTIVE {
return false, nil
}
return true, nil
}

View File

@@ -1,34 +0,0 @@
@tailwind base;
@tailwind components;
@tailwind utilities;
html,
body {
background: transparent;
}
.drag {
-webkit-app-region: drag;
}
.no-drag {
-webkit-app-region: no-drag;
}
.blink {
-webkit-animation: 1s blink step-end infinite;
-moz-animation: 1s blink step-end infinite;
-ms-animation: 1s blink step-end infinite;
-o-animation: 1s blink step-end infinite;
animation: 1s blink step-end infinite;
}
@keyframes blink {
from,
to {
color: transparent;
}
50% {
color: black;
}
}

View File

@@ -1,122 +0,0 @@
import { useState } from 'react'
import copy from 'copy-to-clipboard'
import { CheckIcon, DocumentDuplicateIcon } from '@heroicons/react/24/outline'
import Store from 'electron-store'
import { getCurrentWindow, app } from '@electron/remote'
import { install } from './install'
import OllamaIcon from './ollama.svg'
const store = new Store()
enum Step {
WELCOME = 0,
CLI,
FINISH,
}
export default function () {
const [step, setStep] = useState<Step>(Step.WELCOME)
const [commandCopied, setCommandCopied] = useState<boolean>(false)
const command = 'ollama run llama2'
return (
<div className='drag'>
<div className='mx-auto flex min-h-screen w-full flex-col justify-between bg-white px-4 pt-16'>
{step === Step.WELCOME && (
<>
<div className='mx-auto text-center'>
<h1 className='mb-6 mt-4 text-2xl tracking-tight text-gray-900'>Welcome to Ollama</h1>
<p className='mx-auto w-[65%] text-sm text-gray-400'>
Let's get you up and running with your own large language models.
</p>
<button
onClick={() => setStep(Step.CLI)}
className='no-drag rounded-dm mx-auto my-8 w-[40%] rounded-md bg-black px-4 py-2 text-sm text-white hover:brightness-110'
>
Next
</button>
</div>
<div className='mx-auto'>
<OllamaIcon />
</div>
</>
)}
{step === Step.CLI && (
<>
<div className='mx-auto flex flex-col space-y-28 text-center'>
<h1 className='mt-4 text-2xl tracking-tight text-gray-900'>Install the command line</h1>
<pre className='mx-auto text-4xl text-gray-400'>&gt; ollama</pre>
<div className='mx-auto'>
<button
onClick={async () => {
try {
await install()
setStep(Step.FINISH)
} catch (e) {
console.error('could not install: ', e)
} finally {
getCurrentWindow().show()
getCurrentWindow().focus()
}
}}
className='no-drag rounded-dm mx-auto w-[60%] rounded-md bg-black px-4 py-2 text-sm text-white hover:brightness-110'
>
Install
</button>
<p className='mx-auto my-4 w-[70%] text-xs text-gray-400'>
You will be prompted for administrator access
</p>
</div>
</div>
</>
)}
{step === Step.FINISH && (
<>
<div className='mx-auto flex flex-col space-y-20 text-center'>
<h1 className='mt-4 text-2xl tracking-tight text-gray-900'>Run your first model</h1>
<div className='flex flex-col'>
<div className='group relative flex items-center'>
<pre className='language-none text-2xs w-full rounded-md bg-gray-100 px-4 py-3 text-start leading-normal'>
{command}
</pre>
<button
className={`no-drag absolute right-[5px] px-2 py-2 ${
commandCopied
? 'text-gray-900 opacity-100 hover:cursor-auto'
: 'text-gray-200 opacity-50 hover:cursor-pointer'
} hover:font-bold hover:text-gray-900 group-hover:opacity-100`}
onClick={() => {
copy(command)
setCommandCopied(true)
setTimeout(() => setCommandCopied(false), 3000)
}}
>
{commandCopied ? (
<CheckIcon className='h-4 w-4 font-bold text-gray-500' />
) : (
<DocumentDuplicateIcon className='h-4 w-4 text-gray-500' />
)}
</button>
</div>
<p className='mx-auto my-4 w-[70%] text-xs text-gray-400'>
Run this command in your favorite terminal.
</p>
</div>
<button
onClick={() => {
store.set('first-time-run', true)
window.close()
}}
className='no-drag rounded-dm mx-auto w-[60%] rounded-md bg-black px-4 py-2 text-sm text-white hover:brightness-110'
>
Finish
</button>
</div>
</>
)}
</div>
</div>
)
}

View File

@@ -1,4 +0,0 @@
declare module '*.svg' {
const content: string
export default content
}

View File

@@ -1,9 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8" />
</head>
<body>
<div id="app"></div>
</body>
</html>

View File

@@ -1,302 +0,0 @@
import { spawn, ChildProcess } from 'child_process'
import { app, autoUpdater, dialog, Tray, Menu, BrowserWindow, MenuItemConstructorOptions, nativeTheme } from 'electron'
import Store from 'electron-store'
import winston from 'winston'
import 'winston-daily-rotate-file'
import * as path from 'path'
import { v4 as uuidv4 } from 'uuid'
import { installed } from './install'
require('@electron/remote/main').initialize()
if (require('electron-squirrel-startup')) {
app.quit()
}
const store = new Store()
let welcomeWindow: BrowserWindow | null = null
declare const MAIN_WINDOW_WEBPACK_ENTRY: string
const logger = winston.createLogger({
transports: [
new winston.transports.Console(),
new winston.transports.File({
filename: path.join(app.getPath('home'), '.ollama', 'logs', 'server.log'),
maxsize: 1024 * 1024 * 20,
maxFiles: 5,
}),
],
format: winston.format.printf(info => info.message),
})
app.on('ready', () => {
const gotTheLock = app.requestSingleInstanceLock()
if (!gotTheLock) {
app.exit(0)
return
}
app.on('second-instance', () => {
if (app.hasSingleInstanceLock()) {
app.releaseSingleInstanceLock()
}
if (proc) {
proc.off('exit', restart)
proc.kill()
}
app.exit(0)
})
app.focus({ steal: true })
init()
})
function firstRunWindow() {
// Create the browser window.
welcomeWindow = new BrowserWindow({
width: 400,
height: 500,
frame: false,
fullscreenable: false,
resizable: false,
movable: true,
show: false,
webPreferences: {
nodeIntegration: true,
contextIsolation: false,
},
})
require('@electron/remote/main').enable(welcomeWindow.webContents)
welcomeWindow.loadURL(MAIN_WINDOW_WEBPACK_ENTRY)
welcomeWindow.on('ready-to-show', () => welcomeWindow.show())
welcomeWindow.on('closed', () => {
if (process.platform === 'darwin') {
app.dock.hide()
}
})
}
let tray: Tray | null = null
let updateAvailable = false
const assetPath = app.isPackaged ? process.resourcesPath : path.join(__dirname, '..', '..', 'assets')
function trayIconPath() {
return nativeTheme.shouldUseDarkColors
? updateAvailable
? path.join(assetPath, 'iconDarkUpdateTemplate.png')
: path.join(assetPath, 'iconDarkTemplate.png')
: updateAvailable
? path.join(assetPath, 'iconUpdateTemplate.png')
: path.join(assetPath, 'iconTemplate.png')
}
function updateTrayIcon() {
if (tray) {
tray.setImage(trayIconPath())
}
}
function updateTray() {
const updateItems: MenuItemConstructorOptions[] = [
{ label: 'An update is available', enabled: false },
{
label: 'Restart to update',
click: () => autoUpdater.quitAndInstall(),
},
{ type: 'separator' },
]
const menu = Menu.buildFromTemplate([
...(updateAvailable ? updateItems : []),
{ role: 'quit', label: 'Quit Ollama', accelerator: 'Command+Q' },
])
if (!tray) {
tray = new Tray(trayIconPath())
}
tray.setToolTip(updateAvailable ? 'An update is available' : 'Ollama')
tray.setContextMenu(menu)
tray.setImage(trayIconPath())
nativeTheme.off('updated', updateTrayIcon)
nativeTheme.on('updated', updateTrayIcon)
}
let proc: ChildProcess = null
function server() {
const binary = app.isPackaged
? path.join(process.resourcesPath, 'ollama')
: path.resolve(process.cwd(), '..', 'ollama')
proc = spawn(binary, ['serve'])
proc.stdout.on('data', data => {
logger.info(data.toString().trim())
})
proc.stderr.on('data', data => {
logger.error(data.toString().trim())
})
proc.on('exit', restart)
}
function restart() {
setTimeout(server, 1000)
}
app.on('before-quit', () => {
if (proc) {
proc.off('exit', restart)
proc.kill('SIGINT') // send SIGINT signal to the server, which also stops any loaded llms
}
})
const updateURL = `https://ollama.ai/api/update?os=${process.platform}&arch=${
process.arch
}&version=${app.getVersion()}&id=${id()}`
let latest = ''
async function isNewReleaseAvailable() {
try {
const response = await fetch(updateURL)
if (!response.ok) {
return false
}
if (response.status === 204) {
return false
}
const data = await response.json()
const url = data?.url
if (!url) {
return false
}
if (latest === url) {
return false
}
latest = url
return true
} catch (error) {
logger.error(`update check failed - ${error}`)
return false
}
}
async function checkUpdate() {
const available = await isNewReleaseAvailable()
if (available) {
logger.info('checking for update')
autoUpdater.checkForUpdates()
}
}
function init() {
if (app.isPackaged) {
checkUpdate()
setInterval(() => {
checkUpdate()
}, 60 * 60 * 1000)
}
updateTray()
if (process.platform === 'darwin') {
if (app.isPackaged) {
if (!app.isInApplicationsFolder()) {
const chosen = dialog.showMessageBoxSync({
type: 'question',
buttons: ['Move to Applications', 'Do Not Move'],
message: 'Ollama works best when run from the Applications directory.',
defaultId: 0,
cancelId: 1,
})
if (chosen === 0) {
try {
app.moveToApplicationsFolder({
conflictHandler: conflictType => {
if (conflictType === 'existsAndRunning') {
dialog.showMessageBoxSync({
type: 'info',
message: 'Cannot move to Applications directory',
detail:
'Another version of Ollama is currently running from your Applications directory. Close it first and try again.',
})
}
return true
},
})
return
} catch (e) {
logger.error(`[Move to Applications] Failed to move to applications folder - ${e.message}}`)
}
}
}
}
}
server()
if (store.get('first-time-run') && installed()) {
if (process.platform === 'darwin') {
app.dock.hide()
}
app.setLoginItemSettings({ openAtLogin: app.getLoginItemSettings().openAtLogin })
return
}
// This is the first run or the CLI is no longer installed
app.setLoginItemSettings({ openAtLogin: true })
firstRunWindow()
}
// Quit when all windows are closed, except on macOS. There, it's common
// for applications and their menu bar to stay active until the user quits
// explicitly with Cmd + Q.
app.on('window-all-closed', () => {
if (process.platform !== 'darwin') {
app.quit()
}
})
function id(): string {
const id = store.get('id') as string
if (id) {
return id
}
const uuid = uuidv4()
store.set('id', uuid)
return uuid
}
autoUpdater.setFeedURL({ url: updateURL })
autoUpdater.on('error', e => {
logger.error(`update check failed - ${e.message}`)
console.error(`update check failed - ${e.message}`)
})
autoUpdater.on('update-downloaded', () => {
updateAvailable = true
updateTray()
})

View File

@@ -1,21 +0,0 @@
import * as fs from 'fs'
import { exec as cbExec } from 'child_process'
import * as path from 'path'
import { promisify } from 'util'
const app = process && process.type === 'renderer' ? require('@electron/remote').app : require('electron').app
const ollama = app.isPackaged ? path.join(process.resourcesPath, 'ollama') : path.resolve(process.cwd(), '..', 'ollama')
const exec = promisify(cbExec)
const symlinkPath = '/usr/local/bin/ollama'
export function installed() {
return fs.existsSync(symlinkPath) && fs.readlinkSync(symlinkPath) === ollama
}
export async function install() {
const command = `do shell script "mkdir -p ${path.dirname(
symlinkPath
)} && ln -F -s \\"${ollama}\\" \\"${symlinkPath}\\"" with administrator privileges`
await exec(`osascript -e '${command}'`)
}

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 17 KiB

View File

View File

@@ -1,7 +0,0 @@
import App from './app'
import './app.css'
import { createRoot } from 'react-dom/client'
const container = document.getElementById('app')
const root = createRoot(container)
root.render(<App />)

98
app/store/store.go Normal file
View File

@@ -0,0 +1,98 @@
package store
import (
"encoding/json"
"errors"
"fmt"
"log/slog"
"os"
"path/filepath"
"sync"
"github.com/google/uuid"
)
type Store struct {
ID string `json:"id"`
FirstTimeRun bool `json:"first-time-run"`
}
var (
lock sync.Mutex
store Store
)
func GetID() string {
lock.Lock()
defer lock.Unlock()
if store.ID == "" {
initStore()
}
return store.ID
}
func GetFirstTimeRun() bool {
lock.Lock()
defer lock.Unlock()
if store.ID == "" {
initStore()
}
return store.FirstTimeRun
}
func SetFirstTimeRun(val bool) {
lock.Lock()
defer lock.Unlock()
if store.FirstTimeRun == val {
return
}
store.FirstTimeRun = val
writeStore(getStorePath())
}
// lock must be held
func initStore() {
storeFile, err := os.Open(getStorePath())
if err == nil {
defer storeFile.Close()
err = json.NewDecoder(storeFile).Decode(&store)
if err == nil {
slog.Debug(fmt.Sprintf("loaded existing store %s - ID: %s", getStorePath(), store.ID))
return
}
} else if !errors.Is(err, os.ErrNotExist) {
slog.Debug(fmt.Sprintf("unexpected error searching for store: %s", err))
}
slog.Debug("initializing new store")
store.ID = uuid.New().String()
writeStore(getStorePath())
}
func writeStore(storeFilename string) {
ollamaDir := filepath.Dir(storeFilename)
_, err := os.Stat(ollamaDir)
if errors.Is(err, os.ErrNotExist) {
if err := os.MkdirAll(ollamaDir, 0o755); err != nil {
slog.Error(fmt.Sprintf("create ollama dir %s: %v", ollamaDir, err))
return
}
}
payload, err := json.Marshal(store)
if err != nil {
slog.Error(fmt.Sprintf("failed to marshal store: %s", err))
return
}
fp, err := os.OpenFile(storeFilename, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0o755)
if err != nil {
slog.Error(fmt.Sprintf("write store payload %s: %v", storeFilename, err))
return
}
defer fp.Close()
if n, err := fp.Write(payload); err != nil || n != len(payload) {
slog.Error(fmt.Sprintf("write store payload %s: %d vs %d -- %v", storeFilename, n, len(payload), err))
return
}
slog.Debug("Store contents: " + string(payload))
slog.Info(fmt.Sprintf("wrote store: %s", storeFilename))
}

13
app/store/store_darwin.go Normal file
View File

@@ -0,0 +1,13 @@
package store
import (
"os"
"path/filepath"
)
func getStorePath() string {
// TODO - system wide location?
home := os.Getenv("HOME")
return filepath.Join(home, "Library", "Application Support", "Ollama", "config.json")
}

16
app/store/store_linux.go Normal file
View File

@@ -0,0 +1,16 @@
package store
import (
"os"
"path/filepath"
)
func getStorePath() string {
if os.Geteuid() == 0 {
// TODO where should we store this on linux for system-wide operation?
return "/etc/ollama/config.json"
}
home := os.Getenv("HOME")
return filepath.Join(home, ".ollama", "config.json")
}

View File

@@ -0,0 +1,11 @@
package store
import (
"os"
"path/filepath"
)
func getStorePath() string {
localAppData := os.Getenv("LOCALAPPDATA")
return filepath.Join(localAppData, "Ollama", "config.json")
}

View File

@@ -1,6 +0,0 @@
/** @type {import('tailwindcss').Config} */
module.exports = {
content: ['./src/**/*.{js,ts,jsx,tsx,mdx}'],
theme: {},
plugins: [],
}

View File

@@ -0,0 +1,24 @@
package commontray
var (
Title = "Ollama"
ToolTip = "Ollama"
UpdateIconName = "tray_upgrade"
IconName = "tray"
)
type Callbacks struct {
Quit chan struct{}
Update chan struct{}
DoFirstUse chan struct{}
ShowLogs chan struct{}
}
type OllamaTray interface {
GetCallbacks() Callbacks
Run()
UpdateAvailable(ver string) error
DisplayFirstUseNotification() error
Quit()
}

28
app/tray/tray.go Normal file
View File

@@ -0,0 +1,28 @@
package tray
import (
"fmt"
"runtime"
"github.com/ollama/ollama/app/assets"
"github.com/ollama/ollama/app/tray/commontray"
)
func NewTray() (commontray.OllamaTray, error) {
extension := ".png"
if runtime.GOOS == "windows" {
extension = ".ico"
}
iconName := commontray.UpdateIconName + extension
updateIcon, err := assets.GetIcon(iconName)
if err != nil {
return nil, fmt.Errorf("failed to load icon %s: %w", iconName, err)
}
iconName = commontray.IconName + extension
icon, err := assets.GetIcon(iconName)
if err != nil {
return nil, fmt.Errorf("failed to load icon %s: %w", iconName, err)
}
return InitPlatformTray(icon, updateIcon)
}

11
app/tray/tray_darwin.go Normal file
View File

@@ -0,0 +1,11 @@
package tray
import (
"fmt"
"github.com/ollama/ollama/app/tray/commontray"
)
func InitPlatformTray(icon, updateIcon []byte) (commontray.OllamaTray, error) {
return nil, fmt.Errorf("NOT IMPLEMENTED YET")
}

10
app/tray/tray_windows.go Normal file
View File

@@ -0,0 +1,10 @@
package tray
import (
"github.com/ollama/ollama/app/tray/commontray"
"github.com/ollama/ollama/app/tray/wintray"
)
func InitPlatformTray(icon, updateIcon []byte) (commontray.OllamaTray, error) {
return wintray.InitTray(icon, updateIcon)
}

View File

@@ -0,0 +1,184 @@
//go:build windows
package wintray
import (
"fmt"
"log/slog"
"sync"
"unsafe"
"golang.org/x/sys/windows"
)
var (
quitOnce sync.Once
)
func (t *winTray) Run() {
nativeLoop()
}
func nativeLoop() {
// Main message pump.
slog.Debug("starting event handling loop")
m := &struct {
WindowHandle windows.Handle
Message uint32
Wparam uintptr
Lparam uintptr
Time uint32
Pt point
LPrivate uint32
}{}
for {
ret, _, err := pGetMessage.Call(uintptr(unsafe.Pointer(m)), 0, 0, 0)
// If the function retrieves a message other than WM_QUIT, the return value is nonzero.
// If the function retrieves the WM_QUIT message, the return value is zero.
// If there is an error, the return value is -1
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms644936(v=vs.85).aspx
switch int32(ret) {
case -1:
slog.Error(fmt.Sprintf("get message failure: %v", err))
return
case 0:
return
default:
pTranslateMessage.Call(uintptr(unsafe.Pointer(m))) //nolint:errcheck
pDispatchMessage.Call(uintptr(unsafe.Pointer(m))) //nolint:errcheck
}
}
}
// WindowProc callback function that processes messages sent to a window.
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms633573(v=vs.85).aspx
func (t *winTray) wndProc(hWnd windows.Handle, message uint32, wParam, lParam uintptr) (lResult uintptr) {
const (
WM_RBUTTONUP = 0x0205
WM_LBUTTONUP = 0x0202
WM_COMMAND = 0x0111
WM_ENDSESSION = 0x0016
WM_CLOSE = 0x0010
WM_DESTROY = 0x0002
WM_MOUSEMOVE = 0x0200
WM_LBUTTONDOWN = 0x0201
)
switch message {
case WM_COMMAND:
menuItemId := int32(wParam)
// https://docs.microsoft.com/en-us/windows/win32/menurc/wm-command#menus
switch menuItemId {
case quitMenuID:
select {
case t.callbacks.Quit <- struct{}{}:
// should not happen but in case not listening
default:
slog.Error("no listener on Quit")
}
case updateMenuID:
select {
case t.callbacks.Update <- struct{}{}:
// should not happen but in case not listening
default:
slog.Error("no listener on Update")
}
case diagLogsMenuID:
select {
case t.callbacks.ShowLogs <- struct{}{}:
// should not happen but in case not listening
default:
slog.Error("no listener on ShowLogs")
}
default:
slog.Debug(fmt.Sprintf("Unexpected menu item id: %d", menuItemId))
}
case WM_CLOSE:
boolRet, _, err := pDestroyWindow.Call(uintptr(t.window))
if boolRet == 0 {
slog.Error(fmt.Sprintf("failed to destroy window: %s", err))
}
err = t.wcex.unregister()
if err != nil {
slog.Error(fmt.Sprintf("failed to uregister windo %s", err))
}
case WM_DESTROY:
// same as WM_ENDSESSION, but throws 0 exit code after all
defer pPostQuitMessage.Call(uintptr(int32(0))) //nolint:errcheck
fallthrough
case WM_ENDSESSION:
t.muNID.Lock()
if t.nid != nil {
err := t.nid.delete()
if err != nil {
slog.Error(fmt.Sprintf("failed to delete nid: %s", err))
}
}
t.muNID.Unlock()
case t.wmSystrayMessage:
switch lParam {
case WM_MOUSEMOVE, WM_LBUTTONDOWN:
// Ignore these...
case WM_RBUTTONUP, WM_LBUTTONUP:
err := t.showMenu()
if err != nil {
slog.Error(fmt.Sprintf("failed to show menu: %s", err))
}
case 0x405: // TODO - how is this magic value derived for the notification left click
if t.pendingUpdate {
select {
case t.callbacks.Update <- struct{}{}:
// should not happen but in case not listening
default:
slog.Error("no listener on Update")
}
} else {
select {
case t.callbacks.DoFirstUse <- struct{}{}:
// should not happen but in case not listening
default:
slog.Error("no listener on DoFirstUse")
}
}
case 0x404: // Middle click or close notification
// slog.Debug("doing nothing on close of first time notification")
default:
// 0x402 also seems common - what is it?
slog.Debug(fmt.Sprintf("unmanaged app message, lParm: 0x%x", lParam))
}
case t.wmTaskbarCreated: // on explorer.exe restarts
t.muNID.Lock()
err := t.nid.add()
if err != nil {
slog.Error(fmt.Sprintf("failed to refresh the taskbar on explorer restart: %s", err))
}
t.muNID.Unlock()
default:
// Calls the default window procedure to provide default processing for any window messages that an application does not process.
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms633572(v=vs.85).aspx
lResult, _, _ = pDefWindowProc.Call(
uintptr(hWnd),
uintptr(message),
uintptr(wParam),
uintptr(lParam),
)
}
return
}
func (t *winTray) Quit() {
quitOnce.Do(quit)
}
func quit() {
boolRet, _, err := pPostMessage.Call(
uintptr(wt.window),
WM_CLOSE,
0,
0,
)
if boolRet == 0 {
slog.Error(fmt.Sprintf("failed to post close message on shutdown %s", err))
}
}

71
app/tray/wintray/menus.go Normal file
View File

@@ -0,0 +1,71 @@
//go:build windows
package wintray
import (
"fmt"
"log/slog"
"unsafe"
"golang.org/x/sys/windows"
)
const (
updatAvailableMenuID = 1
updateMenuID = updatAvailableMenuID + 1
separatorMenuID = updateMenuID + 1
diagLogsMenuID = separatorMenuID + 1
diagSeparatorMenuID = diagLogsMenuID + 1
quitMenuID = diagSeparatorMenuID + 1
)
func (t *winTray) initMenus() error {
if err := t.addOrUpdateMenuItem(diagLogsMenuID, 0, diagLogsMenuTitle, false); err != nil {
return fmt.Errorf("unable to create menu entries %w\n", err)
}
if err := t.addSeparatorMenuItem(diagSeparatorMenuID, 0); err != nil {
return fmt.Errorf("unable to create menu entries %w", err)
}
if err := t.addOrUpdateMenuItem(quitMenuID, 0, quitMenuTitle, false); err != nil {
return fmt.Errorf("unable to create menu entries %w\n", err)
}
return nil
}
func (t *winTray) UpdateAvailable(ver string) error {
if !t.updateNotified {
slog.Debug("updating menu and sending notification for new update")
if err := t.addOrUpdateMenuItem(updatAvailableMenuID, 0, updateAvailableMenuTitle, true); err != nil {
return fmt.Errorf("unable to create menu entries %w", err)
}
if err := t.addOrUpdateMenuItem(updateMenuID, 0, updateMenutTitle, false); err != nil {
return fmt.Errorf("unable to create menu entries %w", err)
}
if err := t.addSeparatorMenuItem(separatorMenuID, 0); err != nil {
return fmt.Errorf("unable to create menu entries %w", err)
}
iconFilePath, err := iconBytesToFilePath(wt.updateIcon)
if err != nil {
return fmt.Errorf("unable to write icon data to temp file: %w", err)
}
if err := wt.setIcon(iconFilePath); err != nil {
return fmt.Errorf("unable to set icon: %w", err)
}
t.updateNotified = true
t.pendingUpdate = true
// Now pop up the notification
t.muNID.Lock()
defer t.muNID.Unlock()
copy(t.nid.InfoTitle[:], windows.StringToUTF16(updateTitle))
copy(t.nid.Info[:], windows.StringToUTF16(fmt.Sprintf(updateMessage, ver)))
t.nid.Flags |= NIF_INFO
t.nid.Timeout = 10
t.nid.Size = uint32(unsafe.Sizeof(*wt.nid))
err = t.nid.modify()
if err != nil {
return err
}
}
return nil
}

View File

@@ -0,0 +1,15 @@
//go:build windows
package wintray
const (
firstTimeTitle = "Ollama is running"
firstTimeMessage = "Click here to get started"
updateTitle = "Update available"
updateMessage = "Ollama version %s is ready to install"
quitMenuTitle = "Quit Ollama"
updateAvailableMenuTitle = "An update is available"
updateMenutTitle = "Restart to update"
diagLogsMenuTitle = "View logs"
)

View File

@@ -0,0 +1,66 @@
//go:build windows
package wintray
import (
"unsafe"
"golang.org/x/sys/windows"
)
// Contains information that the system needs to display notifications in the notification area.
// Used by Shell_NotifyIcon.
// https://msdn.microsoft.com/en-us/library/windows/desktop/bb773352(v=vs.85).aspx
// https://msdn.microsoft.com/en-us/library/windows/desktop/bb762159
type notifyIconData struct {
Size uint32
Wnd windows.Handle
ID, Flags, CallbackMessage uint32
Icon windows.Handle
Tip [128]uint16
State, StateMask uint32
Info [256]uint16
// Timeout, Version uint32
Timeout uint32
InfoTitle [64]uint16
InfoFlags uint32
GuidItem windows.GUID
BalloonIcon windows.Handle
}
func (nid *notifyIconData) add() error {
const NIM_ADD = 0x00000000
res, _, err := pShellNotifyIcon.Call(
uintptr(NIM_ADD),
uintptr(unsafe.Pointer(nid)),
)
if res == 0 {
return err
}
return nil
}
func (nid *notifyIconData) modify() error {
const NIM_MODIFY = 0x00000001
res, _, err := pShellNotifyIcon.Call(
uintptr(NIM_MODIFY),
uintptr(unsafe.Pointer(nid)),
)
if res == 0 {
return err
}
return nil
}
func (nid *notifyIconData) delete() error {
const NIM_DELETE = 0x00000002
res, _, err := pShellNotifyIcon.Call(
uintptr(NIM_DELETE),
uintptr(unsafe.Pointer(nid)),
)
if res == 0 {
return err
}
return nil
}

485
app/tray/wintray/tray.go Normal file
View File

@@ -0,0 +1,485 @@
//go:build windows
package wintray
import (
"crypto/md5"
"encoding/hex"
"fmt"
"log/slog"
"os"
"path/filepath"
"sort"
"sync"
"unsafe"
"github.com/ollama/ollama/app/tray/commontray"
"golang.org/x/sys/windows"
)
// Helpful sources: https://github.com/golang/exp/blob/master/shiny/driver/internal/win32
// Contains information about loaded resources
type winTray struct {
instance,
icon,
cursor,
window windows.Handle
loadedImages map[string]windows.Handle
muLoadedImages sync.RWMutex
// menus keeps track of the submenus keyed by the menu item ID, plus 0
// which corresponds to the main popup menu.
menus map[uint32]windows.Handle
muMenus sync.RWMutex
menuOf map[uint32]windows.Handle
muMenuOf sync.RWMutex
// menuItemIcons maintains the bitmap of each menu item (if applies). It's
// needed to show the icon correctly when showing a previously hidden menu
// item again.
// menuItemIcons map[uint32]windows.Handle
// muMenuItemIcons sync.RWMutex
visibleItems map[uint32][]uint32
muVisibleItems sync.RWMutex
nid *notifyIconData
muNID sync.RWMutex
wcex *wndClassEx
wmSystrayMessage,
wmTaskbarCreated uint32
pendingUpdate bool
updateNotified bool // Only pop up the notification once - TODO consider daily nag?
// Callbacks
callbacks commontray.Callbacks
normalIcon []byte
updateIcon []byte
}
var wt winTray
func (t *winTray) GetCallbacks() commontray.Callbacks {
return t.callbacks
}
func InitTray(icon, updateIcon []byte) (*winTray, error) {
wt.callbacks.Quit = make(chan struct{})
wt.callbacks.Update = make(chan struct{})
wt.callbacks.ShowLogs = make(chan struct{})
wt.callbacks.DoFirstUse = make(chan struct{})
wt.normalIcon = icon
wt.updateIcon = updateIcon
if err := wt.initInstance(); err != nil {
return nil, fmt.Errorf("Unable to init instance: %w\n", err)
}
if err := wt.createMenu(); err != nil {
return nil, fmt.Errorf("Unable to create menu: %w\n", err)
}
iconFilePath, err := iconBytesToFilePath(wt.normalIcon)
if err != nil {
return nil, fmt.Errorf("Unable to write icon data to temp file: %w", err)
}
if err := wt.setIcon(iconFilePath); err != nil {
return nil, fmt.Errorf("Unable to set icon: %w", err)
}
return &wt, wt.initMenus()
}
func (t *winTray) initInstance() error {
const (
className = "OllamaClass"
windowName = ""
)
t.wmSystrayMessage = WM_USER + 1
t.visibleItems = make(map[uint32][]uint32)
t.menus = make(map[uint32]windows.Handle)
t.menuOf = make(map[uint32]windows.Handle)
t.loadedImages = make(map[string]windows.Handle)
taskbarEventNamePtr, _ := windows.UTF16PtrFromString("TaskbarCreated")
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms644947
res, _, err := pRegisterWindowMessage.Call(
uintptr(unsafe.Pointer(taskbarEventNamePtr)),
)
if res == 0 { // success 0xc000-0xfff
return fmt.Errorf("failed to register window: %w", err)
}
t.wmTaskbarCreated = uint32(res)
instanceHandle, _, err := pGetModuleHandle.Call(0)
if instanceHandle == 0 {
return err
}
t.instance = windows.Handle(instanceHandle)
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms648072(v=vs.85).aspx
iconHandle, _, err := pLoadIcon.Call(0, uintptr(IDI_APPLICATION))
if iconHandle == 0 {
return err
}
t.icon = windows.Handle(iconHandle)
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms648391(v=vs.85).aspx
cursorHandle, _, err := pLoadCursor.Call(0, uintptr(IDC_ARROW))
if cursorHandle == 0 {
return err
}
t.cursor = windows.Handle(cursorHandle)
classNamePtr, err := windows.UTF16PtrFromString(className)
if err != nil {
return err
}
windowNamePtr, err := windows.UTF16PtrFromString(windowName)
if err != nil {
return err
}
t.wcex = &wndClassEx{
Style: CS_HREDRAW | CS_VREDRAW,
WndProc: windows.NewCallback(t.wndProc),
Instance: t.instance,
Icon: t.icon,
Cursor: t.cursor,
Background: windows.Handle(6), // (COLOR_WINDOW + 1)
ClassName: classNamePtr,
IconSm: t.icon,
}
if err := t.wcex.register(); err != nil {
return err
}
windowHandle, _, err := pCreateWindowEx.Call(
uintptr(0),
uintptr(unsafe.Pointer(classNamePtr)),
uintptr(unsafe.Pointer(windowNamePtr)),
uintptr(WS_OVERLAPPEDWINDOW),
uintptr(CW_USEDEFAULT),
uintptr(CW_USEDEFAULT),
uintptr(CW_USEDEFAULT),
uintptr(CW_USEDEFAULT),
uintptr(0),
uintptr(0),
uintptr(t.instance),
uintptr(0),
)
if windowHandle == 0 {
return err
}
t.window = windows.Handle(windowHandle)
pShowWindow.Call(uintptr(t.window), uintptr(SW_HIDE)) //nolint:errcheck
boolRet, _, err := pUpdateWindow.Call(uintptr(t.window))
if boolRet == 0 {
slog.Error(fmt.Sprintf("failed to update window: %s", err))
}
t.muNID.Lock()
defer t.muNID.Unlock()
t.nid = &notifyIconData{
Wnd: windows.Handle(t.window),
ID: 100,
Flags: NIF_MESSAGE,
CallbackMessage: t.wmSystrayMessage,
}
t.nid.Size = uint32(unsafe.Sizeof(*t.nid))
return t.nid.add()
}
func (t *winTray) createMenu() error {
menuHandle, _, err := pCreatePopupMenu.Call()
if menuHandle == 0 {
return err
}
t.menus[0] = windows.Handle(menuHandle)
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms647575(v=vs.85).aspx
mi := struct {
Size, Mask, Style, Max uint32
Background windows.Handle
ContextHelpID uint32
MenuData uintptr
}{
Mask: MIM_APPLYTOSUBMENUS,
}
mi.Size = uint32(unsafe.Sizeof(mi))
res, _, err := pSetMenuInfo.Call(
uintptr(t.menus[0]),
uintptr(unsafe.Pointer(&mi)),
)
if res == 0 {
return err
}
return nil
}
// Contains information about a menu item.
// https://msdn.microsoft.com/en-us/library/windows/desktop/ms647578(v=vs.85).aspx
type menuItemInfo struct {
Size, Mask, Type, State uint32
ID uint32
SubMenu, Checked, Unchecked windows.Handle
ItemData uintptr
TypeData *uint16
Cch uint32
BMPItem windows.Handle
}
func (t *winTray) addOrUpdateMenuItem(menuItemId uint32, parentId uint32, title string, disabled bool) error {
titlePtr, err := windows.UTF16PtrFromString(title)
if err != nil {
return err
}
mi := menuItemInfo{
Mask: MIIM_FTYPE | MIIM_STRING | MIIM_ID | MIIM_STATE,
Type: MFT_STRING,
ID: uint32(menuItemId),
TypeData: titlePtr,
Cch: uint32(len(title)),
}
mi.Size = uint32(unsafe.Sizeof(mi))
if disabled {
mi.State |= MFS_DISABLED
}
var res uintptr
t.muMenus.RLock()
menu := t.menus[parentId]
t.muMenus.RUnlock()
if t.getVisibleItemIndex(parentId, menuItemId) != -1 {
// We set the menu item info based on the menuID
boolRet, _, err := pSetMenuItemInfo.Call(
uintptr(menu),
uintptr(menuItemId),
0,
uintptr(unsafe.Pointer(&mi)),
)
if boolRet == 0 {
return fmt.Errorf("failed to set menu item: %w", err)
}
}
if res == 0 {
// Menu item does not already exist, create it
t.muMenus.RLock()
submenu, exists := t.menus[menuItemId]
t.muMenus.RUnlock()
if exists {
mi.Mask |= MIIM_SUBMENU
mi.SubMenu = submenu
}
t.addToVisibleItems(parentId, menuItemId)
position := t.getVisibleItemIndex(parentId, menuItemId)
res, _, err = pInsertMenuItem.Call(
uintptr(menu),
uintptr(position),
1,
uintptr(unsafe.Pointer(&mi)),
)
if res == 0 {
t.delFromVisibleItems(parentId, menuItemId)
return err
}
t.muMenuOf.Lock()
t.menuOf[menuItemId] = menu
t.muMenuOf.Unlock()
}
return nil
}
func (t *winTray) addSeparatorMenuItem(menuItemId, parentId uint32) error {
mi := menuItemInfo{
Mask: MIIM_FTYPE | MIIM_ID | MIIM_STATE,
Type: MFT_SEPARATOR,
ID: uint32(menuItemId),
}
mi.Size = uint32(unsafe.Sizeof(mi))
t.addToVisibleItems(parentId, menuItemId)
position := t.getVisibleItemIndex(parentId, menuItemId)
t.muMenus.RLock()
menu := uintptr(t.menus[parentId])
t.muMenus.RUnlock()
res, _, err := pInsertMenuItem.Call(
menu,
uintptr(position),
1,
uintptr(unsafe.Pointer(&mi)),
)
if res == 0 {
return err
}
return nil
}
// func (t *winTray) hideMenuItem(menuItemId, parentId uint32) error {
// const ERROR_SUCCESS syscall.Errno = 0
// t.muMenus.RLock()
// menu := uintptr(t.menus[parentId])
// t.muMenus.RUnlock()
// res, _, err := pRemoveMenu.Call(
// menu,
// uintptr(menuItemId),
// MF_BYCOMMAND,
// )
// if res == 0 && err.(syscall.Errno) != ERROR_SUCCESS {
// return err
// }
// t.delFromVisibleItems(parentId, menuItemId)
// return nil
// }
func (t *winTray) showMenu() error {
p := point{}
boolRet, _, err := pGetCursorPos.Call(uintptr(unsafe.Pointer(&p)))
if boolRet == 0 {
return err
}
boolRet, _, err = pSetForegroundWindow.Call(uintptr(t.window))
if boolRet == 0 {
slog.Warn(fmt.Sprintf("failed to bring menu to foreground: %s", err))
}
boolRet, _, err = pTrackPopupMenu.Call(
uintptr(t.menus[0]),
TPM_BOTTOMALIGN|TPM_LEFTALIGN,
uintptr(p.X),
uintptr(p.Y),
0,
uintptr(t.window),
0,
)
if boolRet == 0 {
return err
}
return nil
}
func (t *winTray) delFromVisibleItems(parent, val uint32) {
t.muVisibleItems.Lock()
defer t.muVisibleItems.Unlock()
visibleItems := t.visibleItems[parent]
for i, itemval := range visibleItems {
if val == itemval {
t.visibleItems[parent] = append(visibleItems[:i], visibleItems[i+1:]...)
break
}
}
}
func (t *winTray) addToVisibleItems(parent, val uint32) {
t.muVisibleItems.Lock()
defer t.muVisibleItems.Unlock()
if visibleItems, exists := t.visibleItems[parent]; !exists {
t.visibleItems[parent] = []uint32{val}
} else {
newvisible := append(visibleItems, val)
sort.Slice(newvisible, func(i, j int) bool { return newvisible[i] < newvisible[j] })
t.visibleItems[parent] = newvisible
}
}
func (t *winTray) getVisibleItemIndex(parent, val uint32) int {
t.muVisibleItems.RLock()
defer t.muVisibleItems.RUnlock()
for i, itemval := range t.visibleItems[parent] {
if val == itemval {
return i
}
}
return -1
}
func iconBytesToFilePath(iconBytes []byte) (string, error) {
bh := md5.Sum(iconBytes)
dataHash := hex.EncodeToString(bh[:])
iconFilePath := filepath.Join(os.TempDir(), "ollama_temp_icon_"+dataHash)
if _, err := os.Stat(iconFilePath); os.IsNotExist(err) {
if err := os.WriteFile(iconFilePath, iconBytes, 0644); err != nil {
return "", err
}
}
return iconFilePath, nil
}
// Loads an image from file and shows it in tray.
// Shell_NotifyIcon: https://msdn.microsoft.com/en-us/library/windows/desktop/bb762159(v=vs.85).aspx
func (t *winTray) setIcon(src string) error {
h, err := t.loadIconFrom(src)
if err != nil {
return err
}
t.muNID.Lock()
defer t.muNID.Unlock()
t.nid.Icon = h
t.nid.Flags |= NIF_ICON
t.nid.Size = uint32(unsafe.Sizeof(*t.nid))
return t.nid.modify()
}
// Loads an image from file to be shown in tray or menu item.
// LoadImage: https://msdn.microsoft.com/en-us/library/windows/desktop/ms648045(v=vs.85).aspx
func (t *winTray) loadIconFrom(src string) (windows.Handle, error) {
// Save and reuse handles of loaded images
t.muLoadedImages.RLock()
h, ok := t.loadedImages[src]
t.muLoadedImages.RUnlock()
if !ok {
srcPtr, err := windows.UTF16PtrFromString(src)
if err != nil {
return 0, err
}
res, _, err := pLoadImage.Call(
0,
uintptr(unsafe.Pointer(srcPtr)),
IMAGE_ICON,
0,
0,
LR_LOADFROMFILE|LR_DEFAULTSIZE,
)
if res == 0 {
return 0, err
}
h = windows.Handle(res)
t.muLoadedImages.Lock()
t.loadedImages[src] = h
t.muLoadedImages.Unlock()
}
return h, nil
}
func (t *winTray) DisplayFirstUseNotification() error {
t.muNID.Lock()
defer t.muNID.Unlock()
copy(t.nid.InfoTitle[:], windows.StringToUTF16(firstTimeTitle))
copy(t.nid.Info[:], windows.StringToUTF16(firstTimeMessage))
t.nid.Flags |= NIF_INFO
t.nid.Size = uint32(unsafe.Sizeof(*wt.nid))
return t.nid.modify()
}

View File

@@ -0,0 +1,89 @@
//go:build windows
package wintray
import (
"runtime"
"golang.org/x/sys/windows"
)
var (
k32 = windows.NewLazySystemDLL("Kernel32.dll")
u32 = windows.NewLazySystemDLL("User32.dll")
s32 = windows.NewLazySystemDLL("Shell32.dll")
pCreatePopupMenu = u32.NewProc("CreatePopupMenu")
pCreateWindowEx = u32.NewProc("CreateWindowExW")
pDefWindowProc = u32.NewProc("DefWindowProcW")
pDestroyWindow = u32.NewProc("DestroyWindow")
pDispatchMessage = u32.NewProc("DispatchMessageW")
pGetCursorPos = u32.NewProc("GetCursorPos")
pGetMessage = u32.NewProc("GetMessageW")
pGetModuleHandle = k32.NewProc("GetModuleHandleW")
pInsertMenuItem = u32.NewProc("InsertMenuItemW")
pLoadCursor = u32.NewProc("LoadCursorW")
pLoadIcon = u32.NewProc("LoadIconW")
pLoadImage = u32.NewProc("LoadImageW")
pPostMessage = u32.NewProc("PostMessageW")
pPostQuitMessage = u32.NewProc("PostQuitMessage")
pRegisterClass = u32.NewProc("RegisterClassExW")
pRegisterWindowMessage = u32.NewProc("RegisterWindowMessageW")
pSetForegroundWindow = u32.NewProc("SetForegroundWindow")
pSetMenuInfo = u32.NewProc("SetMenuInfo")
pSetMenuItemInfo = u32.NewProc("SetMenuItemInfoW")
pShellNotifyIcon = s32.NewProc("Shell_NotifyIconW")
pShowWindow = u32.NewProc("ShowWindow")
pTrackPopupMenu = u32.NewProc("TrackPopupMenu")
pTranslateMessage = u32.NewProc("TranslateMessage")
pUnregisterClass = u32.NewProc("UnregisterClassW")
pUpdateWindow = u32.NewProc("UpdateWindow")
)
const (
CS_HREDRAW = 0x0002
CS_VREDRAW = 0x0001
CW_USEDEFAULT = 0x80000000
IDC_ARROW = 32512 // Standard arrow
IDI_APPLICATION = 32512
IMAGE_ICON = 1 // Loads an icon
LR_DEFAULTSIZE = 0x00000040 // Loads default-size icon for windows(SM_CXICON x SM_CYICON) if cx, cy are set to zero
LR_LOADFROMFILE = 0x00000010 // Loads the stand-alone image from the file
MF_BYCOMMAND = 0x00000000
MFS_DISABLED = 0x00000003
MFT_SEPARATOR = 0x00000800
MFT_STRING = 0x00000000
MIIM_BITMAP = 0x00000080
MIIM_FTYPE = 0x00000100
MIIM_ID = 0x00000002
MIIM_STATE = 0x00000001
MIIM_STRING = 0x00000040
MIIM_SUBMENU = 0x00000004
MIM_APPLYTOSUBMENUS = 0x80000000
NIF_ICON = 0x00000002
NIF_INFO = 0x00000010
NIF_MESSAGE = 0x00000001
SW_HIDE = 0
TPM_BOTTOMALIGN = 0x0020
TPM_LEFTALIGN = 0x0000
WM_CLOSE = 0x0010
WM_USER = 0x0400
WS_CAPTION = 0x00C00000
WS_MAXIMIZEBOX = 0x00010000
WS_MINIMIZEBOX = 0x00020000
WS_OVERLAPPED = 0x00000000
WS_OVERLAPPEDWINDOW = WS_OVERLAPPED | WS_CAPTION | WS_SYSMENU | WS_THICKFRAME | WS_MINIMIZEBOX | WS_MAXIMIZEBOX
WS_SYSMENU = 0x00080000
WS_THICKFRAME = 0x00040000
)
// Not sure if this is actually needed on windows
func init() {
runtime.LockOSThread()
}
// The POINT structure defines the x- and y- coordinates of a point.
// https://msdn.microsoft.com/en-us/library/windows/desktop/dd162805(v=vs.85).aspx
type point struct {
X, Y int32
}

View File

@@ -0,0 +1,45 @@
//go:build windows
package wintray
import (
"unsafe"
"golang.org/x/sys/windows"
)
// Contains window class information.
// It is used with the RegisterClassEx and GetClassInfoEx functions.
// https://msdn.microsoft.com/en-us/library/ms633577.aspx
type wndClassEx struct {
Size, Style uint32
WndProc uintptr
ClsExtra, WndExtra int32
Instance, Icon, Cursor, Background windows.Handle
MenuName, ClassName *uint16
IconSm windows.Handle
}
// Registers a window class for subsequent use in calls to the CreateWindow or CreateWindowEx function.
// https://msdn.microsoft.com/en-us/library/ms633587.aspx
func (w *wndClassEx) register() error {
w.Size = uint32(unsafe.Sizeof(*w))
res, _, err := pRegisterClass.Call(uintptr(unsafe.Pointer(w)))
if res == 0 {
return err
}
return nil
}
// Unregisters a window class, freeing the memory required for the class.
// https://msdn.microsoft.com/en-us/library/ms644899.aspx
func (w *wndClassEx) unregister() error {
res, _, err := pUnregisterClass.Call(
uintptr(unsafe.Pointer(w.ClassName)),
uintptr(w.Instance),
)
if res == 0 {
return err
}
return nil
}

View File

@@ -1,20 +0,0 @@
{
"compilerOptions": {
"target": "ES6",
"allowJs": true,
"module": "commonjs",
"skipLibCheck": true,
"esModuleInterop": true,
"noImplicitAny": true,
"sourceMap": true,
"baseUrl": ".",
"outDir": "dist",
"moduleResolution": "node",
"resolveJsonModule": true,
"paths": {
"*": ["node_modules/*"]
},
"jsx": "react-jsx"
},
"include": ["src/**/*"]
}

232
app/updater/updater.go Normal file
View File

@@ -0,0 +1,232 @@
package updater
import (
"context"
"crypto/rand"
"encoding/json"
"errors"
"fmt"
"io"
"log/slog"
"mime"
"net/http"
"net/url"
"os"
"path"
"path/filepath"
"runtime"
"strings"
"time"
"github.com/ollama/ollama/auth"
"github.com/ollama/ollama/version"
)
var (
UpdateStageDir string
)
var (
UpdateCheckURLBase = "https://ollama.com/api/update"
UpdateDownloaded = false
UpdateCheckInterval = 60 * 60 * time.Second
)
// TODO - maybe move up to the API package?
type UpdateResponse struct {
UpdateURL string `json:"url"`
UpdateVersion string `json:"version"`
}
func IsNewReleaseAvailable(ctx context.Context) (bool, UpdateResponse) {
var updateResp UpdateResponse
requestURL, err := url.Parse(UpdateCheckURLBase)
if err != nil {
return false, updateResp
}
query := requestURL.Query()
query.Add("os", runtime.GOOS)
query.Add("arch", runtime.GOARCH)
query.Add("version", version.Version)
query.Add("ts", fmt.Sprintf("%d", time.Now().Unix()))
nonce, err := auth.NewNonce(rand.Reader, 16)
if err != nil {
return false, updateResp
}
query.Add("nonce", nonce)
requestURL.RawQuery = query.Encode()
data := []byte(fmt.Sprintf("%s,%s", http.MethodGet, requestURL.RequestURI()))
signature, err := auth.Sign(ctx, data)
if err != nil {
return false, updateResp
}
req, err := http.NewRequestWithContext(ctx, http.MethodGet, requestURL.String(), nil)
if err != nil {
slog.Warn(fmt.Sprintf("failed to check for update: %s", err))
return false, updateResp
}
req.Header.Set("Authorization", signature)
req.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))
slog.Debug("checking for available update", "requestURL", requestURL)
resp, err := http.DefaultClient.Do(req)
if err != nil {
slog.Warn(fmt.Sprintf("failed to check for update: %s", err))
return false, updateResp
}
defer resp.Body.Close()
if resp.StatusCode == 204 {
slog.Debug("check update response 204 (current version is up to date)")
return false, updateResp
}
body, err := io.ReadAll(resp.Body)
if err != nil {
slog.Warn(fmt.Sprintf("failed to read body response: %s", err))
}
if resp.StatusCode != 200 {
slog.Info(fmt.Sprintf("check update error %d - %.96s", resp.StatusCode, string(body)))
return false, updateResp
}
err = json.Unmarshal(body, &updateResp)
if err != nil {
slog.Warn(fmt.Sprintf("malformed response checking for update: %s", err))
return false, updateResp
}
// Extract the version string from the URL in the github release artifact path
updateResp.UpdateVersion = path.Base(path.Dir(updateResp.UpdateURL))
slog.Info("New update available at " + updateResp.UpdateURL)
return true, updateResp
}
func DownloadNewRelease(ctx context.Context, updateResp UpdateResponse) error {
// Do a head first to check etag info
req, err := http.NewRequestWithContext(ctx, http.MethodHead, updateResp.UpdateURL, nil)
if err != nil {
return err
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
return fmt.Errorf("error checking update: %w", err)
}
if resp.StatusCode != 200 {
return fmt.Errorf("unexpected status attempting to download update %d", resp.StatusCode)
}
resp.Body.Close()
etag := strings.Trim(resp.Header.Get("etag"), "\"")
if etag == "" {
slog.Debug("no etag detected, falling back to filename based dedup")
etag = "_"
}
filename := "OllamaSetup.exe"
_, params, err := mime.ParseMediaType(resp.Header.Get("content-disposition"))
if err == nil {
filename = params["filename"]
}
stageFilename := filepath.Join(UpdateStageDir, etag, filename)
// Check to see if we already have it downloaded
_, err = os.Stat(stageFilename)
if err == nil {
slog.Info("update already downloaded")
return nil
}
cleanupOldDownloads()
req.Method = http.MethodGet
resp, err = http.DefaultClient.Do(req)
if err != nil {
return fmt.Errorf("error checking update: %w", err)
}
defer resp.Body.Close()
etag = strings.Trim(resp.Header.Get("etag"), "\"")
if etag == "" {
slog.Debug("no etag detected, falling back to filename based dedup") // TODO probably can get rid of this redundant log
etag = "_"
}
stageFilename = filepath.Join(UpdateStageDir, etag, filename)
_, err = os.Stat(filepath.Dir(stageFilename))
if errors.Is(err, os.ErrNotExist) {
if err := os.MkdirAll(filepath.Dir(stageFilename), 0o755); err != nil {
return fmt.Errorf("create ollama dir %s: %v", filepath.Dir(stageFilename), err)
}
}
payload, err := io.ReadAll(resp.Body)
if err != nil {
return fmt.Errorf("failed to read body response: %w", err)
}
fp, err := os.OpenFile(stageFilename, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0o755)
if err != nil {
return fmt.Errorf("write payload %s: %w", stageFilename, err)
}
defer fp.Close()
if n, err := fp.Write(payload); err != nil || n != len(payload) {
return fmt.Errorf("write payload %s: %d vs %d -- %w", stageFilename, n, len(payload), err)
}
slog.Info("new update downloaded " + stageFilename)
UpdateDownloaded = true
return nil
}
func cleanupOldDownloads() {
files, err := os.ReadDir(UpdateStageDir)
if err != nil && errors.Is(err, os.ErrNotExist) {
// Expected behavior on first run
return
} else if err != nil {
slog.Warn(fmt.Sprintf("failed to list stage dir: %s", err))
return
}
for _, file := range files {
fullname := filepath.Join(UpdateStageDir, file.Name())
slog.Debug("cleaning up old download: " + fullname)
err = os.RemoveAll(fullname)
if err != nil {
slog.Warn(fmt.Sprintf("failed to cleanup stale update download %s", err))
}
}
}
func StartBackgroundUpdaterChecker(ctx context.Context, cb func(string) error) {
go func() {
// Don't blast an update message immediately after startup
// time.Sleep(30 * time.Second)
time.Sleep(3 * time.Second)
for {
available, resp := IsNewReleaseAvailable(ctx)
if available {
err := DownloadNewRelease(ctx, resp)
if err != nil {
slog.Error(fmt.Sprintf("failed to download new release: %s", err))
}
err = cb(resp.UpdateVersion)
if err != nil {
slog.Warn(fmt.Sprintf("failed to register update available with tray: %s", err))
}
}
select {
case <-ctx.Done():
slog.Debug("stopping background update checker")
return
default:
time.Sleep(UpdateCheckInterval)
}
}
}()
}

View File

@@ -0,0 +1,10 @@
package updater
import (
"context"
"fmt"
)
func DoUpgrade(cancel context.CancelFunc, done chan int) error {
return fmt.Errorf("DoUpgrade not yet implemented")
}

View File

@@ -0,0 +1,86 @@
package updater
import (
"context"
"fmt"
"log/slog"
"os"
"os/exec"
"path/filepath"
)
func init() {
UpdateStageDir = filepath.Join(os.Getenv("LOCALAPPDATA"), "Ollama", "updates")
}
func DoUpgrade(cancel context.CancelFunc, done chan int) error {
logFile := filepath.Join(os.Getenv("LOCALAPPDATA"), "Ollama", "upgrade.log")
files, err := filepath.Glob(filepath.Join(UpdateStageDir, "*", "*.exe")) // TODO generalize for multiplatform
if err != nil {
return fmt.Errorf("failed to lookup downloads: %s", err)
}
if len(files) == 0 {
return fmt.Errorf("no update downloads found")
} else if len(files) > 1 {
// Shouldn't happen
slog.Warn(fmt.Sprintf("multiple downloads found, using first one %v", files))
}
installerExe := files[0]
slog.Info("starting upgrade with " + installerExe)
slog.Info("upgrade log file " + logFile)
// When running in debug mode, we'll be "verbose" and let the installer pop up and prompt
installArgs := []string{
"/CLOSEAPPLICATIONS", // Quit the tray app if it's still running
"/LOG=" + filepath.Base(logFile), // Only relative seems reliable, so set pwd
"/FORCECLOSEAPPLICATIONS", // Force close the tray app - might be needed
}
// When we're not in debug mode, make the upgrade as quiet as possible (no GUI, no prompts)
// TODO - temporarily disable since we're pinning in debug mode for the preview
// if debug := os.Getenv("OLLAMA_DEBUG"); debug == "" {
installArgs = append(installArgs,
"/SP", // Skip the "This will install... Do you wish to continue" prompt
"/SUPPRESSMSGBOXES",
"/SILENT",
"/VERYSILENT",
)
// }
// Safeguard in case we have requests in flight that need to drain...
slog.Info("Waiting for server to shutdown")
cancel()
if done != nil {
<-done
} else {
// Shouldn't happen
slog.Warn("done chan was nil, not actually waiting")
}
slog.Debug(fmt.Sprintf("starting installer: %s %v", installerExe, installArgs))
os.Chdir(filepath.Dir(logFile)) //nolint:errcheck
cmd := exec.Command(installerExe, installArgs...)
if err := cmd.Start(); err != nil {
return fmt.Errorf("unable to start ollama app %w", err)
}
if cmd.Process != nil {
err = cmd.Process.Release()
if err != nil {
slog.Error(fmt.Sprintf("failed to release server process: %s", err))
}
} else {
// TODO - some details about why it didn't start, or is this a pedantic error case?
return fmt.Errorf("installer process did not start")
}
// TODO should we linger for a moment and check to make sure it's actually running by checking the pid?
slog.Info("Installer started in background, exiting")
os.Exit(0)
// Not reached
return nil
}

View File

@@ -1,20 +0,0 @@
import type { Configuration } from 'webpack'
import { rules } from './webpack.rules'
import { plugins } from './webpack.plugins'
export const mainConfig: Configuration = {
/**
* This is the main entry point for your application, it's the first file
* that runs in the main process.
*/
entry: './src/index.ts',
// Put your normal webpack config below here
module: {
rules,
},
plugins,
resolve: {
extensions: ['.js', '.ts', '.jsx', '.tsx', '.css', '.json'],
},
}

View File

@@ -1,14 +0,0 @@
import type IForkTsCheckerWebpackPlugin from 'fork-ts-checker-webpack-plugin'
import { DefinePlugin } from 'webpack'
// eslint-disable-next-line @typescript-eslint/no-var-requires
const ForkTsCheckerWebpackPlugin: typeof IForkTsCheckerWebpackPlugin = require('fork-ts-checker-webpack-plugin')
export const plugins = [
new ForkTsCheckerWebpackPlugin({
logger: 'webpack-infrastructure',
}),
new DefinePlugin({
'process.env.TELEMETRY_WRITE_KEY': JSON.stringify(process.env.TELEMETRY_WRITE_KEY),
}),
]

View File

@@ -1,19 +0,0 @@
import type { Configuration } from 'webpack'
import { rules } from './webpack.rules'
import { plugins } from './webpack.plugins'
rules.push({
test: /\.css$/,
use: [{ loader: 'style-loader' }, { loader: 'css-loader' }, { loader: 'postcss-loader' }],
})
export const rendererConfig: Configuration = {
module: {
rules,
},
plugins,
resolve: {
extensions: ['.js', '.ts', '.jsx', '.tsx', '.css'],
},
}

View File

@@ -1,35 +0,0 @@
import type { ModuleOptions } from 'webpack'
export const rules: Required<ModuleOptions>['rules'] = [
// Add support for native node modules
{
// We're specifying native_modules in the test because the asset relocator loader generates a
// "fake" .node file which is really a cjs file.
test: /native_modules[/\\].+\.node$/,
use: 'node-loader',
},
{
test: /[/\\]node_modules[/\\].+\.(m?js|node)$/,
parser: { amd: false },
use: {
loader: '@vercel/webpack-asset-relocator-loader',
options: {
outputAssetBase: 'native_modules',
},
},
},
{
test: /\.tsx?$/,
exclude: /(node_modules|\.webpack)/,
use: {
loader: 'ts-loader',
options: {
transpileOnly: true,
},
},
},
{
test: /\.svg$/,
use: ['@svgr/webpack'],
},
]

156
app/windows/ollama.iss Normal file
View File

@@ -0,0 +1,156 @@
; Inno Setup Installer for Ollama
;
; To build the installer use the build script invoked from the top of the source tree
;
; powershell -ExecutionPolicy Bypass -File .\scripts\build_windows.ps
#define MyAppName "Ollama"
#if GetEnv("PKG_VERSION") != ""
#define MyAppVersion GetEnv("PKG_VERSION")
#else
#define MyAppVersion "0.0.0"
#endif
#define MyAppPublisher "Ollama"
#define MyAppURL "https://ollama.com/"
#define MyAppExeName "ollama app.exe"
#define MyIcon ".\assets\app.ico"
[Setup]
; NOTE: The value of AppId uniquely identifies this application. Do not use the same AppId value in installers for other applications.
; (To generate a new GUID, click Tools | Generate GUID inside the IDE.)
AppId={{44E83376-CE68-45EB-8FC1-393500EB558C}
AppName={#MyAppName}
AppVersion={#MyAppVersion}
VersionInfoVersion={#MyAppVersion}
;AppVerName={#MyAppName} {#MyAppVersion}
AppPublisher={#MyAppPublisher}
AppPublisherURL={#MyAppURL}
AppSupportURL={#MyAppURL}
AppUpdatesURL={#MyAppURL}
ArchitecturesAllowed=x64 arm64
ArchitecturesInstallIn64BitMode=x64 arm64
DefaultDirName={localappdata}\Programs\{#MyAppName}
DefaultGroupName={#MyAppName}
DisableProgramGroupPage=yes
PrivilegesRequired=lowest
OutputBaseFilename="OllamaSetup"
SetupIconFile={#MyIcon}
UninstallDisplayIcon={uninstallexe}
Compression=lzma2
SolidCompression=no
WizardStyle=modern
ChangesEnvironment=yes
OutputDir=..\dist\
; Disable logging once everything's battle tested
; Filename will be %TEMP%\Setup Log*.txt
SetupLogging=yes
CloseApplications=yes
RestartApplications=no
; https://jrsoftware.org/ishelp/index.php?topic=setup_wizardimagefile
WizardSmallImageFile=.\assets\setup.bmp
; TODO verifty actual min windows version...
; OG Win 10
MinVersion=10.0.10240
; First release that supports WinRT UI Composition for win32 apps
; MinVersion=10.0.17134
; First release with XAML Islands - possible UI path forward
; MinVersion=10.0.18362
; quiet...
DisableDirPage=yes
DisableFinishedPage=yes
DisableReadyMemo=yes
DisableReadyPage=yes
DisableStartupPrompt=yes
DisableWelcomePage=yes
; TODO - percentage can't be set less than 100, so how to make it shorter?
; WizardSizePercent=100,80
#if GetEnv("KEY_CONTAINER")
SignTool=MySignTool
SignedUninstaller=yes
#endif
SetupMutex=OllamaSetupMutex
[Languages]
Name: "english"; MessagesFile: "compiler:Default.isl"
[LangOptions]
DialogFontSize=12
[Files]
Source: ".\app.exe"; DestDir: "{app}"; DestName: "{#MyAppExeName}" ; Flags: ignoreversion 64bit
Source: "..\ollama.exe"; DestDir: "{app}"; Flags: ignoreversion 64bit
Source: "..\dist\windows-amd64\*.dll"; DestDir: "{app}"; Flags: ignoreversion 64bit
Source: "..\dist\windows-amd64\ollama_runners\*"; DestDir: "{app}\ollama_runners"; Flags: ignoreversion 64bit recursesubdirs
Source: "..\dist\ollama_welcome.ps1"; DestDir: "{app}"; Flags: ignoreversion
Source: ".\assets\app.ico"; DestDir: "{app}"; Flags: ignoreversion
#if DirExists("..\dist\windows-amd64\rocm")
Source: "..\dist\windows-amd64\rocm\*"; DestDir: "{app}\rocm\"; Flags: ignoreversion recursesubdirs
#endif
[Icons]
Name: "{group}\{#MyAppName}"; Filename: "{app}\{#MyAppExeName}"; IconFilename: "{app}\app.ico"
Name: "{userstartup}\{#MyAppName}"; Filename: "{app}\{#MyAppExeName}"; IconFilename: "{app}\app.ico"
Name: "{userprograms}\{#MyAppName}"; Filename: "{app}\{#MyAppExeName}"; IconFilename: "{app}\app.ico"
[Run]
Filename: "{cmd}"; Parameters: "/C set PATH={app};%PATH% & ""{app}\{#MyAppExeName}"""; Flags: postinstall nowait runhidden
[UninstallRun]
; Filename: "{cmd}"; Parameters: "/C ""taskkill /im ''{#MyAppExeName}'' /f /t"; Flags: runhidden
; Filename: "{cmd}"; Parameters: "/C ""taskkill /im ollama.exe /f /t"; Flags: runhidden
Filename: "taskkill"; Parameters: "/im ""{#MyAppExeName}"" /f /t"; Flags: runhidden
Filename: "taskkill"; Parameters: "/im ""ollama.exe"" /f /t"; Flags: runhidden
; HACK! need to give the server and app enough time to exit
; TODO - convert this to a Pascal code script so it waits until they're no longer running, then completes
Filename: "{cmd}"; Parameters: "/c timeout 5"; Flags: runhidden
[UninstallDelete]
Type: filesandordirs; Name: "{%TEMP}\ollama*"
Type: filesandordirs; Name: "{%LOCALAPPDATA}\Ollama"
Type: filesandordirs; Name: "{%LOCALAPPDATA}\Programs\Ollama"
Type: filesandordirs; Name: "{%USERPROFILE}\.ollama\models"
Type: filesandordirs; Name: "{%USERPROFILE}\.ollama\history"
; NOTE: if the user has a custom OLLAMA_MODELS it will be preserved
[Messages]
WizardReady=Ollama Windows Preview
ReadyLabel1=%nLet's get you up and running with your own large language models.
SetupAppRunningError=Another Ollama installer is running.%n%nPlease cancel or finish the other installer, then click OK to continue with this install, or Cancel to exit.
;FinishedHeadingLabel=Run your first model
;FinishedLabel=%nRun this command in a PowerShell or cmd terminal.%n%n%n ollama run llama3
;ClickFinish=%n
[Registry]
Root: HKCU; Subkey: "Environment"; \
ValueType: expandsz; ValueName: "Path"; ValueData: "{olddata};{app}"; \
Check: NeedsAddPath('{app}')
[Code]
function NeedsAddPath(Param: string): boolean;
var
OrigPath: string;
begin
if not RegQueryStringValue(HKEY_CURRENT_USER,
'Environment',
'Path', OrigPath)
then begin
Result := True;
exit;
end;
{ look for the path with leading and trailing semicolon }
{ Pos() returns 0 if not found }
Result := Pos(';' + ExpandConstant(Param) + ';', ';' + OrigPath + ';') = 0;
end;

29
app/windows/ollama.rc Normal file
View File

@@ -0,0 +1,29 @@
#include <winver.h>
VS_VERSION_INFO VERSIONINFO
FILEFLAGSMASK 0x3fL
#ifdef _DEBUG
FILEFLAGS 0x1L
#else
FILEFLAGS 0x0L
#endif
FILEOS 0x40004L
FILETYPE 0x1L
FILESUBTYPE 0x0L
BEGIN
BLOCK "StringFileInfo"
BEGIN
BLOCK "040904b0"
BEGIN
VALUE "FileDescription", "Ollama"
VALUE "InternalName", "Ollama"
VALUE "OriginalFilename", "ollama app.exe"
VALUE "ProductName", "Ollama"
END
END
BLOCK "VarFileInfo"
BEGIN
VALUE "Translation", 0x409, 1200
END
END

View File

@@ -0,0 +1,8 @@
# TODO - consider ANSI colors and maybe ASCII art...
write-host ""
write-host "Welcome to Ollama!"
write-host ""
write-host "Run your first model:"
write-host ""
write-host "`tollama run llama2"
write-host ""

61
auth/auth.go Normal file
View File

@@ -0,0 +1,61 @@
package auth
import (
"bytes"
"context"
"crypto/rand"
"encoding/base64"
"fmt"
"io"
"log/slog"
"os"
"path/filepath"
"golang.org/x/crypto/ssh"
)
const defaultPrivateKey = "id_ed25519"
func NewNonce(r io.Reader, length int) (string, error) {
nonce := make([]byte, length)
if _, err := io.ReadFull(r, nonce); err != nil {
return "", err
}
return base64.RawURLEncoding.EncodeToString(nonce), nil
}
func Sign(ctx context.Context, bts []byte) (string, error) {
home, err := os.UserHomeDir()
if err != nil {
return "", err
}
keyPath := filepath.Join(home, ".ollama", defaultPrivateKey)
privateKeyFile, err := os.ReadFile(keyPath)
if err != nil {
slog.Info(fmt.Sprintf("Failed to load private key: %v", err))
return "", err
}
privateKey, err := ssh.ParsePrivateKey(privateKeyFile)
if err != nil {
return "", err
}
// get the pubkey, but remove the type
publicKey := ssh.MarshalAuthorizedKey(privateKey.PublicKey())
parts := bytes.Split(publicKey, []byte(" "))
if len(parts) < 2 {
return "", fmt.Errorf("malformed public key")
}
signedData, err := privateKey.Sign(rand.Reader, bts)
if err != nil {
return "", err
}
// signature is <pubkey>:<signature>
return fmt.Sprintf("%s:%s", bytes.TrimSpace(parts[1]), base64.StdEncoding.EncodeToString(signedData.Blob)), nil
}

1064
cmd/cmd.go

File diff suppressed because it is too large Load Diff

667
cmd/interactive.go Normal file
View File

@@ -0,0 +1,667 @@
package cmd
import (
"errors"
"fmt"
"io"
"net/http"
"os"
"path/filepath"
"regexp"
"sort"
"strings"
"github.com/spf13/cobra"
"golang.org/x/exp/slices"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/progress"
"github.com/ollama/ollama/readline"
)
type MultilineState int
const (
MultilineNone MultilineState = iota
MultilinePrompt
MultilineSystem
MultilineTemplate
)
func loadModel(cmd *cobra.Command, opts *runOptions) error {
client, err := api.ClientFromEnvironment()
if err != nil {
return err
}
p := progress.NewProgress(os.Stderr)
defer p.StopAndClear()
spinner := progress.NewSpinner("")
p.Add("", spinner)
showReq := api.ShowRequest{Name: opts.Model}
showResp, err := client.Show(cmd.Context(), &showReq)
if err != nil {
return err
}
opts.MultiModal = slices.Contains(showResp.Details.Families, "clip")
opts.ParentModel = showResp.Details.ParentModel
if len(showResp.Messages) > 0 {
opts.Messages = append(opts.Messages, showResp.Messages...)
}
chatReq := &api.ChatRequest{
Model: opts.Model,
Messages: []api.Message{},
}
err = client.Chat(cmd.Context(), chatReq, func(resp api.ChatResponse) error {
p.StopAndClear()
if len(opts.Messages) > 0 {
for _, msg := range opts.Messages {
switch msg.Role {
case "user":
fmt.Printf(">>> %s\n", msg.Content)
case "assistant":
state := &displayResponseState{}
displayResponse(msg.Content, opts.WordWrap, state)
fmt.Println()
fmt.Println()
}
}
}
return nil
})
if err != nil {
return err
}
return nil
}
func generateInteractive(cmd *cobra.Command, opts runOptions) error {
opts.Messages = make([]api.Message, 0)
err := loadModel(cmd, &opts)
if err != nil {
return err
}
usage := func() {
fmt.Fprintln(os.Stderr, "Available Commands:")
fmt.Fprintln(os.Stderr, " /set Set session variables")
fmt.Fprintln(os.Stderr, " /show Show model information")
fmt.Fprintln(os.Stderr, " /load <model> Load a session or model")
fmt.Fprintln(os.Stderr, " /save <model> Save your current session")
fmt.Fprintln(os.Stderr, " /bye Exit")
fmt.Fprintln(os.Stderr, " /?, /help Help for a command")
fmt.Fprintln(os.Stderr, " /? shortcuts Help for keyboard shortcuts")
fmt.Fprintln(os.Stderr, "")
fmt.Fprintln(os.Stderr, "Use \"\"\" to begin a multi-line message.")
if opts.MultiModal {
fmt.Fprintf(os.Stderr, "Use %s to include .jpg or .png images.\n", filepath.FromSlash("/path/to/file"))
}
fmt.Fprintln(os.Stderr, "")
}
usageSet := func() {
fmt.Fprintln(os.Stderr, "Available Commands:")
fmt.Fprintln(os.Stderr, " /set parameter ... Set a parameter")
fmt.Fprintln(os.Stderr, " /set system <string> Set system message")
fmt.Fprintln(os.Stderr, " /set template <string> Set prompt template")
fmt.Fprintln(os.Stderr, " /set history Enable history")
fmt.Fprintln(os.Stderr, " /set nohistory Disable history")
fmt.Fprintln(os.Stderr, " /set wordwrap Enable wordwrap")
fmt.Fprintln(os.Stderr, " /set nowordwrap Disable wordwrap")
fmt.Fprintln(os.Stderr, " /set format json Enable JSON mode")
fmt.Fprintln(os.Stderr, " /set noformat Disable formatting")
fmt.Fprintln(os.Stderr, " /set verbose Show LLM stats")
fmt.Fprintln(os.Stderr, " /set quiet Disable LLM stats")
fmt.Fprintln(os.Stderr, "")
}
usageShortcuts := func() {
fmt.Fprintln(os.Stderr, "Available keyboard shortcuts:")
fmt.Fprintln(os.Stderr, " Ctrl + a Move to the beginning of the line (Home)")
fmt.Fprintln(os.Stderr, " Ctrl + e Move to the end of the line (End)")
fmt.Fprintln(os.Stderr, " Alt + b Move back (left) one word")
fmt.Fprintln(os.Stderr, " Alt + f Move forward (right) one word")
fmt.Fprintln(os.Stderr, " Ctrl + k Delete the sentence after the cursor")
fmt.Fprintln(os.Stderr, " Ctrl + u Delete the sentence before the cursor")
fmt.Fprintln(os.Stderr, "")
fmt.Fprintln(os.Stderr, " Ctrl + l Clear the screen")
fmt.Fprintln(os.Stderr, " Ctrl + c Stop the model from responding")
fmt.Fprintln(os.Stderr, " Ctrl + d Exit ollama (/bye)")
fmt.Fprintln(os.Stderr, "")
}
usageShow := func() {
fmt.Fprintln(os.Stderr, "Available Commands:")
fmt.Fprintln(os.Stderr, " /show info Show details for this model")
fmt.Fprintln(os.Stderr, " /show license Show model license")
fmt.Fprintln(os.Stderr, " /show modelfile Show Modelfile for this model")
fmt.Fprintln(os.Stderr, " /show parameters Show parameters for this model")
fmt.Fprintln(os.Stderr, " /show system Show system message")
fmt.Fprintln(os.Stderr, " /show template Show prompt template")
fmt.Fprintln(os.Stderr, "")
}
// only list out the most common parameters
usageParameters := func() {
fmt.Fprintln(os.Stderr, "Available Parameters:")
fmt.Fprintln(os.Stderr, " /set parameter seed <int> Random number seed")
fmt.Fprintln(os.Stderr, " /set parameter num_predict <int> Max number of tokens to predict")
fmt.Fprintln(os.Stderr, " /set parameter top_k <int> Pick from top k num of tokens")
fmt.Fprintln(os.Stderr, " /set parameter top_p <float> Pick token based on sum of probabilities")
fmt.Fprintln(os.Stderr, " /set parameter num_ctx <int> Set the context size")
fmt.Fprintln(os.Stderr, " /set parameter temperature <float> Set creativity level")
fmt.Fprintln(os.Stderr, " /set parameter repeat_penalty <float> How strongly to penalize repetitions")
fmt.Fprintln(os.Stderr, " /set parameter repeat_last_n <int> Set how far back to look for repetitions")
fmt.Fprintln(os.Stderr, " /set parameter num_gpu <int> The number of layers to send to the GPU")
fmt.Fprintln(os.Stderr, " /set parameter stop \"<string>\", ... Set the stop parameters")
fmt.Fprintln(os.Stderr, "")
}
scanner, err := readline.New(readline.Prompt{
Prompt: ">>> ",
AltPrompt: "... ",
Placeholder: "Send a message (/? for help)",
AltPlaceholder: `Use """ to end multi-line input`,
})
if err != nil {
return err
}
fmt.Print(readline.StartBracketedPaste)
defer fmt.Printf(readline.EndBracketedPaste)
var sb strings.Builder
var multiline MultilineState
for {
line, err := scanner.Readline()
switch {
case errors.Is(err, io.EOF):
fmt.Println()
return nil
case errors.Is(err, readline.ErrInterrupt):
if line == "" {
fmt.Println("\nUse Ctrl + d or /bye to exit.")
}
scanner.Prompt.UseAlt = false
sb.Reset()
continue
case err != nil:
return err
}
switch {
case multiline != MultilineNone:
// check if there's a multiline terminating string
before, ok := strings.CutSuffix(line, `"""`)
sb.WriteString(before)
if !ok {
fmt.Fprintln(&sb)
continue
}
switch multiline {
case MultilineSystem:
opts.System = sb.String()
opts.Messages = append(opts.Messages, api.Message{Role: "system", Content: opts.System})
fmt.Println("Set system message.")
sb.Reset()
case MultilineTemplate:
opts.Template = sb.String()
fmt.Println("Set prompt template.")
sb.Reset()
}
multiline = MultilineNone
scanner.Prompt.UseAlt = false
case strings.HasPrefix(line, `"""`):
line := strings.TrimPrefix(line, `"""`)
line, ok := strings.CutSuffix(line, `"""`)
sb.WriteString(line)
if !ok {
// no multiline terminating string; need more input
fmt.Fprintln(&sb)
multiline = MultilinePrompt
scanner.Prompt.UseAlt = true
}
case scanner.Pasting:
fmt.Fprintln(&sb, line)
continue
case strings.HasPrefix(line, "/list"):
args := strings.Fields(line)
if err := ListHandler(cmd, args[1:]); err != nil {
return err
}
case strings.HasPrefix(line, "/load"):
args := strings.Fields(line)
if len(args) != 2 {
fmt.Println("Usage:\n /load <modelname>")
continue
}
opts.Model = args[1]
opts.Messages = []api.Message{}
fmt.Printf("Loading model '%s'\n", opts.Model)
if err := loadModel(cmd, &opts); err != nil {
return err
}
continue
case strings.HasPrefix(line, "/save"):
args := strings.Fields(line)
if len(args) != 2 {
fmt.Println("Usage:\n /save <modelname>")
continue
}
client, err := api.ClientFromEnvironment()
if err != nil {
fmt.Println("error: couldn't connect to ollama server")
return err
}
req := &api.CreateRequest{
Name: args[1],
Modelfile: buildModelfile(opts),
}
fn := func(resp api.ProgressResponse) error { return nil }
err = client.Create(cmd.Context(), req, fn)
if err != nil {
fmt.Println("error: couldn't save model")
return err
}
fmt.Printf("Created new model '%s'\n", args[1])
continue
case strings.HasPrefix(line, "/set"):
args := strings.Fields(line)
if len(args) > 1 {
switch args[1] {
case "history":
scanner.HistoryEnable()
case "nohistory":
scanner.HistoryDisable()
case "wordwrap":
opts.WordWrap = true
fmt.Println("Set 'wordwrap' mode.")
case "nowordwrap":
opts.WordWrap = false
fmt.Println("Set 'nowordwrap' mode.")
case "verbose":
if err := cmd.Flags().Set("verbose", "true"); err != nil {
return err
}
fmt.Println("Set 'verbose' mode.")
case "quiet":
if err := cmd.Flags().Set("verbose", "false"); err != nil {
return err
}
fmt.Println("Set 'quiet' mode.")
case "format":
if len(args) < 3 || args[2] != "json" {
fmt.Println("Invalid or missing format. For 'json' mode use '/set format json'")
} else {
opts.Format = args[2]
fmt.Printf("Set format to '%s' mode.\n", args[2])
}
case "noformat":
opts.Format = ""
fmt.Println("Disabled format.")
case "parameter":
if len(args) < 4 {
usageParameters()
continue
}
params := args[3:]
fp, err := api.FormatParams(map[string][]string{args[2]: params})
if err != nil {
fmt.Printf("Couldn't set parameter: %q\n", err)
continue
}
fmt.Printf("Set parameter '%s' to '%s'\n", args[2], strings.Join(params, ", "))
opts.Options[args[2]] = fp[args[2]]
case "system", "template":
if len(args) < 3 {
usageSet()
continue
}
if args[1] == "system" {
multiline = MultilineSystem
} else if args[1] == "template" {
multiline = MultilineTemplate
}
line := strings.Join(args[2:], " ")
line, ok := strings.CutPrefix(line, `"""`)
if !ok {
multiline = MultilineNone
} else {
// only cut suffix if the line is multiline
line, ok = strings.CutSuffix(line, `"""`)
if ok {
multiline = MultilineNone
}
}
sb.WriteString(line)
if multiline != MultilineNone {
scanner.Prompt.UseAlt = true
continue
}
if args[1] == "system" {
opts.System = sb.String() // for display in modelfile
newMessage := api.Message{Role: "system", Content: sb.String()}
// Check if the slice is not empty and the last message is from 'system'
if len(opts.Messages) > 0 && opts.Messages[len(opts.Messages)-1].Role == "system" {
// Replace the last message
opts.Messages[len(opts.Messages)-1] = newMessage
} else {
opts.Messages = append(opts.Messages, newMessage)
}
fmt.Println("Set system message.")
sb.Reset()
} else if args[1] == "template" {
opts.Template = sb.String()
fmt.Println("Set prompt template.")
sb.Reset()
}
sb.Reset()
continue
default:
fmt.Printf("Unknown command '/set %s'. Type /? for help\n", args[1])
}
} else {
usageSet()
}
case strings.HasPrefix(line, "/show"):
args := strings.Fields(line)
if len(args) > 1 {
client, err := api.ClientFromEnvironment()
if err != nil {
fmt.Println("error: couldn't connect to ollama server")
return err
}
req := &api.ShowRequest{
Name: opts.Model,
System: opts.System,
Template: opts.Template,
Options: opts.Options,
}
resp, err := client.Show(cmd.Context(), req)
if err != nil {
fmt.Println("error: couldn't get model")
return err
}
switch args[1] {
case "info":
fmt.Println("Model details:")
if len(resp.Details.Families) > 0 {
fmt.Printf("Family %s\n", strings.Join(resp.Details.Families, ", "))
} else if resp.Details.Family != "" {
fmt.Printf("Family %s\n", resp.Details.Family)
}
fmt.Printf("Parameter Size %s\n", resp.Details.ParameterSize)
fmt.Printf("Quantization Level %s\n", resp.Details.QuantizationLevel)
fmt.Println("")
case "license":
if resp.License == "" {
fmt.Println("No license was specified for this model.")
} else {
fmt.Println(resp.License)
}
case "modelfile":
fmt.Println(resp.Modelfile)
case "parameters":
if resp.Parameters == "" {
fmt.Println("No parameters were specified for this model.")
} else {
if len(opts.Options) > 0 {
fmt.Println("User defined parameters:")
for k, v := range opts.Options {
fmt.Printf("%-*s %v\n", 30, k, v)
}
fmt.Println()
}
fmt.Println("Model defined parameters:")
fmt.Println(resp.Parameters)
}
case "system":
switch {
case opts.System != "":
fmt.Println(opts.System + "\n")
case resp.System != "":
fmt.Println(resp.System + "\n")
default:
fmt.Println("No system message was specified for this model.")
}
case "template":
switch {
case opts.Template != "":
fmt.Println(opts.Template + "\n")
case resp.Template != "":
fmt.Println(resp.Template)
default:
fmt.Println("No prompt template was specified for this model.")
}
default:
fmt.Printf("Unknown command '/show %s'. Type /? for help\n", args[1])
}
} else {
usageShow()
}
case strings.HasPrefix(line, "/help"), strings.HasPrefix(line, "/?"):
args := strings.Fields(line)
if len(args) > 1 {
switch args[1] {
case "set", "/set":
usageSet()
case "show", "/show":
usageShow()
case "shortcut", "shortcuts":
usageShortcuts()
}
} else {
usage()
}
case strings.HasPrefix(line, "/exit"), strings.HasPrefix(line, "/bye"):
return nil
case strings.HasPrefix(line, "/"):
args := strings.Fields(line)
isFile := false
if opts.MultiModal {
for _, f := range extractFileNames(line) {
if strings.HasPrefix(f, args[0]) {
isFile = true
break
}
}
}
if !isFile {
fmt.Printf("Unknown command '%s'. Type /? for help\n", args[0])
continue
}
sb.WriteString(line)
default:
sb.WriteString(line)
}
if sb.Len() > 0 && multiline == MultilineNone {
newMessage := api.Message{Role: "user", Content: sb.String()}
if opts.MultiModal {
msg, images, err := extractFileData(sb.String())
if err != nil {
return err
}
// clear all previous images for better responses
if len(images) > 0 {
for i := range opts.Messages {
opts.Messages[i].Images = nil
}
}
newMessage.Content = msg
newMessage.Images = images
}
opts.Messages = append(opts.Messages, newMessage)
assistant, err := chat(cmd, opts)
if err != nil {
return err
}
if assistant != nil {
opts.Messages = append(opts.Messages, *assistant)
}
sb.Reset()
}
}
}
func buildModelfile(opts runOptions) string {
var mf strings.Builder
model := opts.ParentModel
if model == "" {
model = opts.Model
}
fmt.Fprintf(&mf, "FROM %s\n", model)
if opts.System != "" {
fmt.Fprintf(&mf, "SYSTEM \"\"\"%s\"\"\"\n", opts.System)
}
if opts.Template != "" {
fmt.Fprintf(&mf, "TEMPLATE \"\"\"%s\"\"\"\n", opts.Template)
}
keys := make([]string, 0)
for k := range opts.Options {
keys = append(keys, k)
}
sort.Strings(keys)
for _, k := range keys {
fmt.Fprintf(&mf, "PARAMETER %s %v\n", k, opts.Options[k])
}
fmt.Fprintln(&mf)
for _, msg := range opts.Messages {
fmt.Fprintf(&mf, "MESSAGE %s \"\"\"%s\"\"\"\n", msg.Role, msg.Content)
}
return mf.String()
}
func normalizeFilePath(fp string) string {
// Define a map of escaped characters and their replacements
replacements := map[string]string{
"\\ ": " ", // Escaped space
"\\(": "(", // Escaped left parenthesis
"\\)": ")", // Escaped right parenthesis
"\\[": "[", // Escaped left square bracket
"\\]": "]", // Escaped right square bracket
"\\{": "{", // Escaped left curly brace
"\\}": "}", // Escaped right curly brace
"\\$": "$", // Escaped dollar sign
"\\&": "&", // Escaped ampersand
"\\;": ";", // Escaped semicolon
"\\'": "'", // Escaped single quote
"\\\\": "\\", // Escaped backslash
"\\*": "*", // Escaped asterisk
"\\?": "?", // Escaped question mark
}
for escaped, actual := range replacements {
fp = strings.ReplaceAll(fp, escaped, actual)
}
return fp
}
func extractFileNames(input string) []string {
// Regex to match file paths starting with optional drive letter, / ./ \ or .\ and include escaped or unescaped spaces (\ or %20)
// and followed by more characters and a file extension
// This will capture non filename strings, but we'll check for file existence to remove mismatches
regexPattern := `(?:[a-zA-Z]:)?(?:\./|/|\\)[\S\\ ]+?\.(?i:jpg|jpeg|png|svg)\b`
re := regexp.MustCompile(regexPattern)
return re.FindAllString(input, -1)
}
func extractFileData(input string) (string, []api.ImageData, error) {
filePaths := extractFileNames(input)
var imgs []api.ImageData
for _, fp := range filePaths {
nfp := normalizeFilePath(fp)
data, err := getImageData(nfp)
if err != nil {
if os.IsNotExist(err) {
continue
}
fmt.Fprintf(os.Stderr, "Couldn't process image: %q\n", err)
return "", imgs, err
}
fmt.Fprintf(os.Stderr, "Added image '%s'\n", nfp)
input = strings.ReplaceAll(input, fp, "")
imgs = append(imgs, data)
}
return input, imgs, nil
}
func getImageData(filePath string) ([]byte, error) {
file, err := os.Open(filePath)
if err != nil {
return nil, err
}
defer file.Close()
buf := make([]byte, 512)
_, err = file.Read(buf)
if err != nil {
return nil, err
}
contentType := http.DetectContentType(buf)
allowedTypes := []string{"image/jpeg", "image/jpg", "image/png"}
if !slices.Contains(allowedTypes, contentType) {
return nil, fmt.Errorf("invalid image type: %s", contentType)
}
info, err := file.Stat()
if err != nil {
return nil, err
}
// Check if the file size exceeds 100MB
var maxSize int64 = 100 * 1024 * 1024 // 100MB in bytes
if info.Size() > maxSize {
return nil, fmt.Errorf("file size exceeds maximum limit (100MB)")
}
buf = make([]byte, info.Size())
_, err = file.Seek(0, 0)
if err != nil {
return nil, err
}
_, err = io.ReadFull(file, buf)
if err != nil {
return nil, err
}
return buf, nil
}

116
cmd/interactive_test.go Normal file
View File

@@ -0,0 +1,116 @@
package cmd
import (
"bytes"
"testing"
"text/template"
"github.com/stretchr/testify/assert"
"github.com/ollama/ollama/api"
)
func TestExtractFilenames(t *testing.T) {
// Unix style paths
input := ` some preamble
./relative\ path/one.png inbetween1 ./not a valid two.jpg inbetween2
/unescaped space /three.jpeg inbetween3 /valid\ path/dir/four.png "./quoted with spaces/five.svg`
res := extractFileNames(input)
assert.Len(t, res, 5)
assert.Contains(t, res[0], "one.png")
assert.Contains(t, res[1], "two.jpg")
assert.Contains(t, res[2], "three.jpeg")
assert.Contains(t, res[3], "four.png")
assert.Contains(t, res[4], "five.svg")
assert.NotContains(t, res[4], '"')
assert.NotContains(t, res, "inbtween")
// Windows style paths
input = ` some preamble
c:/users/jdoe/one.png inbetween1 c:/program files/someplace/two.jpg inbetween2
/absolute/nospace/three.jpeg inbetween3 /absolute/with space/four.png inbetween4
./relative\ path/five.svg inbetween5 "./relative with/spaces/six.png inbetween6
d:\path with\spaces\seven.svg inbetween7 c:\users\jdoe\eight.png inbetween8
d:\program files\someplace\nine.png inbetween9 "E:\program files\someplace\ten.svg some ending
`
res = extractFileNames(input)
assert.Len(t, res, 10)
assert.NotContains(t, res, "inbtween")
assert.Contains(t, res[0], "one.png")
assert.Contains(t, res[0], "c:")
assert.Contains(t, res[1], "two.jpg")
assert.Contains(t, res[1], "c:")
assert.Contains(t, res[2], "three.jpeg")
assert.Contains(t, res[3], "four.png")
assert.Contains(t, res[4], "five.svg")
assert.Contains(t, res[5], "six.png")
assert.Contains(t, res[6], "seven.svg")
assert.Contains(t, res[6], "d:")
assert.Contains(t, res[7], "eight.png")
assert.Contains(t, res[7], "c:")
assert.Contains(t, res[8], "nine.png")
assert.Contains(t, res[8], "d:")
assert.Contains(t, res[9], "ten.svg")
assert.Contains(t, res[9], "E:")
}
func TestModelfileBuilder(t *testing.T) {
opts := runOptions{
Model: "hork",
System: "You are part horse and part shark, but all hork. Do horklike things",
Template: "This is a template.",
Messages: []api.Message{
{Role: "user", Content: "Hey there hork!"},
{Role: "assistant", Content: "Yes it is true, I am half horse, half shark."},
},
Options: map[string]interface{}{},
}
opts.Options["temperature"] = 0.9
opts.Options["seed"] = 42
opts.Options["penalize_newline"] = false
opts.Options["stop"] = []string{"hi", "there"}
mf := buildModelfile(opts)
expectedModelfile := `FROM {{.Model}}
SYSTEM """{{.System}}"""
TEMPLATE """{{.Template}}"""
PARAMETER penalize_newline false
PARAMETER seed 42
PARAMETER stop [hi there]
PARAMETER temperature 0.9
MESSAGE user """Hey there hork!"""
MESSAGE assistant """Yes it is true, I am half horse, half shark."""
`
tmpl, err := template.New("").Parse(expectedModelfile)
assert.Nil(t, err)
var buf bytes.Buffer
err = tmpl.Execute(&buf, opts)
assert.Nil(t, err)
assert.Equal(t, buf.String(), mf)
opts.ParentModel = "horseshark"
mf = buildModelfile(opts)
expectedModelfile = `FROM {{.ParentModel}}
SYSTEM """{{.System}}"""
TEMPLATE """{{.Template}}"""
PARAMETER penalize_newline false
PARAMETER seed 42
PARAMETER stop [hi there]
PARAMETER temperature 0.9
MESSAGE user """Hey there hork!"""
MESSAGE assistant """Yes it is true, I am half horse, half shark."""
`
tmpl, err = template.New("").Parse(expectedModelfile)
assert.Nil(t, err)
var parentBuf bytes.Buffer
err = tmpl.Execute(&parentBuf, opts)
assert.Nil(t, err)
assert.Equal(t, parentBuf.String(), mf)
}

View File

@@ -1,44 +0,0 @@
package cmd
import (
"fmt"
"os"
"time"
"github.com/jmorganca/ollama/progressbar"
)
type Spinner struct {
description string
*progressbar.ProgressBar
}
func NewSpinner(description string) *Spinner {
return &Spinner{
description: description,
ProgressBar: progressbar.NewOptions(-1,
progressbar.OptionSetWriter(os.Stderr),
progressbar.OptionThrottle(60*time.Millisecond),
progressbar.OptionSpinnerType(14),
progressbar.OptionSetRenderBlankState(true),
progressbar.OptionSetElapsedTime(false),
progressbar.OptionClearOnFinish(),
progressbar.OptionSetDescription(description),
),
}
}
func (s *Spinner) Spin(tick time.Duration) {
for range time.Tick(tick) {
if s.IsFinished() {
break
}
s.Add(1)
}
}
func (s *Spinner) Stop() {
s.Finish()
fmt.Println(s.description)
}

30
cmd/start_darwin.go Normal file
View File

@@ -0,0 +1,30 @@
package cmd
import (
"context"
"fmt"
"os"
"os/exec"
"strings"
"github.com/ollama/ollama/api"
)
func startApp(ctx context.Context, client *api.Client) error {
exe, err := os.Executable()
if err != nil {
return err
}
link, err := os.Readlink(exe)
if err != nil {
return err
}
if !strings.Contains(link, "Ollama.app") {
return fmt.Errorf("could not find ollama app")
}
path := strings.Split(link, "Ollama.app")
if err := exec.Command("/usr/bin/open", "-a", path[0]+"Ollama.app").Run(); err != nil {
return err
}
return waitForServer(ctx, client)
}

Some files were not shown because too many files have changed in this diff Show More