add examples of streaming in python and node

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

.dockerignore

@@ -1,8 +1,5 @@
 .vscode
 ollama
 app
-dist
-llm/llama.cpp
-.env
-.cache
-test_data
+llm/llama.cpp/ggml
+llm/llama.cpp/gguf

.github/workflows/test.yaml

@@ -1,106 +0,0 @@
-name: test
-
-on:
-  pull_request:
-
-jobs:
-  generate:
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-        arch: [amd64, arm64]
-        exclude:
-          - os: ubuntu-latest
-            arch: arm64
-          - os: windows-latest
-            arch: arm64
-    runs-on: ${{ matrix.os }}
-    env:
-      GOARCH: ${{ matrix.arch }}
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-go@v5
-        with:
-          go-version: '1.21'
-          cache: true
-      - if: ${{ startsWith(matrix.os, 'windows-') }}
-        shell: pwsh
-        run: |
-          $path = vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath
-          if ($path) {
-              $path = join-path $path 'Common7\Tools\vsdevcmd.bat'
-              if (test-path $path) {
-                  cmd /s /c """$path"" $args && set" | where { $_ -match '(\w+)=(.*)' } | foreach {
-                      echo "$($Matches[1])=$($Matches[2])" | Out-File -FilePath $Env:GITHUB_ENV -Encoding utf8 -Append
-                  }
-              }
-          }
-
-          echo "C:\Program Files\Git\usr\bin" | Out-File -FilePath $Env:GITHUB_PATH -Encoding utf8 -Append
-      - run: go get ./...
-      - run: go generate -x ./...
-      - uses: actions/upload-artifact@v4
-        with:
-          name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
-          path: |
-            llm/llama.cpp/build/**/lib/*
-  lint:
-    needs: generate
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-        arch: [amd64, arm64]
-        exclude:
-          - os: ubuntu-latest
-            arch: arm64
-          - os: windows-latest
-            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: '1.21'
-          cache: false
-      - uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
-          path: llm/llama.cpp/build
-      - uses: golangci/golangci-lint-action@v3
-  test:
-    needs: generate
-    strategy:
-      matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-        arch: [amd64]
-        exclude:
-          - os: ubuntu-latest
-            arch: arm64
-          - os: windows-latest
-            arch: arm64
-    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: '1.21'
-          cache: true
-      - run: go get
-      - uses: actions/download-artifact@v4
-        with:
-          name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
-          path: llm/llama.cpp/build
-      - run: go build
-      - run: go test -v ./...

.gitignore

@@ -6,7 +6,3 @@
 dist
 ollama
 ggml-metal.metal
-.cache
-*.exe
-.idea
-test_data

.gitmodules

@@ -1,4 +1,9 @@
-[submodule "llama.cpp"]
-	path = llm/llama.cpp
-	url = https://github.com/ggerganov/llama.cpp.git
-	shallow = true
+[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
+    shallow = true

.golangci.yaml

@@ -1,27 +0,0 @@
-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
-linters-settings:
-  errcheck:
-    # exclude the following functions since we don't generally
-    # need to be concerned with the returned errors
-    exclude-functions:
-      - encoding/binary.Read
-      - (*os.File).Seek
-      - (*bufio.Writer).WriteString
-      - (*github.com/spf13/pflag.FlagSet).Set
-      - (*github.com/jmorganca/ollama/llm.readSeekOffset).Seek

Dockerfile

@@ -1,29 +1,21 @@
-FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
-
-ARG TARGETARCH
-ARG GOFLAGS="'-ldflags=-w -s'"
+FROM golang:alpine
 
 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
+RUN apk add --no-cache git build-base cmake
 
 COPY . .
-ENV GOARCH=$TARGETARCH
-ENV GOFLAGS=$GOFLAGS
-RUN /usr/local/go/bin/go generate ./... \
-    && /usr/local/go/bin/go build .
+RUN go generate ./... && go build -ldflags '-linkmode external -extldflags "-static"' .
 
-FROM ubuntu:22.04
-RUN apt-get update && apt-get install -y ca-certificates
-COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
-EXPOSE 11434
+FROM alpine
 ENV OLLAMA_HOST 0.0.0.0
+RUN apk add --no-cache libstdc++
 
-# set some environment variable for better NVIDIA compatibility
-ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/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
+ARG USER=ollama
+ARG GROUP=ollama
+RUN addgroup $GROUP && adduser -D -G $GROUP $USER
 
+COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
+
+USER $USER:$GROUP
 ENTRYPOINT ["/bin/ollama"]
 CMD ["serve"]

Dockerfile.build

@@ -1,99 +0,0 @@
-ARG GOLANG_VERSION=1.21.3
-ARG CMAKE_VERSION=3.22.1
-ARG CUDA_VERSION=11.3.1
-
-# 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
-
-FROM --platform=linux/amd64 nvidia/cuda:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
-ARG CMAKE_VERSION
-ARG CGO_CFLAGS
-COPY ./scripts/rh_linux_deps.sh /
-RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
-ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
-COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
-WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
-RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
-
-FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
-ARG CMAKE_VERSION
-ARG CGO_CFLAGS
-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/jmorganca/ollama/
-WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
-RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
-
-FROM --platform=linux/amd64 rocm/dev-centos-7:5.7.1-complete AS rocm-5-build-amd64
-ARG CMAKE_VERSION
-ARG CGO_CFLAGS
-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/jmorganca/ollama/
-WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
-RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
-
-FROM --platform=linux/amd64 rocm/dev-centos-7:6.0-complete AS rocm-6-build-amd64
-ARG CMAKE_VERSION
-ARG CGO_CFLAGS
-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/jmorganca/ollama/
-WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
-RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
-
-FROM --platform=linux/amd64 centos:7 AS cpu-build-amd64
-ARG CMAKE_VERSION
-ARG GOLANG_VERSION
-ARG OLLAMA_CUSTOM_CPU_DEFS
-ARG CGO_CFLAGS
-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:$PATH
-COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
-WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
-RUN sh gen_linux.sh
-
-FROM --platform=linux/arm64 centos:7 AS cpu-build-arm64
-ARG CMAKE_VERSION
-ARG GOLANG_VERSION
-ARG OLLAMA_CUSTOM_CPU_DEFS
-ARG CGO_CFLAGS
-COPY ./scripts/rh_linux_deps.sh /
-RUN CMAKE_VERSION=${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/jmorganca/ollama/
-WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
-RUN sh gen_linux.sh
-
-
-FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
-ENV CGO_ENABLED 1
-ARG GOFLAGS
-ARG CGO_CFLAGS
-WORKDIR /go/src/github.com/jmorganca/ollama
-COPY . .
-COPY --from=cuda-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
-COPY --from=rocm-5-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
-COPY --from=rocm-6-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
-RUN go build .
-
-FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
-ENV CGO_ENABLED 1
-ARG GOLANG_VERSION
-ARG GOFLAGS
-ARG CGO_CFLAGS
-WORKDIR /go/src/github.com/jmorganca/ollama
-COPY . .
-COPY --from=cuda-build-arm64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
-RUN go build .
-
-FROM build-$TARGETARCH

Dockerfile.cuda

@@ -0,0 +1,22 @@
+FROM nvidia/cuda:12.2.0-devel-ubuntu22.04
+
+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/go1.21.1.linux-amd64.tar.gz /tmp/go1.21.1.tar.gz
+RUN mkdir -p /usr/local && tar xz -C /usr/local </tmp/go1.21.1.tar.gz
+
+COPY . .
+RUN /usr/local/go/bin/go generate ./... && /usr/local/go/bin/go build -ldflags '-linkmode external -extldflags "-static"' .
+
+FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04
+ENV OLLAMA_HOST 0.0.0.0
+
+ARG USER=ollama
+ARG GROUP=ollama
+RUN groupadd $GROUP && useradd -m -g $GROUP $USER
+
+COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
+
+USER $USER:$GROUP
+ENTRYPOINT ["/bin/ollama"]
+CMD ["serve"]

README.md

@@ -9,31 +9,19 @@
 
 [![Discord](https://dcbadge.vercel.app/api/server/ollama?style=flat&compact=true)](https://discord.gg/ollama)
 
-Get up and running with large language models locally.
+Run, create, and share large language models (LLMs).
 
-### macOS
+> Note: Ollama is in early preview. Please report any issues you find.
 
-[Download](https://ollama.ai/download/Ollama-darwin.zip)
+## Download
 
-### Windows
-
-Coming soon! For now, you can install Ollama on Windows via WSL2.
-
-### Linux & WSL2
-
-```
-curl https://ollama.ai/install.sh | sh
-```
-
-[Manual install instructions](https://github.com/jmorganca/ollama/blob/main/docs/linux.md)
-
-### Docker
-
-The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama` is available on Docker Hub.
+- [Download](https://ollama.ai/download) for macOS
+- Download for Windows and Linux (coming soon)
+- Build [from source](#building)
 
 ## Quickstart
 
-To run and chat with [Llama 2](https://ollama.ai/library/llama2):
+To run and chat with [Llama 2](https://ai.meta.com/llama), the new model by Meta:
 
 ```
 ollama run llama2
@@ -45,55 +33,83 @@ Ollama supports a list of open-source models available on [ollama.ai/library](ht
 
 Here are some example open-source models that can be downloaded:
 
-| Model              | Parameters | Size  | Download                       |
-| ------------------ | ---------- | ----- | ------------------------------ |
-| Llama 2            | 7B         | 3.8GB | `ollama run llama2`            |
-| Mistral            | 7B         | 4.1GB | `ollama run mistral`           |
-| Dolphin Phi        | 2.7B       | 1.6GB | `ollama run dolphin-phi`       |
-| Phi-2              | 2.7B       | 1.7GB | `ollama run phi`               |
-| 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`             |
+| Model                    | Parameters | Size  | Download                        |
+| ------------------------ | ---------- | ----- | ------------------------------- |
+| Llama2                   | 7B         | 3.8GB | `ollama pull llama2`            |
+| Llama2 13B               | 13B        | 7.3GB | `ollama pull llama2:13b`        |
+| Llama2 70B               | 70B        | 39GB  | `ollama pull llama2:70b`        |
+| Llama2 Uncensored        | 7B         | 3.8GB | `ollama pull llama2-uncensored` |
+| Code Llama               | 7B         | 3.8GB | `ollama pull codellama`         |
+| Orca Mini                | 3B         | 1.9GB | `ollama pull orca-mini`         |
+| Vicuna                   | 7B         | 3.8GB | `ollama pull vicuna`            |
+| Nous-Hermes              | 7B         | 3.8GB | `ollama pull nous-hermes`       |
+| Nous-Hermes 13B          | 13B        | 7.3GB | `ollama pull nous-hermes:13b`   |
+| Wizard Vicuna Uncensored | 13B        | 7.3GB | `ollama pull wizard-vicuna`     |
 
-> 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.
+> 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.
 
-## Customize a model
+## Examples
 
-### Import from GGUF
+### Pull a public model
 
-Ollama supports importing GGUF models in the Modelfile:
+```
+ollama pull llama2
+```
 
-1. Create a file named `Modelfile`, with a `FROM` instruction with the local filepath to the model you want to import.
+> This command can also be used to update a local model. Only updated changes will be pulled.
 
-   ```
-   FROM ./vicuna-33b.Q4_0.gguf
-   ```
+### Run a model interactively
 
-2. Create the model in Ollama
+```
+ollama run llama2
+>>> hi
+Hello! How can I help you today?
+```
 
-   ```
-   ollama create example -f Modelfile
-   ```
+For multiline input, you can wrap text with `"""`:
 
-3. Run the model
+```
+>>> """Hello,
+... world!
+... """
+I'm a basic program that prints the famous "Hello, world!" message to the console.
+```
 
-   ```
-   ollama run example
-   ```
+### Run a model non-interactively
 
-### Import from PyTorch or Safetensors
+```
+$ ollama run llama2 'tell me a joke'
+ Sure! Here's a quick one:
+ Why did the scarecrow win an award? Because he was outstanding in his field!
+```
 
-See the [guide](docs/import.md) on importing models for more information.
+```
+$ cat <<EOF >prompts.txt
+tell me a joke about llamas
+tell me another one
+EOF
+$ ollama run llama2 <prompts.txt
+>>> tell me a joke about llamas
+ Why did the llama refuse to play hide-and-seek?
+ nobody likes to be hided!
 
-### Customize a prompt
+>>> tell me another one
+ Sure, here's another one:
 
-Models from the Ollama library can be customized with a prompt. For example, to customize the `llama2` model:
+Why did the llama go to the bar?
+To have a hay-often good time!
+```
+
+### Run a model on contents of a text file
+
+```
+$ ollama run llama2 "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.
+```
+
+### Customize a model
+
+Pull a base model:
 
 ```
 ollama pull llama2
@@ -107,7 +123,7 @@ FROM llama2
 # set the temperature to 1 [higher is more creative, lower is more coherent]
 PARAMETER temperature 1
 
-# set the system message
+# set the system prompt
 SYSTEM """
 You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
 """
@@ -122,94 +138,47 @@ ollama run mario
 Hello! It's your friend Mario.
 ```
 
-For more examples, see the [examples](examples) directory. For more information on working with a Modelfile, see the [Modelfile](docs/modelfile.md) documentation.
+For more examples, see the [examples](./examples) directory. For more information on creating a Modelfile, see the [Modelfile](./docs/modelfile.md) documentation.
 
-## CLI Reference
-
-### Create a model
-
-`ollama create` is used to create a model from a Modelfile.
-
-```
-ollama create mymodel -f ./Modelfile
-```
-
-### Pull a model
-
-```
-ollama pull llama2
-```
-
-> This command can also be used to update a local model. Only the diff will be pulled.
-
-### Remove a model
-
-```
-ollama rm llama2
-```
-
-### Copy a model
-
-```
-ollama cp llama2 my-llama2
-```
-
-### Multiline input
-
-For multiline input, you can wrap text with `"""`:
-
-```
->>> """Hello,
-... world!
-... """
-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 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.
-```
-
-### List models on your computer
+### Listing local models
 
 ```
 ollama list
 ```
 
-### Start Ollama
+### Removing local models
 
-`ollama serve` is used when you want to start ollama without running the desktop application.
+```
+ollama rm llama2
+```
+
+## Model packages
+
+### Overview
+
+Ollama bundles model weights, configurations, and data into a single package, defined by a [Modelfile](./docs/modelfile.md).
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" height="480" srcset="https://github.com/jmorganca/ollama/assets/251292/2fd96b5f-191b-45c1-9668-941cfad4eb70">
+  <img alt="logo" height="480" src="https://github.com/jmorganca/ollama/assets/251292/2fd96b5f-191b-45c1-9668-941cfad4eb70">
+</picture>
 
 ## Building
 
 Install `cmake` and `go`:
 
 ```
-brew install cmake go
+brew install cmake
+brew install go
 ```
 
-Then generate dependencies:
+Then generate dependencies and build:
+
 ```
 go generate ./...
-```
-Then build the binary:
-```
 go build .
 ```
 
-More detailed instructions can be found in the [developer guide](https://github.com/jmorganca/ollama/blob/main/docs/development.md)
-
-
-### Running local builds
 Next, start the server:
 
 ```
@@ -224,107 +193,23 @@ Finally, in a separate shell, run a model:
 
 ## REST API
 
-Ollama has a REST API for running and managing models.
+> See the [API documentation](./docs/api.md) for all endpoints.
 
-### Generate a response
+Ollama has an API for running and managing models. For example to generate text from a model:
 
 ```
-curl http://localhost:11434/api/generate -d '{
+curl -X POST http://localhost:11434/api/generate -d '{
   "model": "llama2",
   "prompt":"Why is the sky blue?"
 }'
 ```
 
-### Chat with a model
+## Community Projects using Ollama
 
-```
-curl http://localhost:11434/api/chat -d '{
-  "model": "mistral",
-  "messages": [
-    { "role": "user", "content": "why is the sky blue?" }
-  ]
-}'
-```
-
-See the [API documentation](./docs/api.md) for all endpoints.
-
-## Integrations
-
-- [ollama-python](https://github.com/jmorganca/ollama-python)
-
-## Community Integrations
-
-### Web & Desktop
-- [Bionic GPT](https://github.com/bionic-gpt/bionic-gpt)
-- [HTML UI](https://github.com/rtcfirefly/ollama-ui)
-- [Chatbot UI](https://github.com/ivanfioravanti/chatbot-ollama)
-- [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)
-- [Web UI](https://github.com/ollama-webui/ollama-webui)
-- [Ollamac](https://github.com/kevinhermawan/Ollamac)
-- [big-AGI](https://github.com/enricoros/big-agi/blob/main/docs/config-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)
-
-
-### 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)
-- [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)
-
-### Database
-
-- [MindsDB](https://github.com/mindsdb/mindsdb/blob/staging/mindsdb/integrations/handlers/ollama_handler/README.md)
-
-### Package managers
-
-- [Pacman](https://archlinux.org/packages/extra/x86_64/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)
-- [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)
-
-
-### 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)
-- [Dagger Chatbot](https://github.com/samalba/dagger-chatbot)
-- [Discord AI Bot](https://github.com/mekb-turtle/discord-ai-bot)
-- [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)
-- [Open Interpreter](https://docs.openinterpreter.com/language-model-setup/local-models/ollama)
+- [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 a question-answering [example](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa).
+- [Continue](https://github.com/continuedev/continue) - embeds Ollama inside Visual Studio Code. The extension lets you highlight code to add to the prompt, ask questions in the sidebar, and generate code inline.
+- [LiteLLM](https://github.com/BerriAI/litellm) a lightweight python package to simplify LLM API calls
+- [Discord AI Bot](https://github.com/mekb-turtle/discord-ai-bot) - interact with Ollama as a chatbot on Discord.
+- [Raycast Ollama](https://github.com/MassimilianoPasquini97/raycast_ollama) - Raycast extension to use Ollama for local llama inference on Raycast.
+- [Simple HTML UI for Ollama](https://github.com/rtcfirefly/ollama-ui)
+- [Emacs client](https://github.com/zweifisch/ollama) for Ollama

api/client.go

@@ -5,23 +5,27 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
-	"errors"
 	"fmt"
 	"io"
-	"net"
 	"net/http"
 	"net/url"
 	"os"
 	"runtime"
 	"strings"
 
-	"github.com/jmorganca/ollama/format"
 	"github.com/jmorganca/ollama/version"
 )
 
+const DefaultHost = "127.0.0.1:11434"
+
+var (
+	envHost = os.Getenv("OLLAMA_HOST")
+)
+
 type Client struct {
-	base *url.URL
-	http http.Client
+	Base    url.URL
+	HTTP    http.Client
+	Headers http.Header
 }
 
 func checkError(resp *http.Response, body []byte) error {
@@ -40,79 +44,49 @@ func checkError(resp *http.Response, body []byte) error {
 	return apiError
 }
 
-func ClientFromEnvironment() (*Client, error) {
-	defaultPort := "11434"
+// Host returns the default host to use for the client. It is determined in the following order:
+// 1. The OLLAMA_HOST environment variable
+// 2. The default host (localhost:11434)
+func Host() string {
+	if envHost != "" {
+		return envHost
+	}
+	return DefaultHost
+}
 
-	scheme, hostport, ok := strings.Cut(os.Getenv("OLLAMA_HOST"), "://")
-	switch {
-	case !ok:
-		scheme, hostport = "http", os.Getenv("OLLAMA_HOST")
-	case scheme == "http":
-		defaultPort = "80"
-	case scheme == "https":
-		defaultPort = "443"
+// FromEnv creates a new client using Host() as the host. An error is returns
+// if the host is invalid.
+func FromEnv() (*Client, error) {
+	h := Host()
+	if !strings.HasPrefix(h, "http://") && !strings.HasPrefix(h, "https://") {
+		h = "http://" + h
 	}
 
-	// trim trailing slashes
-	hostport = strings.TrimRight(hostport, "/")
-
-	host, port, err := net.SplitHostPort(hostport)
+	u, err := url.Parse(h)
 	if err != nil {
-		host, port = "127.0.0.1", defaultPort
-		if ip := net.ParseIP(strings.Trim(hostport, "[]")); ip != nil {
-			host = ip.String()
-		} else if hostport != "" {
-			host = hostport
-		}
+		return nil, fmt.Errorf("could not parse host: %w", err)
 	}
 
-	client := Client{
-		base: &url.URL{
-			Scheme: scheme,
-			Host:   net.JoinHostPort(host, port),
-		},
+	if u.Port() == "" {
+		u.Host += ":11434"
 	}
 
-	mockRequest, err := http.NewRequest(http.MethodHead, client.base.String(), nil)
-	if err != nil {
-		return nil, err
-	}
-
-	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
+	return &Client{Base: *u, HTTP: http.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
-
-	switch reqData := reqData.(type) {
-	case io.Reader:
-		// reqData is already an io.Reader
-		reqBody = reqData
-	case nil:
-		// noop
-	default:
+	if reqData != nil {
 		data, err = json.Marshal(reqData)
 		if err != nil {
 			return err
 		}
-
 		reqBody = bytes.NewReader(data)
 	}
 
-	requestURL := c.base.JoinPath(path)
+	requestURL := c.Base.JoinPath(path)
 	request, err := http.NewRequestWithContext(ctx, method, requestURL.String(), reqBody)
 	if err != nil {
 		return err
@@ -122,7 +96,11 @@ func (c *Client) do(ctx context.Context, method, path string, reqData, respData
 	request.Header.Set("Accept", "application/json")
 	request.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))
 
-	respObj, err := c.http.Do(request)
+	for k, v := range c.Headers {
+		request.Header[k] = v
+	}
+
+	respObj, err := c.HTTP.Do(request)
 	if err != nil {
 		return err
 	}
@@ -145,8 +123,6 @@ func (c *Client) do(ctx context.Context, method, path string, reqData, respData
 	return nil
 }
 
-const maxBufferSize = 512 * format.KiloByte
-
 func (c *Client) stream(ctx context.Context, method, path string, data any, fn func([]byte) error) error {
 	var buf *bytes.Buffer
 	if data != nil {
@@ -158,26 +134,23 @@ func (c *Client) stream(ctx context.Context, method, path string, data any, fn f
 		buf = bytes.NewBuffer(bts)
 	}
 
-	requestURL := c.base.JoinPath(path)
+	requestURL := c.Base.JoinPath(path)
 	request, err := http.NewRequestWithContext(ctx, method, requestURL.String(), buf)
 	if err != nil {
 		return err
 	}
 
 	request.Header.Set("Content-Type", "application/json")
-	request.Header.Set("Accept", "application/x-ndjson")
+	request.Header.Set("Accept", "application/json")
 	request.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))
 
-	response, err := c.http.Do(request)
+	response, err := http.DefaultClient.Do(request)
 	if err != nil {
 		return err
 	}
 	defer response.Body.Close()
 
 	scanner := bufio.NewScanner(response.Body)
-	// increase the buffer size to avoid running out of space
-	scanBuf := make([]byte, 0, maxBufferSize)
-	scanner.Buffer(scanBuf, maxBufferSize)
 	for scanner.Scan() {
 		var errorResponse struct {
 			Error string `json:"error,omitempty"`
@@ -221,19 +194,6 @@ func (c *Client) Generate(ctx context.Context, req *GenerateRequest, fn Generate
 	})
 }
 
-type ChatResponseFunc func(ChatResponse) error
-
-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)
-	})
-}
-
 type PullProgressFunc func(ProgressResponse) error
 
 func (c *Client) Pull(ctx context.Context, req *PullRequest, fn PullProgressFunc) error {
@@ -309,37 +269,3 @@ 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 {
-	if err := c.do(ctx, http.MethodHead, fmt.Sprintf("/api/blobs/%s", digest), nil, nil); err != nil {
-		var statusError StatusError
-		if !errors.As(err, &statusError) || statusError.StatusCode != http.StatusNotFound {
-			return err
-		}
-
-		if err := c.do(ctx, http.MethodPost, fmt.Sprintf("/api/blobs/%s", digest), r, nil); err != nil {
-			return err
-		}
-	}
-
-	return 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
-}

api/client_test.go

@@ -1,43 +0,0 @@
-package api
-
-import "testing"
-
-func TestClientFromEnvironment(t *testing.T) {
-	type testCase struct {
-		value  string
-		expect string
-		err    error
-	}
-
-	testCases := map[string]*testCase{
-		"empty":                      {value: "", expect: "http://127.0.0.1:11434"},
-		"only address":               {value: "1.2.3.4", expect: "http://1.2.3.4:11434"},
-		"only port":                  {value: ":1234", expect: "http://:1234"},
-		"address and port":           {value: "1.2.3.4:1234", expect: "http://1.2.3.4:1234"},
-		"scheme http and address":    {value: "http://1.2.3.4", expect: "http://1.2.3.4:80"},
-		"scheme https and address":   {value: "https://1.2.3.4", expect: "https://1.2.3.4:443"},
-		"scheme, address, and port":  {value: "https://1.2.3.4:1234", expect: "https://1.2.3.4:1234"},
-		"hostname":                   {value: "example.com", expect: "http://example.com:11434"},
-		"hostname and port":          {value: "example.com:1234", expect: "http://example.com:1234"},
-		"scheme http and hostname":   {value: "http://example.com", expect: "http://example.com:80"},
-		"scheme https and hostname":  {value: "https://example.com", expect: "https://example.com:443"},
-		"scheme, hostname, and port": {value: "https://example.com:1234", expect: "https://example.com:1234"},
-		"trailing slash":             {value: "example.com/", expect: "http://example.com:11434"},
-		"trailing slash port":        {value: "example.com:1234/", expect: "http://example.com:1234"},
-	}
-
-	for k, v := range testCases {
-		t.Run(k, func(t *testing.T) {
-			t.Setenv("OLLAMA_HOST", v.value)
-
-			client, err := ClientFromEnvironment()
-			if err != v.err {
-				t.Fatalf("expected %s, got %s", v.err, err)
-			}
-
-			if client.base.String() != v.expect {
-				t.Fatalf("expected %s, got %s", v.expect, client.base.String())
-			}
-		})
-	}
-}

api/types.go

@@ -3,10 +3,10 @@ package api
 import (
 	"encoding/json"
 	"fmt"
+	"log"
 	"math"
 	"os"
 	"reflect"
-	"strconv"
 	"strings"
 	"time"
 )
@@ -31,48 +31,97 @@ func (e StatusError) Error() string {
 	}
 }
 
-type ImageData []byte
-
 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"`
-	Raw      bool        `json:"raw,omitempty"`
-	Format   string      `json:"format"`
-	Images   []ImageData `json:"images,omitempty"`
+	Model    string `json:"model"`
+	Prompt   string `json:"prompt"`
+	System   string `json:"system"`
+	Template string `json:"template"`
+	Context  []int  `json:"context,omitempty"`
 
 	Options map[string]interface{} `json:"options"`
 }
 
-type ChatRequest struct {
-	Model    string    `json:"model"`
-	Messages []Message `json:"messages"`
-	Stream   *bool     `json:"stream,omitempty"`
-	Format   string    `json:"format"`
+type EmbeddingRequest struct {
+	Model  string `json:"model"`
+	Prompt string `json:"prompt"`
 
 	Options map[string]interface{} `json:"options"`
 }
 
-type Message struct {
-	Role    string      `json:"role"` // one of ["system", "user", "assistant"]
-	Content string      `json:"content"`
-	Images  []ImageData `json:"images,omitempty"`
+type EmbeddingResponse struct {
+	Embedding []float64 `json:"embedding"`
 }
 
-type ChatResponse struct {
+type CreateRequest struct {
+	Name string `json:"name"`
+	Path string `json:"path"`
+}
+
+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"`
+}
+
+type ProgressResponse struct {
+	Status    string `json:"status"`
+	Digest    string `json:"digest,omitempty"`
+	Total     int    `json:"total,omitempty"`
+	Completed int    `json:"completed,omitempty"`
+}
+
+type PushRequest struct {
+	Name     string `json:"name"`
+	Insecure bool   `json:"insecure,omitempty"`
+	Username string `json:"username"`
+	Password string `json:"password"`
+}
+
+type ListResponse struct {
+	Models []ModelResponse `json:"models"`
+}
+
+type ModelResponse struct {
+	Name       string    `json:"name"`
+	ModifiedAt time.Time `json:"modified_at"`
+	Size       int       `json:"size"`
+	Digest     string    `json:"digest"`
+}
+
+type TokenResponse struct {
+	Token string `json:"token"`
+}
+
+type GenerateResponse struct {
 	Model     string    `json:"model"`
 	CreatedAt time.Time `json:"created_at"`
-	Message   Message   `json:"message"`
+	Response  string    `json:"response,omitempty"`
 
-	Done bool `json:"done"`
+	Done    bool  `json:"done"`
+	Context []int `json:"context,omitempty"`
 
-	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"`
@@ -81,13 +130,58 @@ type Metrics struct {
 	EvalDuration       time.Duration `json:"eval_duration,omitempty"`
 }
 
-// Options specfied in GenerateRequest, if you add a new option here add it to the API docs also
-type Options struct {
-	Runner
+func (r *GenerateResponse) Summary() {
+	if r.TotalDuration > 0 {
+		fmt.Fprintf(os.Stderr, "total duration:       %v\n", r.TotalDuration)
+	}
 
-	// Predict options used at runtime
-	NumKeep          int      `json:"num_keep,omitempty"`
-	Seed             int      `json:"seed,omitempty"`
+	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())
+	}
+}
+
+type Options struct {
+	Seed int `json:"seed,omitempty"`
+
+	// Backend options
+	UseNUMA bool `json:"numa,omitempty"`
+
+	// Model options
+	NumCtx             int     `json:"num_ctx,omitempty"`
+	NumKeep            int     `json:"num_keep,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"`
+
+	// Predict options
 	NumPredict       int      `json:"num_predict,omitempty"`
 	TopK             int      `json:"top_k,omitempty"`
 	TopP             float32  `json:"top_p,omitempty"`
@@ -103,176 +197,10 @@ type Options struct {
 	MirostatEta      float32  `json:"mirostat_eta,omitempty"`
 	PenalizeNewline  bool     `json:"penalize_newline,omitempty"`
 	Stop             []string `json:"stop,omitempty"`
+
+	NumThread int `json:"num_thread,omitempty"`
 }
 
-// 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"`
-}
-
-type EmbeddingRequest struct {
-	Model  string `json:"model"`
-	Prompt string `json:"prompt"`
-
-	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"`
-
-	// 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"`
-}
-
-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 {
-	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 = fmt.Errorf("invalid options")
-
 func (opts *Options) FromMap(m map[string]interface{}) error {
 	valueOpts := reflect.ValueOf(opts).Elem() // names of the fields in the options struct
 	typeOpts := reflect.TypeOf(opts).Elem()   // types of the fields in the options struct
@@ -286,7 +214,6 @@ func (opts *Options) FromMap(m map[string]interface{}) error {
 		}
 	}
 
-	invalidOpts := []string{}
 	for key, val := range m {
 		if opt, ok := jsonOpts[key]; ok {
 			field := valueOpts.FieldByName(opt.Name)
@@ -304,39 +231,44 @@ func (opts *Options) FromMap(m map[string]interface{}) error {
 						// when JSON unmarshals numbers, it uses float64, not int
 						field.SetInt(int64(t))
 					default:
-						return fmt.Errorf("option %q must be of type integer", key)
+						log.Printf("could not convert model parameter %v to int, skipped", key)
 					}
 				case reflect.Bool:
 					val, ok := val.(bool)
 					if !ok {
-						return fmt.Errorf("option %q must be of type boolean", key)
+						log.Printf("could not convert model parameter %v to bool, skipped", key)
+						continue
 					}
 					field.SetBool(val)
 				case reflect.Float32:
 					// JSON unmarshals to float64
 					val, ok := val.(float64)
 					if !ok {
-						return fmt.Errorf("option %q must be of type float32", key)
+						log.Printf("could not convert model parameter %v to float32, skipped", key)
+						continue
 					}
 					field.SetFloat(val)
 				case reflect.String:
 					val, ok := val.(string)
 					if !ok {
-						return fmt.Errorf("option %q must be of type string", key)
+						log.Printf("could not convert model parameter %v to string, skipped", key)
+						continue
 					}
 					field.SetString(val)
 				case reflect.Slice:
 					// JSON unmarshals to []interface{}, not []string
 					val, ok := val.([]interface{})
 					if !ok {
-						return fmt.Errorf("option %q must be of type array", key)
+						log.Printf("could not convert model parameter %v to slice, skipped", key)
+						continue
 					}
 					// convert []interface{} to []string
 					slice := make([]string, len(val))
 					for i, item := range val {
 						str, ok := item.(string)
 						if !ok {
-							return fmt.Errorf("option %q must be of an array of strings", key)
+							log.Printf("could not convert model parameter %v to slice of strings, skipped", key)
+							continue
 						}
 						slice[i] = str
 					}
@@ -345,53 +277,45 @@ func (opts *Options) FromMap(m map[string]interface{}) error {
 					return fmt.Errorf("unknown type loading config params: %v", field.Kind())
 				}
 			}
-		} else {
-			invalidOpts = append(invalidOpts, key)
 		}
 	}
-
-	if len(invalidOpts) > 0 {
-		return fmt.Errorf("%w: %v", ErrInvalidOpts, strings.Join(invalidOpts, ", "))
-	}
 	return nil
 }
 
 func DefaultOptions() Options {
 	return Options{
-		// options set on request to runner
-		NumPredict:       -1,
-		NumKeep:          0,
+		Seed: -1,
+
+		UseNUMA: false,
+
+		NumCtx:             2048,
+		NumKeep:            -1,
+		NumBatch:           512,
+		NumGPU:             -1, // -1 here indicates that NumGPU should be set dynamically
+		NumGQA:             1,
+		LowVRAM:            false,
+		F16KV:              true,
+		UseMMap:            true,
+		UseMLock:           false,
+		RopeFrequencyBase:  10000.0,
+		RopeFrequencyScale: 1.0,
+		EmbeddingOnly:      true,
+
+		RepeatLastN:      64,
+		RepeatPenalty:    1.1,
+		FrequencyPenalty: 0.0,
+		PresencePenalty:  0.0,
 		Temperature:      0.8,
 		TopK:             40,
 		TopP:             0.9,
 		TFSZ:             1.0,
 		TypicalP:         1.0,
-		RepeatLastN:      64,
-		RepeatPenalty:    1.1,
-		PresencePenalty:  0.0,
-		FrequencyPenalty: 0.0,
 		Mirostat:         0,
 		MirostatTau:      5.0,
 		MirostatEta:      0.1,
 		PenalizeNewline:  true,
-		Seed:             -1,
 
-		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,
-		},
+		NumThread: 0, // let the runtime decide
 	}
 }
 
@@ -423,63 +347,3 @@ func (d *Duration) UnmarshalJSON(b []byte) (err error) {
 
 	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
-}

app/forge.config.ts

@@ -47,6 +47,16 @@ const config: ForgeConfig = {
   },
   rebuildConfig: {},
   makers: [new MakerSquirrel({}), new MakerZIP({}, ['darwin'])],
+  publishers: [
+    new PublisherGithub({
+      repository: {
+        name: 'ollama',
+        owner: 'jmorganca',
+      },
+      draft: false,
+      prerelease: true,
+    }),
+  ],
   hooks: {
     readPackageJson: async (_, packageJson) => {
       return { ...packageJson, version: process.env.VERSION || packageJson.version }

app/package.json

@@ -46,7 +46,7 @@
     "chmodr": "^1.2.0",
     "copy-webpack-plugin": "^11.0.0",
     "css-loader": "^6.8.1",
-    "electron": "25.9.2",
+    "electron": "25.2.0",
     "eslint": "^8.43.0",
     "eslint-plugin-import": "^2.27.5",
     "fork-ts-checker-webpack-plugin": "^7.3.0",

app/src/index.ts

@@ -5,7 +5,7 @@ import winston from 'winston'
 import 'winston-daily-rotate-file'
 import * as path from 'path'
 
-import { v4 as uuidv4 } from 'uuid'
+import { analytics, id } from './telemetry'
 import { installed } from './install'
 
 require('@electron/remote/main').initialize()
@@ -162,56 +162,13 @@ app.on('before-quit', () => {
   }
 })
 
-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()
+    heartbeat()
+    autoUpdater.checkForUpdates()
     setInterval(() => {
-      checkUpdate()
+      heartbeat()
+      autoUpdater.checkForUpdates()
     }, 60 * 60 * 1000)
   }
 
@@ -277,22 +234,28 @@ app.on('window-all-closed', () => {
   }
 })
 
-function id(): string {
-  const id = store.get('id') as string
+// In this file you can include the rest of your app's specific main process
+// code. You can also put them in separate files and import them here.
+let aid = ''
+try {
+  aid = id()
+} catch (e) {}
 
-  if (id) {
-    return id
-  }
+autoUpdater.setFeedURL({
+  url: `https://ollama.ai/api/update?os=${process.platform}&arch=${process.arch}&version=${app.getVersion()}&id=${aid}`,
+})
 
-  const uuid = uuidv4()
-  store.set('id', uuid)
-  return uuid
+async function heartbeat() {
+  analytics.track({
+    anonymousId: aid,
+    event: 'heartbeat',
+    properties: {
+      version: app.getVersion(),
+    },
+  })
 }
 
-autoUpdater.setFeedURL({ url: updateURL })
-
 autoUpdater.on('error', e => {
-  logger.error(`update check failed - ${e.message}`)
   console.error(`update check failed - ${e.message}`)
 })
 

app/src/telemetry.ts

@@ -0,0 +1,19 @@
+import { Analytics } from '@segment/analytics-node'
+import { v4 as uuidv4 } from 'uuid'
+import Store from 'electron-store'
+
+const store = new Store()
+
+export const analytics = new Analytics({ writeKey: process.env.TELEMETRY_WRITE_KEY || '<empty>' })
+
+export function id(): string {
+  const id = store.get('id') as string
+
+  if (id) {
+    return id
+  }
+
+  const uuid = uuidv4()
+  store.set('id', uuid)
+  return uuid
+}

cmd/interactive.go

@@ -1,555 +0,0 @@
-package cmd
-
-import (
-	"errors"
-	"fmt"
-	"io"
-	"net/http"
-	"os"
-	"regexp"
-	"strings"
-
-	"github.com/spf13/cobra"
-	"golang.org/x/exp/slices"
-
-	"github.com/jmorganca/ollama/api"
-	"github.com/jmorganca/ollama/readline"
-)
-
-type MultilineState int
-
-const (
-	MultilineNone MultilineState = iota
-	MultilinePrompt
-	MultilineSystem
-	MultilineTemplate
-)
-
-func modelIsMultiModal(cmd *cobra.Command, name string) bool {
-	// get model details
-	client, err := api.ClientFromEnvironment()
-	if err != nil {
-		fmt.Println("error: couldn't connect to ollama server")
-		return false
-	}
-
-	req := api.ShowRequest{Name: name}
-	resp, err := client.Show(cmd.Context(), &req)
-	if err != nil {
-		return false
-	}
-
-	return slices.Contains(resp.Details.Families, "clip")
-}
-
-func generateInteractive(cmd *cobra.Command, opts runOptions) error {
-	multiModal := modelIsMultiModal(cmd, opts.Model)
-
-	// load the model
-	loadOpts := runOptions{
-		Model:    opts.Model,
-		Prompt:   "",
-		Messages: []api.Message{},
-	}
-	if _, err := chat(cmd, loadOpts); 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, "  /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.")
-		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
-	opts.Messages = make([]api.Message, 0)
-
-	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()
-				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
-				break
-			}
-		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, "/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":
-					cmd.Flags().Set("verbose", "true")
-					fmt.Println("Set 'verbose' mode.")
-				case "quiet":
-					cmd.Flags().Set("verbose", "false")
-					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()
-						fmt.Println("Set system message.")
-					} else if args[1] == "template" {
-						opts.Template = sb.String()
-						fmt.Println("Set prompt template.")
-					}
-
-					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 line == "/exit", line == "/bye":
-			return nil
-		case strings.HasPrefix(line, "/"):
-			args := strings.Fields(line)
-			isFile := false
-
-			if 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 multiModal {
-				msg, images, err := extractFileData(sb.String())
-				if err != nil {
-					return err
-				}
-				newMessage.Content = msg
-
-				// reset the context if we find another image
-				if len(images) > 0 {
-					newMessage.Images = append(newMessage.Images, images...)
-					// reset the context for the new image
-					opts.Messages = []api.Message{}
-				} else {
-					if len(opts.Messages) > 1 {
-						newMessage.Images = append(newMessage.Images, opts.Messages[len(opts.Messages)-2].Images...)
-					}
-				}
-				if len(newMessage.Images) == 0 {
-					fmt.Println("This model requires you to add a jpeg, png, or svg image.")
-					fmt.Println()
-					sb.Reset()
-					continue
-				}
-			}
-
-			if opts.System != "" {
-				opts.Messages = append(opts.Messages, api.Message{Role: "system", Content: opts.System})
-			}
-			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 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.Printf("Couldn't process image: %q\n", err)
-			return "", imgs, err
-		}
-		fmt.Printf("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/svg+xml", "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
-}

cmd/interactive_test.go

@@ -1,51 +0,0 @@
-package cmd
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-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:")
-}

cmd/spinner.go

@@ -0,0 +1,44 @@
+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)
+}

docs/README.md

@@ -1,25 +1,6 @@
 # Documentation
 
-To get started, see the project's **[quickstart](../README.md#quickstart)**.
-
-Ollama is a tool for running AI models on your hardware. Many users will choose to use the Command Line Interface (CLI) to work with Ollama. Learn more about all the commands in the CLI in the **[Main Readme](../README.md)**.
-
-Use the RESTful API using any language, including Python, JavaScript, Typescript, Go, Rust, and many more. Learn more about using the API in the **[API Documentation](./api.md)**.
-
-Create new models or modify models already in the library using the Modelfile. Learn more about the Modelfile syntax in the **[Modelfile Documentation](./modelfile.md)**.
-
-Import models using source model weights found on Hugging Face and similar sites by referring to the **[Import Documentation](./import.md)**.
-
-Installing on Linux in most cases is easy using the script on Ollama.ai. To get more detail about the install, including CUDA drivers, see the **[Linux Documentation](./linux.md)**.
-
-Many of our users like the flexibility of using our official Docker Image. Learn more about using Docker with Ollama using the **[Docker Documentation](https://hub.docker.com/r/ollama/ollama)**.
-
-It is easy to install on Linux and Mac, but many users will choose to build Ollama on their own. To do this, refer to the **[Development Documentation](./development.md)**.
-
-If encountering a problem with Ollama, the best place to start is the logs. Find more information about them here in the **[Troubleshooting Guide](./troubleshooting.md)**.
-
-Finally for all the questions that don't fit anywhere else, there is the **[FAQ](./faq.md)**
-
-[Tutorials](./tutorials.md) apply the documentation to tasks.
-
-For working code examples of using Ollama, see [Examples](../examples).
+- [Modelfile](./modelfile.md)
+- [How to develop Ollama](./development.md)
+- [API](./api.md)
+- [Tutorials](./tutorials.md)

docs/development.md

@@ -1,136 +1,39 @@
 # Development
 
+- Install cmake or (optionally, required tools for GPUs)
+- run `go generate ./...`
+- run `go build .`
+
 Install required tools:
 
 - cmake version 3.24 or higher
-- go version 1.21 or higher
+- go version 1.20 or higher
 - gcc version 11.4.0 or higher
 
-```bash
+```
 brew install go cmake gcc
 ```
 
-Optionally enable debugging and more verbose logging:
+Get the required libraries:
 
-```bash
-# At build time
-export CGO_CFLAGS="-g"
-
-# At runtime
-export OLLAMA_DEBUG=1
 ```
-
-Get the required libraries and build the native LLM code:
-
-```bash
 go generate ./...
 ```
 
 Then build ollama:
 
-```bash
+```
 go build .
 ```
 
 Now you can run `ollama`:
 
-```bash
+```
 ./ollama
 ```
 
-### Linux
+## Building on Linux with GPU support
 
-#### Linux CUDA (NVIDIA)
-
-*Your operating system distribution may already have packages for NVIDIA CUDA. Distro packages are often preferable, but instructions are distro-specific. Please consult distro-specific docs for dependencies if available!*
-
-Install `cmake` and `golang` as well as [NVIDIA CUDA](https://developer.nvidia.com/cuda-downloads)
-development and runtime packages. 
-
-Typically the build scripts will auto-detect CUDA, however, if your Linux distro
-or installation approach uses unusual paths, you can specify the location by
-specifying an environment variable `CUDA_LIB_DIR` to the location of the shared
-libraries, and `CUDACXX` to the location of the nvcc compiler.
-
-Then generate dependencies:
-
-```
-go generate ./...
-```
-
-Then build the binary:
-
-```
-go build .
-```
-
-#### Linux ROCm (AMD)
-
-*Your operating system distribution may already have packages for AMD ROCm and CLBlast. Distro packages are often preferable, but instructions are distro-specific. Please consult distro-specific docs for dependencies if available!*
-
-Install [CLBlast](https://github.com/CNugteren/CLBlast/blob/master/doc/installation.md) and [ROCm](https://rocm.docs.amd.com/en/latest/deploy/linux/quick_start.html) developement packages first, as well as `cmake` and `golang`.
-
-Typically the build scripts will auto-detect ROCm, however, if your Linux distro
-or installation approach uses unusual paths, you can specify the location by
-specifying an environment variable `ROCM_PATH` to the location of the ROCm
-install (typically `/opt/rocm`), and `CLBlast_DIR` to the location of the
-CLBlast install (typically `/usr/lib/cmake/CLBlast`).
-
-```
-go generate ./...
-```
-
-Then build the binary:
-
-```
-go build .
-```
-
-ROCm requires elevated privileges to access the GPU at runtime.  On most distros you can add your user account to the `render` group, or run as root.
-
-#### Advanced CPU Settings
-
-By default, running `go generate ./...` will compile a few different variations
-of the LLM library based on common CPU families and vector math capabilities,
-including a lowest-common-denominator which should run on almost any 64 bit CPU
-somewhat slowly.  At runtime, Ollama will auto-detect the optimal variation to
-load.  If you would like to build a CPU-based build customized for your
-processor, you can set `OLLAMA_CUSTOM_CPU_DEFS` to the llama.cpp flags you would
-like to use.  For example, to compile an optimized binary for an Intel i9-9880H,
-you might use:
-
-```
-OLLAMA_CUSTOM_CPU_DEFS="-DLLAMA_AVX=on -DLLAMA_AVX2=on -DLLAMA_F16C=on -DLLAMA_FMA=on" go generate ./...
-go build .
-```
-
-#### Containerized Linux Build
-
-If you have Docker available, you can build linux binaries with `./scripts/build_linux.sh` which has the CUDA and ROCm dependencies included.  The resulting binary is placed in `./dist`
-
-
-### Windows
-
-Note: The windows build for Ollama is still under development.
-
-Install required tools:
-
-- MSVC toolchain - C/C++ and cmake as minimal requirements
-- go version 1.21 or higher
-- MinGW (pick one variant) with GCC.
-  - <https://www.mingw-w64.org/>
-  - <https://www.msys2.org/>
-
-```powershell
-$env:CGO_ENABLED="1"
-
-go generate ./...
-
-go build .
-```
-
-#### Windows CUDA (NVIDIA)
-
-In addition to the common Windows development tools described above, install:
-
-- [NVIDIA CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html)
+- Install cmake and nvidia-cuda-toolkit
+- run `go generate ./...`
+- run `go build .`

docs/faq.md

@@ -1,114 +1,17 @@
 # FAQ
 
-## How can I upgrade Ollama?
+## How can I expose the Ollama server?
 
-To upgrade Ollama, run the installation process again. On the Mac, click the Ollama icon in the menubar and choose the restart option if an update is available.
-
-## How can I view the logs?
-
-Review the [Troubleshooting](./troubleshooting.md) docs for more about using logs.
-
-## How do I use Ollama server environment variables on Mac
-
-On macOS, Ollama runs in the background and is managed by the menubar app. If adding environment variables, Ollama will need to be run manually.
-
-1. Click the menubar icon for Ollama and choose **Quit Ollama**.
-2. Open a new terminal window and run the following command (this example uses `OLLAMA_HOST` with an IP address of `123.1.1.1`):
-
-   ```bash
-   OLLAMA_HOST=123.1.1.1 ollama serve
-   ```
-
-## How do I use Ollama server environment variables on Linux?
-
-If Ollama is installed with the install script, a systemd service was created, running as the Ollama user. To add an environment variable, such as OLLAMA_HOST, follow these steps:
-
-1. Create a `systemd` drop-in directory and add a config file. This is only needed once.
-
-   ```bash
-   mkdir -p /etc/systemd/system/ollama.service.d
-   echo '[Service]' >>/etc/systemd/system/ollama.service.d/environment.conf
-   ```
-
-2. For each environment variable, add it to the config file:
-
-   ```bash
-   echo 'Environment="OLLAMA_HOST=0.0.0.0:11434"' >>/etc/systemd/system/ollama.service.d/environment.conf
-   ```
-
-3. Reload `systemd` and restart Ollama:
-
-   ```bash
-   systemctl daemon-reload
-   systemctl restart ollama
-   ```
-
-## How can I expose Ollama on my network?
-
-Ollama binds to 127.0.0.1 port 11434 by default. Change the bind address with the `OLLAMA_HOST` environment variable. Refer to the section above for how to use environment variables on your platform.
-
-## How can I allow additional web origins to access Ollama?
-
-Ollama allows cross-origin requests from `127.0.0.1` and `0.0.0.0` by default. Add additional origins with the `OLLAMA_ORIGINS` environment variable. For example, to add all ports on 192.168.1.1 and https://example.com, use:
-
-```shell
-OLLAMA_ORIGINS=http://192.168.1.1:*,https://example.com
+```
+OLLAMA_HOST=0.0.0.0:11435 ollama serve
 ```
 
-Refer to the section above for how to use environment variables on your platform.
+By default, Ollama allows cross origin requests from `127.0.0.1` and `0.0.0.0`. To support more origins, you can use the `OLLAMA_ORIGINS` environment variable:
+
+```
+OLLAMA_ORIGINS=http://192.168.1.1:*,https://example.com ollama serve
+```
 
 ## Where are models stored?
 
-- macOS: `~/.ollama/models`.
-- Linux: `/usr/share/ollama/.ollama/models`
-
-## How do I set them to a different location?
-
-If a different directory needs to be used, set the environment variable `OLLAMA_MODELS` to the chosen directory. Refer to the section above for how to use environment variables on your platform.
-
-## Does Ollama send my prompts and answers back to Ollama.ai to use in any way?
-
-No, Ollama runs entirely locally, and conversation data will never leave your machine.
-
-## How can I use Ollama in Visual Studio Code?
-
-There is already a large collection of plugins available for VSCode as well as other editors that leverage Ollama. See the list of [extensions & plugins](https://github.com/jmorganca/ollama#extensions--plugins) at the bottom of the main repository readme.
-
-## How do I use Ollama behind a proxy?
-
-Ollama is compatible with proxy servers if `HTTP_PROXY` or `HTTPS_PROXY` are configured. When using either variables, ensure it is set where `ollama serve` can access the values. When using `HTTPS_PROXY`, ensure the proxy certificate is installed as a system certificate. Refer to the section above for how to use environment variables on your platform.
-
-### How do I use Ollama behind a proxy in Docker?
-
-The Ollama Docker container image can be configured to use a proxy by passing `-e HTTPS_PROXY=https://proxy.example.com` when starting the container.
-
-Alternatively, the Docker daemon can be configured to use a proxy. Instructions are available for Docker Desktop on [macOS](https://docs.docker.com/desktop/settings/mac/#proxies), [Windows](https://docs.docker.com/desktop/settings/windows/#proxies), and [Linux](https://docs.docker.com/desktop/settings/linux/#proxies), and Docker [daemon with systemd](https://docs.docker.com/config/daemon/systemd/#httphttps-proxy).
-
-Ensure the certificate is installed as a system certificate when using HTTPS. This may require a new Docker image when using a self-signed certificate.
-
-```dockerfile
-FROM ollama/ollama
-COPY my-ca.pem /usr/local/share/ca-certificates/my-ca.crt
-RUN update-ca-certificates
-```
-
-Build and run this image:
-
-```shell
-docker build -t ollama-with-ca .
-docker run -d -e HTTPS_PROXY=https://my.proxy.example.com -p 11434:11434 ollama-with-ca
-```
-
-## How do I use Ollama with GPU acceleration in Docker?
-
-The Ollama Docker container can be configured with GPU acceleration in Linux or Windows (with WSL2). This requires the [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia-container-toolkit). See [ollama/ollama](https://hub.docker.com/r/ollama/ollama) for more details.
-
-GPU acceleration is not available for Docker Desktop in macOS due to the lack of GPU passthrough and emulation.
-
-## Why is networking slow in WSL2 on Windows 10?
-
-This can impact both installing Ollama, as well as downloading models.
-
-Open `Control Panel > Networking and Internet > View network status and tasks` and click on `Change adapter settings` on the left panel. Find the `vEthernel (WSL)` adapter, right click and select `Properties`.
-Click on `Configure` and open the `Advanced` tab. Search through each of the properties until you find `Large Send Offload Version 2 (IPv4)` and `Large Send Offload Version 2 (IPv6)`. *Disable* both of these
-properties.
+Raw model data is stored under `~/.ollama/models`.

docs/import.md

@@ -1,195 +0,0 @@
-# Import a model
-
-This guide walks through importing a GGUF, PyTorch or Safetensors model.
-
-## Importing (GGUF)
-
-### Step 1: Write a `Modelfile`
-
-Start by creating a `Modelfile`. This file is the blueprint for your model, specifying weights, parameters, prompt templates and more.
-
-```
-FROM ./mistral-7b-v0.1.Q4_0.gguf
-```
-
-(Optional) many chat models require a prompt template in order to answer correctly. A default prompt template can be specified with the `TEMPLATE` instruction in the `Modelfile`:
-
-```
-FROM ./q4_0.bin
-TEMPLATE "[INST] {{ .Prompt }} [/INST]"
-```
-
-### Step 2: Create the Ollama model
-
-Finally, create a model from your `Modelfile`:
-
-```
-ollama create example -f Modelfile
-```
-
-### Step 3: Run your model
-
-Next, test the model with `ollama run`:
-
-```
-ollama run example "What is your favourite condiment?"
-```
-
-## Importing (PyTorch & Safetensors)
-
-### Supported models
-
-Ollama supports a set of model architectures, with support for more coming soon:
-
-- Llama & Mistral
-- Falcon & RW
-- BigCode
-
-To view a model's architecture, check the `config.json` file in its HuggingFace repo. You should see an entry under `architectures` (e.g. `LlamaForCausalLM`).
-
-### Step 1: Clone the HuggingFace repository (optional)
-
-If the model is currently hosted in a HuggingFace repository, first clone that repository to download the raw model.
-
-```
-git lfs install
-git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
-cd Mistral-7B-Instruct-v0.1
-```
-
-### Step 2: Convert and quantize to a `.bin` file (optional, for PyTorch and Safetensors)
-
-If the model is in PyTorch or Safetensors format, a [Docker image](https://hub.docker.com/r/ollama/quantize) with the tooling required to convert and quantize models is available.
-
-First, Install [Docker](https://www.docker.com/get-started/).
-
-Next, to convert and quantize your model, run:
-
-```
-docker run --rm -v .:/model ollama/quantize -q q4_0 /model
-```
-
-This will output two files into the directory:
-
-- `f16.bin`: the model converted to GGUF
-- `q4_0.bin` the model quantized to a 4-bit quantization (Ollama will use this file to create the Ollama model)
-
-### Step 3: Write a `Modelfile`
-
-Next, create a `Modelfile` for your model:
-
-```
-FROM ./q4_0.bin
-```
-
-(Optional) many chat models require a prompt template in order to answer correctly. A default prompt template can be specified with the `TEMPLATE` instruction in the `Modelfile`:
-
-```
-FROM ./q4_0.bin
-TEMPLATE "[INST] {{ .Prompt }} [/INST]"
-```
-
-### Step 4: Create the Ollama model
-
-Finally, create a model from your `Modelfile`:
-
-```
-ollama create example -f Modelfile
-```
-
-### Step 5: Run your model
-
-Next, test the model with `ollama run`:
-
-```
-ollama run example "What is your favourite condiment?"
-```
-
-## Publishing your model (optional – early alpha)
-
-Publishing models is in early alpha. If you'd like to publish your model to share with others, follow these steps:
-
-1. Create [an account](https://ollama.ai/signup)
-2. Run `cat ~/.ollama/id_ed25519.pub` to view your Ollama public key. Copy this to the clipboard.
-3. Add your public key to your [Ollama account](https://ollama.ai/settings/keys)
-
-Next, copy your model to your username's namespace:
-
-```
-ollama cp example <your username>/example
-```
-
-Then push the model:
-
-```
-ollama push <your username>/example
-```
-
-After publishing, your model will be available at `https://ollama.ai/<your username>/example`.
-
-## Quantization reference
-
-The quantization options are as follow (from highest highest to lowest levels of quantization). Note: some architectures such as Falcon do not support K quants.
-
-- `q2_K`
-- `q3_K`
-- `q3_K_S`
-- `q3_K_M`
-- `q3_K_L`
-- `q4_0` (recommended)
-- `q4_1`
-- `q4_K`
-- `q4_K_S`
-- `q4_K_M`
-- `q5_0`
-- `q5_1`
-- `q5_K`
-- `q5_K_S`
-- `q5_K_M`
-- `q6_K`
-- `q8_0`
-- `f16`
-
-## Manually converting & quantizing models
-
-### Prerequisites
-
-Start by cloning the `llama.cpp` repo to your machine in another directory:
-
-```
-git clone https://github.com/ggerganov/llama.cpp.git
-cd llama.cpp
-```
-
-Next, install the Python dependencies:
-
-```
-pip install -r requirements.txt
-```
-
-Finally, build the `quantize` tool:
-
-```
-make quantize
-```
-
-### Convert the model
-
-Run the correct conversion script for your model architecture:
-
-```shell
-# LlamaForCausalLM or MistralForCausalLM
-python convert.py <path to model directory>
-
-# FalconForCausalLM
-python convert-falcon-hf-to-gguf.py <path to model directory>
-
-# GPTBigCodeForCausalLM
-python convert-starcoder-hf-to-gguf.py <path to model directory>
-```
-
-### Quantize the model
-
-```
-quantize <path to model dir>/ggml-model-f32.bin <path to model dir>/q4_0.bin q4_0
-```

docs/linux.md

@@ -1,117 +0,0 @@
-# Ollama on Linux
-
-## Install
-
-Install Ollama running this one-liner:
->
-```bash
-curl https://ollama.ai/install.sh | sh
-```
-
-## Manual install
-
-### Download the `ollama` binary
-
-Ollama is distributed as a self-contained binary. Download it to a directory in your PATH:
-
-```bash
-sudo curl -L https://ollama.ai/download/ollama-linux-amd64 -o /usr/bin/ollama
-sudo chmod +x /usr/bin/ollama
-```
-
-### Adding Ollama as a startup service (recommended)
-
-Create a user for Ollama:
-
-```bash
-sudo useradd -r -s /bin/false -m -d /usr/share/ollama ollama
-```
-
-Create a service file in `/etc/systemd/system/ollama.service`:
-
-```ini
-[Unit]
-Description=Ollama Service
-After=network-online.target
-
-[Service]
-ExecStart=/usr/bin/ollama serve
-User=ollama
-Group=ollama
-Restart=always
-RestartSec=3
-
-[Install]
-WantedBy=default.target
-```
-
-Then start the service:
-
-```bash
-sudo systemctl daemon-reload
-sudo systemctl enable ollama
-```
-
-### Install CUDA drivers (optional – for Nvidia GPUs)
-
-[Download and install](https://developer.nvidia.com/cuda-downloads) CUDA.
-
-Verify that the drivers are installed by running the following command, which should print details about your GPU:
-
-```bash
-nvidia-smi
-```
-
-### Start Ollama
-
-Start Ollama using `systemd`:
-
-```bash
-sudo systemctl start ollama
-```
-
-## Update
-
-Update ollama by running the install script again:
-
-```bash
-curl https://ollama.ai/install.sh | sh
-```
-
-Or by downloading the ollama binary:
-
-```bash
-sudo curl -L https://ollama.ai/download/ollama-linux-amd64 -o /usr/bin/ollama
-sudo chmod +x /usr/bin/ollama
-```
-
-## Viewing logs
-
-To view logs of Ollama running as a startup service, run:
-
-```bash
-journalctl -u ollama
-```
-
-## Uninstall
-
-Remove the ollama service:
-
-```bash
-sudo systemctl stop ollama
-sudo systemctl disable ollama
-sudo rm /etc/systemd/system/ollama.service
-```
-
-Remove the ollama binary from your bin directory (either `/usr/local/bin`, `/usr/bin`, or `/bin`):
-
-```bash
-sudo rm $(which ollama)
-```
-
-Remove the downloaded models and Ollama service user and group:
-```bash
-sudo rm -r /usr/share/ollama
-sudo userdel ollama
-sudo groupdel ollama
-```

docs/modelfile.md

@@ -1,6 +1,6 @@
 # Ollama Model File
 
-> Note: `Modelfile` syntax is in development
+> Note: this model file syntax is in development
 
 A model file is the blueprint to create and share models with Ollama.
 
@@ -12,6 +12,7 @@ A model file is the blueprint to create and share models with Ollama.
   - [FROM (Required)](#from-required)
     - [Build from llama2](#build-from-llama2)
     - [Build from a bin file](#build-from-a-bin-file)
+  - [EMBED](#embed)
   - [PARAMETER](#parameter)
     - [Valid Parameters and Values](#valid-parameters-and-values)
   - [TEMPLATE](#template)
@@ -23,109 +24,88 @@ A model file is the blueprint to create and share models with Ollama.
 
 ## Format
 
-The format of the `Modelfile`:
+The format of the Modelfile:
 
 ```modelfile
 # comment
 INSTRUCTION arguments
 ```
 
-| Instruction                         | Description                                                    |
-| ----------------------------------- | -------------------------------------------------------------- |
-| [`FROM`](#from-required) (required) | Defines the base model to use.                                 |
-| [`PARAMETER`](#parameter)           | Sets the parameters for how Ollama will run the model.         |
-| [`TEMPLATE`](#template)             | The full prompt template to be sent to the model.              |
-| [`SYSTEM`](#system)                 | Specifies the system message that will be set in the template. |
-| [`ADAPTER`](#adapter)               | Defines the (Q)LoRA adapters to apply to the model.            |
-| [`LICENSE`](#license)               | Specifies the legal license.                                   |
+| Instruction                         | Description                                                   |
+| ----------------------------------- | ------------------------------------------------------------- |
+| [`FROM`](#from-required) (required) | Defines the base model to use.                                |
+| [`PARAMETER`](#parameter)           | Sets the parameters for how Ollama will run the model.        |
+| [`TEMPLATE`](#template)             | The full prompt template to be sent to the model.             |
+| [`SYSTEM`](#system)                 | Specifies the system prompt that will be set in the template. |
+| [`ADAPTER`](#adapter)               | Defines the (Q)LoRA adapters to apply to the model.           |
+| [`LICENSE`](#license)               | Specifies the legal license.                                  |
 
 ## Examples
 
-### Basic `Modelfile`
+An example of a model file creating a mario blueprint:
 
-An example of a `Modelfile` creating a mario blueprint:
-
-```modelfile
+```
 FROM llama2
 # sets the temperature to 1 [higher is more creative, lower is more coherent]
 PARAMETER temperature 1
 # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
 PARAMETER num_ctx 4096
 
-# sets a custom system message to specify the behavior of the chat assistant
+# sets a custom system prompt to specify the behavior of the chat assistant
 SYSTEM You are Mario from super mario bros, acting as an assistant.
 ```
 
 To use this:
 
-1. Save it as a file (e.g. `Modelfile`)
-2. `ollama create choose-a-model-name -f <location of the file e.g. ./Modelfile>'`
-3. `ollama run choose-a-model-name`
+1. Save it as a file (eg. `Modelfile`)
+2. `ollama create NAME -f <location of the file eg. ./Modelfile>'`
+3. `ollama run NAME`
 4. Start using the model!
 
 More examples are available in the [examples directory](../examples).
 
-### `Modelfile`s in [ollama.ai/library][1]
-
-There are two ways to view `Modelfile`s underlying the models in [ollama.ai/library][1]:
-
-- Option 1: view a details page from a model's tags page:
-  1.  Go to a particular model's tags (e.g. https://ollama.ai/library/llama2/tags)
-  2.  Click on a tag (e.g. https://ollama.ai/library/llama2:13b)
-  3.  Scroll down to "Layers"
-      - Note: if the [`FROM` instruction](#from-required) is not present,
-        it means the model was created from a local file
-- Option 2: use `ollama show` to print the `Modelfile` for any local models like so:
-
-  ```bash
-  > ollama show --modelfile llama2:13b
-  # Modelfile generated by "ollama show"
-  # To build a new Modelfile based on this one, replace the FROM line with:
-  # FROM llama2:13b
-
-  FROM /root/.ollama/models/blobs/sha256:123abc
-  TEMPLATE """[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>
-
-  {{ end }}{{ .Prompt }} [/INST] """
-  SYSTEM """"""
-  PARAMETER stop [INST]
-  PARAMETER stop [/INST]
-  PARAMETER stop <<SYS>>
-  PARAMETER stop <</SYS>>
-  ```
-
 ## Instructions
 
 ### FROM (Required)
 
-The `FROM` instruction defines the base model to use when creating a model.
+The FROM instruction defines the base model to use when creating a model.
 
-```modelfile
+```
 FROM <model name>:<tag>
 ```
 
 #### Build from llama2
 
-```modelfile
+```
 FROM llama2
 ```
 
 A list of available base models:
 <https://github.com/jmorganca/ollama#model-library>
 
-#### Build from a `bin` file
+#### Build from a bin file
 
-```modelfile
+```
 FROM ./ollama-model.bin
 ```
 
-This bin file location should be specified as an absolute path or relative to the `Modelfile` location.
+This bin file location should be specified as an absolute path or relative to the Modelfile location.
+
+### EMBED
+
+The EMBED instruction is used to add embeddings of files to a model. This is useful for adding custom data that the model can reference when generating an answer. Note that currently only text files are supported, formatted with each line as one embedding.
+```
+FROM <model name>:<tag>
+EMBED <file path>.txt
+EMBED <different file path>.txt
+EMBED <path to directory>/*.txt
+```
 
 ### PARAMETER
 
 The `PARAMETER` instruction defines a parameter that can be set when the model is run.
 
-```modelfile
+```
 PARAMETER <parameter> <parametervalue>
 ```
 
@@ -138,32 +118,29 @@ PARAMETER <parameter> <parametervalue>
 | mirostat_tau   | Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)                                                                                                         | float      | mirostat_tau 5.0     |
 | num_ctx        | Sets the size of the context window used to generate the next token. (Default: 2048)                                                                                                                                                                    | int        | num_ctx 4096         |
 | num_gqa        | The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for llama2:70b                                                                                                                                         | int        | num_gqa 1            |
-| num_gpu        | The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable.                                                                                                                                            | int        | num_gpu 50           |
+| num_gpu        | The number of GPUs to use. On macOS it defaults to 1 to enable metal support, 0 to disable.                                                                                                                                                             | int        | num_gpu 1            |
 | num_thread     | Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores). | int        | num_thread 8         |
 | repeat_last_n  | Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)                                                                                                                                           | int        | repeat_last_n 64     |
 | repeat_penalty | Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)                                                                     | float      | repeat_penalty 1.1   |
 | temperature    | The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)                                                                                                                                     | float      | temperature 0.7      |
-| seed           | Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0)                                                                                       | int        | seed 42              |
-| stop           | Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate `stop` parameters in a modelfile.                                      | string     | stop "AI assistant:" |
+| stop           | Sets the stop sequences to use.                                                                                                                                                                                                                         | string     | stop "AI assistant:" |
 | tfs_z          | Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)                                               | float      | tfs_z 1              |
-| num_predict    | Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context)                                                                                                                                   | int        | num_predict 42       |
 | top_k          | Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)                                                                        | int        | top_k 40             |
 | top_p          | Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)                                                                 | float      | top_p 0.9            |
 
 ### TEMPLATE
 
-`TEMPLATE` of the full prompt template to be passed into the model. It may include (optionally) a system message and a user's prompt. This is used to create a full custom prompt, and syntax may be model specific. You can usually find the template for a given model in the readme for that model.
+`TEMPLATE` of the full prompt template to be passed into the model. It may include (optionally) a system prompt and a user's prompt. This is used to create a full custom prompt, and syntax may be model specific.
 
 #### Template Variables
 
-| Variable          | Description                                                                                                   |
-| ----------------- | ------------------------------------------------------------------------------------------------------------- |
-| `{{ .System }}`   | The system message used to specify custom behavior, this must also be set in the Modelfile as an instruction. |
-| `{{ .Prompt }}`   | The incoming prompt, this is not specified in the model file and will be set based on input.                  |
-| `{{ .Response }}` | The response from the LLM, if not specified response is appended to the end of the template.                  |
-| `{{ .First }}`    | A boolean value used to render specific template information for the first generation of a session.           |
+| Variable        | Description                                                                                                  |
+| --------------- | ------------------------------------------------------------------------------------------------------------ |
+| `{{ .System }}` | The system prompt used to specify custom behavior, this must also be set in the Modelfile as an instruction. |
+| `{{ .Prompt }}` | The incoming prompt, this is not specified in the model file and will be set based on input.                 |
+| `{{ .First }}`  | A boolean value used to render specific template information for the first generation of a session.          |
 
-```modelfile
+```
 TEMPLATE """
 {{- if .First }}
 ### System:
@@ -181,9 +158,9 @@ SYSTEM """<system message>"""
 
 ### SYSTEM
 
-The `SYSTEM` instruction specifies the system message to be used in the template, if applicable.
+The `SYSTEM` instruction specifies the system prompt to be used in the template, if applicable.
 
-```modelfile
+```
 SYSTEM """<system message>"""
 ```
 
@@ -191,7 +168,7 @@ SYSTEM """<system message>"""
 
 The `ADAPTER` instruction specifies the LoRA adapter to apply to the base model. The value of this instruction should be an absolute path or a path relative to the Modelfile and the file must be in a GGML file format. The adapter should be tuned from the base model otherwise the behaviour is undefined.
 
-```modelfile
+```
 ADAPTER ./ollama-lora.bin
 ```
 
@@ -199,7 +176,7 @@ ADAPTER ./ollama-lora.bin
 
 The `LICENSE` instruction allows you to specify the legal license under which the model used with this Modelfile is shared or distributed.
 
-```modelfile
+```
 LICENSE """
 <license text>
 """
@@ -207,7 +184,5 @@ LICENSE """
 
 ## Notes
 
-- the **`Modelfile` is not case sensitive**. In the examples, uppercase instructions are used to make it easier to distinguish it from arguments.
-- Instructions can be in any order. In the examples, the `FROM` instruction is first to keep it easily readable.
-
-[1]: https://ollama.ai/library
+- the **modelfile is not case sensitive**. In the examples, we use uppercase for instructions to make it easier to distinguish it from arguments.
+- Instructions can be in any order. In the examples, we start with FROM instruction to keep it easily readable.

docs/streaming.md

@@ -0,0 +1,35 @@
+# Streaming responses in the Ollama Client API
+
+## JavaScript / TypeScript / Deno
+
+```javascript
+const pull = async () => {
+  const request = await fetch("http://localhost:11434/api/pull", {
+    method: "POST",
+    body: JSON.stringify({ name: "llama2:7b-q5_0" }),
+  });
+
+  const reader = await request.body?.pipeThrough(new TextDecoderStream());
+  if (!reader) throw new Error("No reader");
+  for await (const chunk of reader) {
+    const out = JSON.parse(chunk);
+    if (out.status.startsWith("downloading")) {
+      console.log(`${out.status} - ${(out.completed / out.total) * 100}%`);
+    }
+  }
+}
+
+pull();
+```
+
+## Python
+
+```python
+import requests
+import json
+response = requests.post("http://localhost:11434/api/pull", json={"name": "llama2:7b-q5_0"}, stream=True)
+for data in response.iter_lines():
+  out = json.loads(data)
+  if "completed" in out:
+    print(out["completed"] / out["total"] * 100)
+```

docs/troubleshooting.md

@@ -1,53 +0,0 @@
-# How to troubleshoot issues
-
-Sometimes Ollama may not perform as expected. One of the best ways to figure out what happened is to take a look at the logs. Find the logs on Mac by running the command:
-
-```shell
-cat ~/.ollama/logs/server.log
-```
-
-On Linux systems with systemd, the logs can be found with this command:
-
-```shell
-journalctl -u ollama
-```
-
-If manually running `ollama serve` in a terminal, the logs will be on that terminal.
-
-Join the [Discord](https://discord.gg/ollama) for help interpreting the logs.
-
-## LLM libraries
-
-Ollama includes multiple LLM libraries compiled for different GPUs and CPU
-vector features.  Ollama tries to pick the best one based on the capabilities of
-your system.  If this autodetection has problems, or you run into other problems
-(e.g. crashes in your GPU) you can workaround this by forcing a specific LLM
-library.  `cpu_avx2` will perform the best, followed by `cpu_avx` an the slowest
-but most compatible is `cpu`.  Rosetta emulation under MacOS will work with the
-`cpu` library. 
-
-In the server log, you will see a message that looks something like this (varies
-from release to release):
-
-```
-Dynamic LLM libraries [rocm_v6 cpu cpu_avx cpu_avx2 cuda_v11 rocm_v5]
-```
-
-**Experimental LLM Library Override**
-
-You can set OLLAMA_LLM_LIBRARY to any of the available LLM libraries to bypass
-autodetection, so for example, if you have a CUDA card, but want to force the
-CPU LLM library with AVX2 vector support, use:
-
-```
-OLLAMA_LLM_LIBRARY="cpu_avx2" ollama serve
-```
-
-You can see what features your CPU has with the following.  
-```
-cat /proc/cpuinfo| grep flags  | head -1
-```
-
-## Known issues
-
-* N/A

docs/tutorials.md

@@ -4,6 +4,5 @@ Here is a list of ways you can use Ollama with other tools to build interesting
 
 - [Using LangChain with Ollama in JavaScript](./tutorials/langchainjs.md)
 - [Using LangChain with Ollama in Python](./tutorials/langchainpy.md)
-- [Running Ollama on NVIDIA Jetson Devices](./tutorials/nvidia-jetson.md)
 
-Also be sure to check out the [examples](../examples) directory for more ways to use Ollama.
+Also be sure to check out the [examples](../examples) directory for more ways to use Ollama.

docs/tutorials/fly-gpu.md

@@ -1,83 +0,0 @@
-# Running Ollama on Fly.io GPU Instances
-
-Ollama runs with little to no configuration on [Fly.io GPU instances](https://fly.io/docs/gpus/gpu-quickstart/). If you don't have access to GPUs yet, you'll need to [apply for access](https://fly.io/gpu/) on the waitlist. Once you're accepted, you'll get an email with instructions on how to get started.
-
-Create a new app with `fly apps create`:
-
-```bash
-fly apps create
-```
-
-Then create a `fly.toml` file in a new folder that looks like this:
-
-```toml
-app = "sparkling-violet-709"
-primary_region = "ord"
-vm.size = "a100-40gb" # see https://fly.io/docs/gpus/gpu-quickstart/ for more info
-
-[build]
-  image = "ollama/ollama"
-
-[http_service]
-  internal_port = 11434
-  force_https = false
-  auto_stop_machines = true
-  auto_start_machines = true
-  min_machines_running = 0
-  processes = ["app"]
-
-[mounts]
-  source = "models"
-  destination = "/root/.ollama"
-  initial_size = "100gb"
-```
-
-Then create a [new private IPv6 address](https://fly.io/docs/reference/private-networking/#flycast-private-load-balancing) for your app:
-
-```bash
-fly ips allocate-v6 --private
-```
-
-Then deploy your app:
-
-```bash
-fly deploy
-```
-
-And finally you can access it interactively with a new Fly.io Machine:
-
-```
-fly machine run -e OLLAMA_HOST=http://your-app-name.flycast --shell ollama/ollama
-```
-
-```bash
-$ ollama run openchat:7b-v3.5-fp16
->>> How do I bake chocolate chip cookies?
- To bake chocolate chip cookies, follow these steps:
-
-1. Preheat the oven to 375°F (190°C) and line a baking sheet with parchment paper or silicone baking mat.
-
-2. In a large bowl, mix together 1 cup of unsalted butter (softened), 3/4 cup granulated sugar, and 3/4
-cup packed brown sugar until light and fluffy.
-
-3. Add 2 large eggs, one at a time, to the butter mixture, beating well after each addition. Stir in 1
-teaspoon of pure vanilla extract.
-
-4. In a separate bowl, whisk together 2 cups all-purpose flour, 1/2 teaspoon baking soda, and 1/2 teaspoon
-salt. Gradually add the dry ingredients to the wet ingredients, stirring until just combined.
-
-5. Fold in 2 cups of chocolate chips (or chunks) into the dough.
-
-6. Drop rounded tablespoons of dough onto the prepared baking sheet, spacing them about 2 inches apart.
-
-7. Bake for 10-12 minutes, or until the edges are golden brown. The centers should still be slightly soft.
-
-8. Allow the cookies to cool on the baking sheet for a few minutes before transferring them to a wire rack
-to cool completely.
-
-Enjoy your homemade chocolate chip cookies!
-```
-
-When you set it up like this, it will automatically turn off when you're done using it. Then when you access it again, it will automatically turn back on. This is a great way to save money on GPU instances when you're not using them. If you want a persistent wake-on-use connection to your Ollama instance, you can set up a [connection to your Fly network using WireGuard](https://fly.io/docs/reference/private-networking/#discovering-apps-through-dns-on-a-wireguard-connection). Then you can access your Ollama instance at `http://your-app-name.flycast`.
-
-And that's it!

docs/tutorials/langchainjs.md

@@ -23,17 +23,13 @@ const answer = await ollama.call(`why is the sky blue?`);
 console.log(answer);
 ```
 
-That will get us the same thing as if we ran `ollama run llama2 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app.
-
-```bash
-npm install cheerio 
-```
+That will get us the same thing as if we ran `ollama run llama2 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's build that part of the app.
 
 ```javascript
 import { CheerioWebBaseLoader } from "langchain/document_loaders/web/cheerio";
 
 const loader = new CheerioWebBaseLoader("https://en.wikipedia.org/wiki/2023_Hawaii_wildfires");
-const data = await loader.load();
+const data = loader.load();
 ```
 
 That will load the document. Although this page is smaller than the Odyssey, it is certainly bigger than the context size for most LLMs. So we are going to need to split into smaller pieces, and then select just the pieces relevant to our question. This is a great use for a vector datastore. In this example, we will use the **MemoryVectorStore** that is part of **LangChain**. But there is one more thing we need to get the content into the datastore. We have to run an embeddings process that converts the tokens in the text into a series of vectors. And for that, we are going to use **Tensorflow**. There is a lot of stuff going on in this one. First, install the **Tensorflow** components that we need.

docs/tutorials/langchainpy.md

@@ -42,13 +42,12 @@ text_splitter=RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
 all_splits = text_splitter.split_documents(data)
 ```
 
-It's split up, but we have to find the relevant splits and then submit those to the model. We can do this by creating embeddings and storing them in a vector database. We can use Ollama directly to instantiate an embedding model. We will use ChromaDB in this example for a vector database. `pip install GPT4All chromadb`
+It's split up, but we have to find the relevant splits and then submit those to the model. We can do this by creating embeddings and storing them in a vector database. For now, we don't have embeddings built in to Ollama, though we will be adding that soon, so for now, we can use the GPT4All library for that. We will use ChromaDB in this example for a vector database. `pip install GPT4All chromadb`
 
 ```python
-from langchain.embeddings import OllamaEmbeddings
+from langchain.embeddings import GPT4AllEmbeddings
 from langchain.vectorstores import Chroma
-oembed = OllamaEmbeddings(base_url="http://localhost:11434", model="llama2")
-vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed)
+vectorstore = Chroma.from_documents(documents=all_splits, embedding=GPT4AllEmbeddings())
 ```
 
 Now let's ask a question from the document. **Who was Neleus, and who is in his family?** Neleus is a character in the Odyssey, and the answer can be found in our text.

docs/tutorials/nvidia-jetson.md

@@ -1,38 +0,0 @@
-# Running Ollama on NVIDIA Jetson Devices
-
-With some minor configuration, Ollama runs well on [NVIDIA Jetson Devices](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/). The following has been tested on [JetPack 5.1.2](https://developer.nvidia.com/embedded/jetpack).
-
-NVIDIA Jetson devices are Linux-based embedded AI computers that are purpose-built for AI applications.
-
-Jetsons have an integrated GPU that is wired directly to the memory controller of the machine. For this reason, the `nvidia-smi` command is unrecognized, and Ollama proceeds to operate in "CPU only"
-mode. This can be verified by using a monitoring tool like jtop.
-
-In order to address this, we simply pass the path to the Jetson's pre-installed CUDA libraries into `ollama serve` (while in a tmux session). We then hardcode the num_gpu parameters into a cloned
-version of our target model.
-
-Prerequisites:
-
-- curl
-- tmux
-
-Here are the steps:
-
-- Install Ollama via standard Linux command (ignore the 404 error): `curl https://ollama.ai/install.sh | sh`
-- Stop the Ollama service: `sudo systemctl stop ollama`
-- Start Ollama serve in a tmux session called ollama_jetson and reference the CUDA libraries path: `tmux has-session -t ollama_jetson 2>/dev/null || tmux new-session -d -s ollama_jetson 
-'LD_LIBRARY_PATH=/usr/local/cuda/lib64 ollama serve'`
-- Pull the model you want to use (e.g. mistral): `ollama pull mistral`
-- Create a new Modelfile specifically for enabling GPU support on the Jetson: `touch ModelfileMistralJetson`
-- In the ModelfileMistralJetson file, specify the FROM model and the num_gpu PARAMETER as shown below:
-
-```
-FROM mistral
-PARAMETER num_gpu 999
-```
-
-- Create a new model from your Modelfile: `ollama create mistral-jetson -f ./ModelfileMistralJetson`
-- Run the new model: `ollama run mistral-jetson`
-
-If you run a monitoring tool like jtop you should now see that Ollama is using the Jetson's integrated GPU.
-
-And that's it!

examples/.gitignore

@@ -1,174 +0,0 @@
-node_modules
-bun.lockb
-.vscode
-# OSX
-.DS_STORE
-
-
-# Models
-models/
-
-# Local Chroma db
-.chroma/
-db/
-
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

examples/10tweets/Modelfile

@@ -0,0 +1,7 @@
+# Modelfile for creating a list of ten tweets from a topic
+# Run `ollama create 10tweets -f ./Modelfile` and then `ollama run 10tweets` and enter a topic
+
+FROM llama2
+SYSTEM """
+You are a content marketer who needs to come up with 10 short but succinct tweets. The answer should be a list of ten tweets. Each tweet can have a maximum of 280 characters and should include hashtags. Each user input will be a subject and you should expand it in ten creative ways. Never stop after just one tweet. Always include ten. 
+"""

examples/README.md

@@ -1,3 +1,15 @@
 # Examples
 
-This directory contains different examples of using Ollama.
+This directory contains different examples of using Ollama
+
+To create a model:
+
+```
+ollama create example -f <example file>
+```
+
+To run a model:
+
+```
+ollama run example
+```

examples/bash-comparemodels/README.md

@@ -1,10 +0,0 @@
-# Bash Shell examples
-
-When calling `ollama`, you can pass it a file to run all the prompts in the file, one after the other:
-
-`ollama run llama2 < sourcequestions.txt`
-
-This concept is used in the following example.
-
-## Compare Models
-`comparemodels.sh` is a script that runs all the questions in `sourcequestions.txt` using any 4 models you choose that you have already pulled from the Ollama library or have created locally.

examples/bash-comparemodels/comparemodels.sh

@@ -1,64 +0,0 @@
-#! /usr/bin/env bash
-# Compare multiple models by running them with the same questions
-
-NUMBEROFCHOICES=4
-SELECTIONS=()
-declare -a SUMS=()
-
-# Get the list of models
-CHOICES=$(ollama list | awk '{print $1}')
-
-# Select which models to run as a comparison
-echo "Select $NUMBEROFCHOICES models to compare:"
-select ITEM in $CHOICES; do
-    if [[ -n $ITEM ]]; then
-        echo "You have selected $ITEM"
-        SELECTIONS+=("$ITEM")
-        ((COUNT++))
-        if [[ $COUNT -eq $NUMBEROFCHOICES ]]; then
-            break
-        fi
-    else
-        echo "Invalid selection"
-    fi
-done
-
-# Loop through each of the selected models
-for ITEM in "${SELECTIONS[@]}"; do
-    echo "--------------------------------------------------------------"
-    echo "Loading the model $ITEM into memory"
-    ollama run "$ITEM" ""
-    echo "--------------------------------------------------------------"
-    echo "Running the questions through the model $ITEM"
-    COMMAND_OUTPUT=$(ollama run "$ITEM" --verbose < sourcequestions.txt 2>&1| tee /dev/stderr)
-
-    # eval duration is sometimes listed in seconds and sometimes in milliseconds. 
-    # Add up the values for each model
-    SUM=$(echo "$COMMAND_OUTPUT" | awk '
-    /eval duration:/ {
-        value = $3
-        if (index(value, "ms") > 0) {
-            gsub("ms", "", value)
-            value /= 1000
-        } else {
-            gsub("s", "", value)
-        }
-        sum += value
-    }
-    END { print sum }')
-
-
-    SUMS+=("All questions for $ITEM completed in $SUM seconds")
-done
-
-echo ""
-echo "--------------------------------------------------------------"
-echo -e "Sums of eval durations for each run:"
-for val in "${SUMS[@]}"; do
-    echo "$val"
-done
-
-echo "--------------------------------------------------------------"
-echo "Comparison complete. Now you can decide"
-echo "which model is best."
-echo "--------------------------------------------------------------"

examples/bash-comparemodels/sourcequestions.txt

@@ -1,7 +0,0 @@
-Why is the sky blue
-What is a black hole
-Explain the big bang theory like I am 5?
-What is the quickest way to win a game of Monopoly with 3 others?
-Why does a vacuum bottle keep my coffee hot and my milkshake cold?
-What is the difference between a meteor, a meteorite, and a meteoroid?
-Create an array with 5 items and print to the console. Do this in Python, C#, Typescript, and Rust.

examples/devops-engineer/Modelfile

@@ -0,0 +1,8 @@
+# Modelfile for creating a devops engineer assistant
+# Run `ollama create devops-engineer -f ./Modelfile` and then `ollama run devops-engineer` and enter a topic
+
+FROM llama2:13b
+PARAMETER temperature 1
+SYSTEM """
+You are a senior devops engineer, acting as an assistant. You offer help with cloud technologies like: Terraform, AWS, kubernetes, python. You answer with code examples when possible
+"""

examples/dockerit/Modelfile

@@ -1,4 +1,4 @@
-FROM mistral
+FROM llama2
 SYSTEM """
 You are an experienced Devops engineer focused on docker. When given specifications for a particular need or application you know the best way to host that within a docker container. For instance if someone tells you they want an nginx server to host files located at /web you will answer as follows
 

examples/dockerit/README.md

@@ -0,0 +1,15 @@
+# DockerIt
+
+DockerIt is a tool to help you build and run your application in a Docker container. It consists of a model that defines the system prompt and model weights to use, along with a python script to then build the container and run the image automatically. 
+
+## Caveats
+
+This is an simple example. It's assuming the Dockerfile content generated is going to work. In many cases, even with simple web servers, it fails when trying to copy files that don't exist. It's simply an example of what you could possibly do.
+
+## Example Usage
+
+```bash
+> python3 ./dockerit.py "simple postgres server with admin password set to 123"
+Enter the name of the image: matttest
+Container named happy_keller  started with id:  7c201bb6c30f02b356ddbc8e2a5af9d7d7d7b8c228519c9a501d15c0bd9d6b3e
+```

examples/golang-simplegenerate/main.go

@@ -1,29 +0,0 @@
-package main
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"log"
-	"net/http"
-	"os"
-)
-
-func main() {
-	body := []byte(`{"model":"mistral"}`)
-	resp, err := http.Post("http://localhost:11434/api/generate", "application/json", bytes.NewBuffer(body))
-
-	if err != nil {
-		fmt.Print(err.Error())
-		os.Exit(1)
-	}
-
-	defer resp.Body.Close()
-	
-	responseData, err := io.ReadAll(resp.Body)
-	if err != nil {
-		log.Fatal(err)
-	}
-	fmt.Println(string(responseData))
-
-}

examples/jupyter-notebook/README.md

@@ -1,5 +0,0 @@
-# Ollama Jupyter Notebook
-
-This example downloads and installs Ollama in a Jupyter instance such as Google Colab. It will start the Ollama service and expose an endpoint using `ngrok` which can be used to communicate with the Ollama instance remotely.
-
-For best results, use an instance with GPU accelerator.

examples/jupyter-notebook/ollama.ipynb

@@ -1,102 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "93f59dcb-c588-41b8-a792-55d88ade739c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Download and run the Ollama Linux install script\n",
-    "!curl https://ollama.ai/install.sh | sh\n",
-    "!command -v systemctl >/dev/null && sudo systemctl stop ollama"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "658c147e-c7f8-490e-910e-62b80f577dda",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install aiohttp pyngrok\n",
-    "\n",
-    "import os\n",
-    "import asyncio\n",
-    "from aiohttp import ClientSession\n",
-    "\n",
-    "# Set LD_LIBRARY_PATH so the system NVIDIA library becomes preferred\n",
-    "# over the built-in library. This is particularly important for \n",
-    "# Google Colab which installs older drivers\n",
-    "os.environ.update({'LD_LIBRARY_PATH': '/usr/lib64-nvidia'})\n",
-    "\n",
-    "async def run(cmd):\n",
-    "  '''\n",
-    "  run is a helper function to run subcommands asynchronously.\n",
-    "  '''\n",
-    "  print('>>> starting', *cmd)\n",
-    "  p = await asyncio.subprocess.create_subprocess_exec(\n",
-    "      *cmd,\n",
-    "      stdout=asyncio.subprocess.PIPE,\n",
-    "      stderr=asyncio.subprocess.PIPE,\n",
-    "  )\n",
-    "\n",
-    "  async def pipe(lines):\n",
-    "    async for line in lines:\n",
-    "      print(line.strip().decode('utf-8'))\n",
-    "\n",
-    "  await asyncio.gather(\n",
-    "      pipe(p.stdout),\n",
-    "      pipe(p.stderr),\n",
-    "  )\n",
-    "\n",
-    "\n",
-    "await asyncio.gather(\n",
-    "    run(['ollama', 'serve']),\n",
-    "    run(['ngrok', 'http', '--log', 'stderr', '11434']),\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e7735a55-9aad-4caf-8683-52e2163ba53b",
-   "metadata": {},
-   "source": [
-    "The previous cell starts two processes, `ollama` and `ngrok`. The log output will show a line like the following which describes the external address.\n",
-    "\n",
-    "```\n",
-    "t=2023-11-12T22:55:56+0000 lvl=info msg=\"started tunnel\" obj=tunnels name=command_line addr=http://localhost:11434 url=https://8249-34-125-179-11.ngrok.io\n",
-    "```\n",
-    "\n",
-    "The external address in this case is `https://8249-34-125-179-11.ngrok.io` which can be passed into `OLLAMA_HOST` to access this instance.\n",
-    "\n",
-    "```bash\n",
-    "export OLLAMA_HOST=https://8249-34-125-179-11.ngrok.io\n",
-    "ollama list\n",
-    "ollama run mistral\n",
-    "```"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/kubernetes/README.md

@@ -1,36 +0,0 @@
-# Deploy Ollama to Kubernetes
-
-## Prerequisites
-
-- Ollama: https://ollama.ai/download
-- Kubernetes cluster. This example will use Google Kubernetes Engine.
-
-## Steps
-
-1. Create the Ollama namespace, daemon set, and service
-
-    ```bash
-    kubectl apply -f cpu.yaml
-    ```
-
-1. Port forward the Ollama service to connect and use it locally
-
-    ```bash
-    kubectl -n ollama port-forward service/ollama 11434:80
-    ```
-
-1. Pull and run a model, for example `orca-mini:3b`
-
-    ```bash
-    ollama run orca-mini:3b
-    ```
-
-## (Optional) Hardware Acceleration
-
-Hardware acceleration in Kubernetes requires NVIDIA's [`k8s-device-plugin`](https://github.com/NVIDIA/k8s-device-plugin). Follow the link for more details.
-
-Once configured, create a GPU enabled Ollama deployment.
-
-```bash
-kubectl apply -f gpu.yaml
-```

examples/kubernetes/cpu.yaml

@@ -1,42 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: ollama
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  selector:
-    matchLabels:
-      name: ollama
-  template:
-    metadata:
-      labels:
-        name: ollama
-    spec:
-      containers:
-      - name: ollama
-        image: ollama/ollama:latest
-        ports:
-        - name: http
-          containerPort: 11434
-          protocol: TCP
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  type: ClusterIP
-  selector:
-    name: ollama
-  ports:
-  - port: 80
-    name: http
-    targetPort: http
-    protocol: TCP

examples/kubernetes/gpu.yaml

@@ -1,58 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: ollama
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      name: ollama
-  template:
-    metadata:
-      labels:
-        name: ollama
-    spec:
-      containers:
-      - name: ollama
-        image: ollama/ollama:latest
-        env:
-        - name: PATH
-          value: /usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
-        - name: LD_LIBRARY_PATH
-          value: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
-        - name: NVIDIA_DRIVER_CAPABILITIES
-          value: compute,utility
-        ports:
-        - name: http
-          containerPort: 11434
-          protocol: TCP
-        resources:
-          limits:
-            nvidia.com/gpu: 1
-      tolerations:
-      - key: nvidia.com/gpu
-        operator: Exists
-        effect: NoSchedule
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: ollama
-  namespace: ollama
-spec:
-  type: ClusterIP
-  selector:
-    name: ollama
-  ports:
-  - port: 80
-    name: http
-    targetPort: http
-    protocol: TCP

examples/langchain-python-rag-privategpt/requirements.txt

@@ -1,14 +0,0 @@
-langchain==0.0.274
-gpt4all==1.0.8
-chromadb==0.4.7
-llama-cpp-python==0.1.81
-urllib3==2.0.4
-PyMuPDF==1.23.5
-python-dotenv==1.0.0
-unstructured==0.10.8
-extract-msg==0.45.0
-tabulate==0.9.0
-pandoc==2.3
-pypandoc==1.11
-tqdm==4.66.1
-sentence_transformers==2.2.2

examples/langchain-python-rag-websummary/README.md

@@ -1,23 +0,0 @@
-# LangChain Web Summarization
-
-This example summarizes the website, [https://ollama.ai/blog/run-llama2-uncensored-locally](https://ollama.ai/blog/run-llama2-uncensored-locally)
-
-## Running the Example
-
-1. Ensure you have the `llama2` model installed:
-
-   ```bash
-   ollama pull llama2
-   ```
-
-2. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Run the example:
-
-   ```bash
-   python main.py
-   ```

examples/langchain-python-simple/README.md

@@ -1,24 +0,0 @@
-# LangChain
-
-This example is a basic "hello world" of using LangChain with Ollama.
-
-## Running the Example
-
-1. Ensure you have the `llama2` model installed:
-
-   ```bash
-   ollama pull llama2
-   ```
-
-2. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Run the example:
-
-   ```bash
-   python main.py
-   ```
-  

examples/langchain-typescript-simple/README.md

@@ -1,23 +0,0 @@
-# LangChain
-
-This example is a basic "hello world" of using LangChain with Ollama using Node.js and Typescript.
-
-## Running the Example
-
-1. Install the prerequisites:
-
-   ```bash
-   npm install
-   ```
-
-2. Ensure the `mistral` model is available:
-
-   ```bash
-   ollama pull mistral
-   ```
-
-3. Run the example:
-
-   ```bash
-   npm start
-   ```

examples/langchain-typescript-simple/main.ts

@@ -1,25 +0,0 @@
-import { Ollama } from 'langchain/llms/ollama';
-import * as readline from "readline";
-
-async function main() {
-  const ollama = new Ollama({
-    model: 'mistral'    
-    // other parameters can be found at https://js.langchain.com/docs/api/llms_ollama/classes/Ollama
-  });
-
-  const rl = readline.createInterface({
-    input: process.stdin,
-    output: process.stdout,
-  });
-
-  rl.question("What is your question: \n", async (user_input) => {
-    const stream = await ollama.stream(user_input);
-  
-    for await (const chunk of stream) {
-      process.stdout.write(chunk);
-    }
-    rl.close();
-  })
-}
-
-main();

examples/langchain-typescript-simple/package-lock.json

@@ -1,997 +0,0 @@
-{
-  "name": "langchain-typescript-simple",
-  "lockfileVersion": 3,
-  "requires": true,
-  "packages": {
-    "": {
-      "dependencies": {
-        "langchain": "^0.0.165"
-      },
-      "devDependencies": {
-        "typescript": "^5.2.2"
-      }
-    },
-    "node_modules/@anthropic-ai/sdk": {
-      "version": "0.6.2",
-      "resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.6.2.tgz",
-      "integrity": "sha512-fB9PUj9RFT+XjkL+E9Ol864ZIJi+1P8WnbHspN3N3/GK2uSzjd0cbVIKTGgf4v3N8MwaQu+UWnU7C4BG/fap/g==",
-      "dependencies": {
-        "@types/node": "^18.11.18",
-        "@types/node-fetch": "^2.6.4",
-        "abort-controller": "^3.0.0",
-        "agentkeepalive": "^4.2.1",
-        "digest-fetch": "^1.3.0",
-        "form-data-encoder": "1.7.2",
-        "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7"
-      }
-    },
-    "node_modules/@types/node": {
-      "version": "18.18.4",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-18.18.4.tgz",
-      "integrity": "sha512-t3rNFBgJRugIhackit2mVcLfF6IRc0JE4oeizPQL8Zrm8n2WY/0wOdpOPhdtG0V9Q2TlW/axbF1MJ6z+Yj/kKQ=="
-    },
-    "node_modules/@types/node-fetch": {
-      "version": "2.6.6",
-      "resolved": "https://registry.npmjs.org/@types/node-fetch/-/node-fetch-2.6.6.tgz",
-      "integrity": "sha512-95X8guJYhfqiuVVhRFxVQcf4hW/2bCuoPwDasMf/531STFoNoWTT7YDnWdXHEZKqAGUigmpG31r2FE70LwnzJw==",
-      "dependencies": {
-        "@types/node": "*",
-        "form-data": "^4.0.0"
-      }
-    },
-    "node_modules/@types/retry": {
-      "version": "0.12.0",
-      "resolved": "https://registry.npmjs.org/@types/retry/-/retry-0.12.0.tgz",
-      "integrity": "sha512-wWKOClTTiizcZhXnPY4wikVAwmdYHp8q6DmC+EJUzAMsycb7HB32Kh9RN4+0gExjmPmZSAQjgURXIGATPegAvA=="
-    },
-    "node_modules/@types/uuid": {
-      "version": "9.0.5",
-      "resolved": "https://registry.npmjs.org/@types/uuid/-/uuid-9.0.5.tgz",
-      "integrity": "sha512-xfHdwa1FMJ082prjSJpoEI57GZITiQz10r3vEJCHa2khEFQjKy91aWKz6+zybzssCvXUwE1LQWgWVwZ4nYUvHQ=="
-    },
-    "node_modules/abort-controller": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
-      "integrity": "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg==",
-      "dependencies": {
-        "event-target-shim": "^5.0.0"
-      },
-      "engines": {
-        "node": ">=6.5"
-      }
-    },
-    "node_modules/agentkeepalive": {
-      "version": "4.5.0",
-      "resolved": "https://registry.npmjs.org/agentkeepalive/-/agentkeepalive-4.5.0.tgz",
-      "integrity": "sha512-5GG/5IbQQpC9FpkRGsSvZI5QYeSCzlJHdpBQntCsuTOxhKD8lqKhrleg2Yi7yvMIf82Ycmmqln9U8V9qwEiJew==",
-      "dependencies": {
-        "humanize-ms": "^1.2.1"
-      },
-      "engines": {
-        "node": ">= 8.0.0"
-      }
-    },
-    "node_modules/ansi-styles": {
-      "version": "5.2.0",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-5.2.0.tgz",
-      "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==",
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/ansi-styles?sponsor=1"
-      }
-    },
-    "node_modules/argparse": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/argparse/-/argparse-2.0.1.tgz",
-      "integrity": "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="
-    },
-    "node_modules/asynckit": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
-      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="
-    },
-    "node_modules/base-64": {
-      "version": "0.1.0",
-      "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
-      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA=="
-    },
-    "node_modules/base64-js": {
-      "version": "1.5.1",
-      "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
-      "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==",
-      "funding": [
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/feross"
-        },
-        {
-          "type": "patreon",
-          "url": "https://www.patreon.com/feross"
-        },
-        {
-          "type": "consulting",
-          "url": "https://feross.org/support"
-        }
-      ]
-    },
-    "node_modules/binary-extensions": {
-      "version": "2.2.0",
-      "resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.2.0.tgz",
-      "integrity": "sha512-jDctJ/IVQbZoJykoeHbhXpOlNBqGNcwXJKJog42E5HDPUwQTSdjCHdihjj0DlnheQ7blbT6dHOafNAiS8ooQKA==",
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/binary-search": {
-      "version": "1.3.6",
-      "resolved": "https://registry.npmjs.org/binary-search/-/binary-search-1.3.6.tgz",
-      "integrity": "sha512-nbE1WxOTTrUWIfsfZ4aHGYu5DOuNkbxGokjV6Z2kxfJK3uaAb8zNK1muzOeipoLHZjInT4Br88BHpzevc681xA=="
-    },
-    "node_modules/camelcase": {
-      "version": "6.3.0",
-      "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-6.3.0.tgz",
-      "integrity": "sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA==",
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/charenc": {
-      "version": "0.0.2",
-      "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
-      "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==",
-      "engines": {
-        "node": "*"
-      }
-    },
-    "node_modules/combined-stream": {
-      "version": "1.0.8",
-      "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
-      "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
-      "dependencies": {
-        "delayed-stream": "~1.0.0"
-      },
-      "engines": {
-        "node": ">= 0.8"
-      }
-    },
-    "node_modules/commander": {
-      "version": "10.0.1",
-      "resolved": "https://registry.npmjs.org/commander/-/commander-10.0.1.tgz",
-      "integrity": "sha512-y4Mg2tXshplEbSGzx7amzPwKKOCGuoSRP/CjEdwwk0FOGlUbq6lKuoyDZTNZkmxHdJtp54hdfY/JUrdL7Xfdug==",
-      "engines": {
-        "node": ">=14"
-      }
-    },
-    "node_modules/crypt": {
-      "version": "0.0.2",
-      "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
-      "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==",
-      "engines": {
-        "node": "*"
-      }
-    },
-    "node_modules/decamelize": {
-      "version": "1.2.0",
-      "resolved": "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz",
-      "integrity": "sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==",
-      "engines": {
-        "node": ">=0.10.0"
-      }
-    },
-    "node_modules/delayed-stream": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
-      "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
-      "engines": {
-        "node": ">=0.4.0"
-      }
-    },
-    "node_modules/digest-fetch": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
-      "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
-      "dependencies": {
-        "base-64": "^0.1.0",
-        "md5": "^2.3.0"
-      }
-    },
-    "node_modules/event-target-shim": {
-      "version": "5.0.1",
-      "resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz",
-      "integrity": "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ==",
-      "engines": {
-        "node": ">=6"
-      }
-    },
-    "node_modules/eventemitter3": {
-      "version": "4.0.7",
-      "resolved": "https://registry.npmjs.org/eventemitter3/-/eventemitter3-4.0.7.tgz",
-      "integrity": "sha512-8guHBZCwKnFhYdHr2ysuRWErTwhoN2X8XELRlrRwpmfeY2jjuUN4taQMsULKUVo1K4DvZl+0pgfyoysHxvmvEw=="
-    },
-    "node_modules/expr-eval": {
-      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/expr-eval/-/expr-eval-2.0.2.tgz",
-      "integrity": "sha512-4EMSHGOPSwAfBiibw3ndnP0AvjDWLsMvGOvWEZ2F96IGk0bIVdjQisOHxReSkE13mHcfbuCiXw+G4y0zv6N8Eg=="
-    },
-    "node_modules/flat": {
-      "version": "5.0.2",
-      "resolved": "https://registry.npmjs.org/flat/-/flat-5.0.2.tgz",
-      "integrity": "sha512-b6suED+5/3rTpUBdG1gupIl8MPFCAMA0QXwmljLhvCUKcUvdE4gWky9zpuGCcXHOsz4J9wPGNWq6OKpmIzz3hQ==",
-      "bin": {
-        "flat": "cli.js"
-      }
-    },
-    "node_modules/form-data": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz",
-      "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==",
-      "dependencies": {
-        "asynckit": "^0.4.0",
-        "combined-stream": "^1.0.8",
-        "mime-types": "^2.1.12"
-      },
-      "engines": {
-        "node": ">= 6"
-      }
-    },
-    "node_modules/form-data-encoder": {
-      "version": "1.7.2",
-      "resolved": "https://registry.npmjs.org/form-data-encoder/-/form-data-encoder-1.7.2.tgz",
-      "integrity": "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="
-    },
-    "node_modules/formdata-node": {
-      "version": "4.4.1",
-      "resolved": "https://registry.npmjs.org/formdata-node/-/formdata-node-4.4.1.tgz",
-      "integrity": "sha512-0iirZp3uVDjVGt9p49aTaqjk84TrglENEDuqfdlZQ1roC9CWlPk6Avf8EEnZNcAqPonwkG35x4n3ww/1THYAeQ==",
-      "dependencies": {
-        "node-domexception": "1.0.0",
-        "web-streams-polyfill": "4.0.0-beta.3"
-      },
-      "engines": {
-        "node": ">= 12.20"
-      }
-    },
-    "node_modules/humanize-ms": {
-      "version": "1.2.1",
-      "resolved": "https://registry.npmjs.org/humanize-ms/-/humanize-ms-1.2.1.tgz",
-      "integrity": "sha512-Fl70vYtsAFb/C06PTS9dZBo7ihau+Tu/DNCk/OyHhea07S+aeMWpFFkUaXRa8fI+ScZbEI8dfSxwY7gxZ9SAVQ==",
-      "dependencies": {
-        "ms": "^2.0.0"
-      }
-    },
-    "node_modules/is-any-array": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/is-any-array/-/is-any-array-2.0.1.tgz",
-      "integrity": "sha512-UtilS7hLRu++wb/WBAw9bNuP1Eg04Ivn1vERJck8zJthEvXCBEBpGR/33u/xLKWEQf95803oalHrVDptcAvFdQ=="
-    },
-    "node_modules/is-buffer": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
-      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w=="
-    },
-    "node_modules/js-tiktoken": {
-      "version": "1.0.7",
-      "resolved": "https://registry.npmjs.org/js-tiktoken/-/js-tiktoken-1.0.7.tgz",
-      "integrity": "sha512-biba8u/clw7iesNEWLOLwrNGoBP2lA+hTaBLs/D45pJdUPFXyxD6nhcDVtADChghv4GgyAiMKYMiRx7x6h7Biw==",
-      "dependencies": {
-        "base64-js": "^1.5.1"
-      }
-    },
-    "node_modules/js-yaml": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz",
-      "integrity": "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA==",
-      "dependencies": {
-        "argparse": "^2.0.1"
-      },
-      "bin": {
-        "js-yaml": "bin/js-yaml.js"
-      }
-    },
-    "node_modules/jsonpointer": {
-      "version": "5.0.1",
-      "resolved": "https://registry.npmjs.org/jsonpointer/-/jsonpointer-5.0.1.tgz",
-      "integrity": "sha512-p/nXbhSEcu3pZRdkW1OfJhpsVtW1gd4Wa1fnQc9YLiTfAjn0312eMKimbdIQzuZl9aa9xUGaRlP9T/CJE/ditQ==",
-      "engines": {
-        "node": ">=0.10.0"
-      }
-    },
-    "node_modules/langchain": {
-      "version": "0.0.165",
-      "resolved": "https://registry.npmjs.org/langchain/-/langchain-0.0.165.tgz",
-      "integrity": "sha512-CpbNpjwaE+9lzjdw+pZz0VgnRrFivEgr7CVp9dDaAb5JpaJAA4V2v6uQ9ZPN+TSqupTQ79HFn2sfyZVEl2EG7Q==",
-      "dependencies": {
-        "@anthropic-ai/sdk": "^0.6.2",
-        "ansi-styles": "^5.0.0",
-        "binary-extensions": "^2.2.0",
-        "camelcase": "6",
-        "decamelize": "^1.2.0",
-        "expr-eval": "^2.0.2",
-        "flat": "^5.0.2",
-        "js-tiktoken": "^1.0.7",
-        "js-yaml": "^4.1.0",
-        "jsonpointer": "^5.0.1",
-        "langchainhub": "~0.0.6",
-        "langsmith": "~0.0.31",
-        "ml-distance": "^4.0.0",
-        "object-hash": "^3.0.0",
-        "openai": "~4.4.0",
-        "openapi-types": "^12.1.3",
-        "p-queue": "^6.6.2",
-        "p-retry": "4",
-        "uuid": "^9.0.0",
-        "yaml": "^2.2.1",
-        "zod": "^3.22.3",
-        "zod-to-json-schema": "^3.20.4"
-      },
-      "engines": {
-        "node": ">=18"
-      },
-      "peerDependencies": {
-        "@aws-crypto/sha256-js": "^5.0.0",
-        "@aws-sdk/client-bedrock-runtime": "^3.422.0",
-        "@aws-sdk/client-dynamodb": "^3.310.0",
-        "@aws-sdk/client-kendra": "^3.352.0",
-        "@aws-sdk/client-lambda": "^3.310.0",
-        "@aws-sdk/client-s3": "^3.310.0",
-        "@aws-sdk/client-sagemaker-runtime": "^3.310.0",
-        "@aws-sdk/client-sfn": "^3.310.0",
-        "@aws-sdk/credential-provider-node": "^3.388.0",
-        "@azure/storage-blob": "^12.15.0",
-        "@clickhouse/client": "^0.0.14",
-        "@cloudflare/ai": "^1.0.12",
-        "@elastic/elasticsearch": "^8.4.0",
-        "@getmetal/metal-sdk": "*",
-        "@getzep/zep-js": "^0.7.0",
-        "@gomomento/sdk": "^1.23.0",
-        "@google-ai/generativelanguage": "^0.2.1",
-        "@google-cloud/storage": "^6.10.1",
-        "@huggingface/inference": "^1.5.1",
-        "@mozilla/readability": "*",
-        "@notionhq/client": "^2.2.10",
-        "@opensearch-project/opensearch": "*",
-        "@pinecone-database/pinecone": "^1.1.0",
-        "@planetscale/database": "^1.8.0",
-        "@qdrant/js-client-rest": "^1.2.0",
-        "@raycast/api": "^1.55.2",
-        "@smithy/eventstream-codec": "^2.0.5",
-        "@smithy/protocol-http": "^3.0.6",
-        "@smithy/signature-v4": "^2.0.10",
-        "@smithy/util-utf8": "^2.0.0",
-        "@supabase/postgrest-js": "^1.1.1",
-        "@supabase/supabase-js": "^2.10.0",
-        "@tensorflow-models/universal-sentence-encoder": "*",
-        "@tensorflow/tfjs-converter": "*",
-        "@tensorflow/tfjs-core": "*",
-        "@upstash/redis": "^1.20.6",
-        "@vercel/postgres": "^0.5.0",
-        "@writerai/writer-sdk": "^0.40.2",
-        "@xata.io/client": "^0.25.1",
-        "@xenova/transformers": "^2.5.4",
-        "@zilliz/milvus2-sdk-node": ">=2.2.7",
-        "apify-client": "^2.7.1",
-        "axios": "*",
-        "cassandra-driver": "^4.6.4",
-        "cheerio": "^1.0.0-rc.12",
-        "chromadb": "*",
-        "cohere-ai": ">=6.0.0",
-        "d3-dsv": "^2.0.0",
-        "epub2": "^3.0.1",
-        "faiss-node": "^0.3.0",
-        "fast-xml-parser": "^4.2.7",
-        "firebase-admin": "^11.9.0",
-        "google-auth-library": "^8.9.0",
-        "googleapis": "^126.0.1",
-        "hnswlib-node": "^1.4.2",
-        "html-to-text": "^9.0.5",
-        "ignore": "^5.2.0",
-        "ioredis": "^5.3.2",
-        "jsdom": "*",
-        "llmonitor": "*",
-        "lodash": "^4.17.21",
-        "mammoth": "*",
-        "mongodb": "^5.2.0",
-        "mysql2": "^3.3.3",
-        "neo4j-driver": "*",
-        "node-llama-cpp": "*",
-        "notion-to-md": "^3.1.0",
-        "pdf-parse": "1.1.1",
-        "peggy": "^3.0.2",
-        "pg": "^8.11.0",
-        "pg-copy-streams": "^6.0.5",
-        "pickleparser": "^0.1.0",
-        "playwright": "^1.32.1",
-        "portkey-ai": "^0.1.11",
-        "puppeteer": "^19.7.2",
-        "redis": "^4.6.4",
-        "replicate": "^0.18.0",
-        "sonix-speech-recognition": "^2.1.1",
-        "srt-parser-2": "^1.2.2",
-        "typeorm": "^0.3.12",
-        "typesense": "^1.5.3",
-        "usearch": "^1.1.1",
-        "vectordb": "^0.1.4",
-        "voy-search": "0.6.2",
-        "weaviate-ts-client": "^1.4.0",
-        "web-auth-library": "^1.0.3",
-        "youtube-transcript": "^1.0.6",
-        "youtubei.js": "^5.8.0"
-      },
-      "peerDependenciesMeta": {
-        "@aws-crypto/sha256-js": {
-          "optional": true
-        },
-        "@aws-sdk/client-bedrock-runtime": {
-          "optional": true
-        },
-        "@aws-sdk/client-dynamodb": {
-          "optional": true
-        },
-        "@aws-sdk/client-kendra": {
-          "optional": true
-        },
-        "@aws-sdk/client-lambda": {
-          "optional": true
-        },
-        "@aws-sdk/client-s3": {
-          "optional": true
-        },
-        "@aws-sdk/client-sagemaker-runtime": {
-          "optional": true
-        },
-        "@aws-sdk/client-sfn": {
-          "optional": true
-        },
-        "@aws-sdk/credential-provider-node": {
-          "optional": true
-        },
-        "@azure/storage-blob": {
-          "optional": true
-        },
-        "@clickhouse/client": {
-          "optional": true
-        },
-        "@cloudflare/ai": {
-          "optional": true
-        },
-        "@elastic/elasticsearch": {
-          "optional": true
-        },
-        "@getmetal/metal-sdk": {
-          "optional": true
-        },
-        "@getzep/zep-js": {
-          "optional": true
-        },
-        "@gomomento/sdk": {
-          "optional": true
-        },
-        "@google-ai/generativelanguage": {
-          "optional": true
-        },
-        "@google-cloud/storage": {
-          "optional": true
-        },
-        "@huggingface/inference": {
-          "optional": true
-        },
-        "@mozilla/readability": {
-          "optional": true
-        },
-        "@notionhq/client": {
-          "optional": true
-        },
-        "@opensearch-project/opensearch": {
-          "optional": true
-        },
-        "@pinecone-database/pinecone": {
-          "optional": true
-        },
-        "@planetscale/database": {
-          "optional": true
-        },
-        "@qdrant/js-client-rest": {
-          "optional": true
-        },
-        "@raycast/api": {
-          "optional": true
-        },
-        "@smithy/eventstream-codec": {
-          "optional": true
-        },
-        "@smithy/protocol-http": {
-          "optional": true
-        },
-        "@smithy/signature-v4": {
-          "optional": true
-        },
-        "@smithy/util-utf8": {
-          "optional": true
-        },
-        "@supabase/postgrest-js": {
-          "optional": true
-        },
-        "@supabase/supabase-js": {
-          "optional": true
-        },
-        "@tensorflow-models/universal-sentence-encoder": {
-          "optional": true
-        },
-        "@tensorflow/tfjs-converter": {
-          "optional": true
-        },
-        "@tensorflow/tfjs-core": {
-          "optional": true
-        },
-        "@upstash/redis": {
-          "optional": true
-        },
-        "@vercel/postgres": {
-          "optional": true
-        },
-        "@writerai/writer-sdk": {
-          "optional": true
-        },
-        "@xata.io/client": {
-          "optional": true
-        },
-        "@xenova/transformers": {
-          "optional": true
-        },
-        "@zilliz/milvus2-sdk-node": {
-          "optional": true
-        },
-        "apify-client": {
-          "optional": true
-        },
-        "axios": {
-          "optional": true
-        },
-        "cassandra-driver": {
-          "optional": true
-        },
-        "cheerio": {
-          "optional": true
-        },
-        "chromadb": {
-          "optional": true
-        },
-        "cohere-ai": {
-          "optional": true
-        },
-        "d3-dsv": {
-          "optional": true
-        },
-        "epub2": {
-          "optional": true
-        },
-        "faiss-node": {
-          "optional": true
-        },
-        "fast-xml-parser": {
-          "optional": true
-        },
-        "firebase-admin": {
-          "optional": true
-        },
-        "google-auth-library": {
-          "optional": true
-        },
-        "googleapis": {
-          "optional": true
-        },
-        "hnswlib-node": {
-          "optional": true
-        },
-        "html-to-text": {
-          "optional": true
-        },
-        "ignore": {
-          "optional": true
-        },
-        "ioredis": {
-          "optional": true
-        },
-        "jsdom": {
-          "optional": true
-        },
-        "llmonitor": {
-          "optional": true
-        },
-        "lodash": {
-          "optional": true
-        },
-        "mammoth": {
-          "optional": true
-        },
-        "mongodb": {
-          "optional": true
-        },
-        "mysql2": {
-          "optional": true
-        },
-        "neo4j-driver": {
-          "optional": true
-        },
-        "node-llama-cpp": {
-          "optional": true
-        },
-        "notion-to-md": {
-          "optional": true
-        },
-        "pdf-parse": {
-          "optional": true
-        },
-        "peggy": {
-          "optional": true
-        },
-        "pg": {
-          "optional": true
-        },
-        "pg-copy-streams": {
-          "optional": true
-        },
-        "pickleparser": {
-          "optional": true
-        },
-        "playwright": {
-          "optional": true
-        },
-        "portkey-ai": {
-          "optional": true
-        },
-        "puppeteer": {
-          "optional": true
-        },
-        "redis": {
-          "optional": true
-        },
-        "replicate": {
-          "optional": true
-        },
-        "sonix-speech-recognition": {
-          "optional": true
-        },
-        "srt-parser-2": {
-          "optional": true
-        },
-        "typeorm": {
-          "optional": true
-        },
-        "typesense": {
-          "optional": true
-        },
-        "usearch": {
-          "optional": true
-        },
-        "vectordb": {
-          "optional": true
-        },
-        "voy-search": {
-          "optional": true
-        },
-        "weaviate-ts-client": {
-          "optional": true
-        },
-        "web-auth-library": {
-          "optional": true
-        },
-        "youtube-transcript": {
-          "optional": true
-        },
-        "youtubei.js": {
-          "optional": true
-        }
-      }
-    },
-    "node_modules/langchainhub": {
-      "version": "0.0.6",
-      "resolved": "https://registry.npmjs.org/langchainhub/-/langchainhub-0.0.6.tgz",
-      "integrity": "sha512-SW6105T+YP1cTe0yMf//7kyshCgvCTyFBMTgH2H3s9rTAR4e+78DA/BBrUL/Mt4Q5eMWui7iGuAYb3pgGsdQ9w=="
-    },
-    "node_modules/langsmith": {
-      "version": "0.0.42",
-      "resolved": "https://registry.npmjs.org/langsmith/-/langsmith-0.0.42.tgz",
-      "integrity": "sha512-sFuN+e7E+pPBIRaRgFqZh/BRBWNHTZNAwi6uj4kydQawooCZYoJmM5snOkiQrhVSvAhgu6xFhLvmfvkPcKzD7w==",
-      "dependencies": {
-        "@types/uuid": "^9.0.1",
-        "commander": "^10.0.1",
-        "p-queue": "^6.6.2",
-        "p-retry": "4",
-        "uuid": "^9.0.0"
-      },
-      "bin": {
-        "langsmith": "dist/cli/main.cjs"
-      }
-    },
-    "node_modules/md5": {
-      "version": "2.3.0",
-      "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
-      "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
-      "dependencies": {
-        "charenc": "0.0.2",
-        "crypt": "0.0.2",
-        "is-buffer": "~1.1.6"
-      }
-    },
-    "node_modules/mime-db": {
-      "version": "1.52.0",
-      "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
-      "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
-      "engines": {
-        "node": ">= 0.6"
-      }
-    },
-    "node_modules/mime-types": {
-      "version": "2.1.35",
-      "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
-      "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
-      "dependencies": {
-        "mime-db": "1.52.0"
-      },
-      "engines": {
-        "node": ">= 0.6"
-      }
-    },
-    "node_modules/ml-array-mean": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/ml-array-mean/-/ml-array-mean-1.1.6.tgz",
-      "integrity": "sha512-MIdf7Zc8HznwIisyiJGRH9tRigg3Yf4FldW8DxKxpCCv/g5CafTw0RRu51nojVEOXuCQC7DRVVu5c7XXO/5joQ==",
-      "dependencies": {
-        "ml-array-sum": "^1.1.6"
-      }
-    },
-    "node_modules/ml-array-sum": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/ml-array-sum/-/ml-array-sum-1.1.6.tgz",
-      "integrity": "sha512-29mAh2GwH7ZmiRnup4UyibQZB9+ZLyMShvt4cH4eTK+cL2oEMIZFnSyB3SS8MlsTh6q/w/yh48KmqLxmovN4Dw==",
-      "dependencies": {
-        "is-any-array": "^2.0.0"
-      }
-    },
-    "node_modules/ml-distance": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/ml-distance/-/ml-distance-4.0.1.tgz",
-      "integrity": "sha512-feZ5ziXs01zhyFUUUeZV5hwc0f5JW0Sh0ckU1koZe/wdVkJdGxcP06KNQuF0WBTj8FttQUzcvQcpcrOp/XrlEw==",
-      "dependencies": {
-        "ml-array-mean": "^1.1.6",
-        "ml-distance-euclidean": "^2.0.0",
-        "ml-tree-similarity": "^1.0.0"
-      }
-    },
-    "node_modules/ml-distance-euclidean": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/ml-distance-euclidean/-/ml-distance-euclidean-2.0.0.tgz",
-      "integrity": "sha512-yC9/2o8QF0A3m/0IXqCTXCzz2pNEzvmcE/9HFKOZGnTjatvBbsn4lWYJkxENkA4Ug2fnYl7PXQxnPi21sgMy/Q=="
-    },
-    "node_modules/ml-tree-similarity": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/ml-tree-similarity/-/ml-tree-similarity-1.0.0.tgz",
-      "integrity": "sha512-XJUyYqjSuUQkNQHMscr6tcjldsOoAekxADTplt40QKfwW6nd++1wHWV9AArl0Zvw/TIHgNaZZNvr8QGvE8wLRg==",
-      "dependencies": {
-        "binary-search": "^1.3.5",
-        "num-sort": "^2.0.0"
-      }
-    },
-    "node_modules/ms": {
-      "version": "2.1.3",
-      "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
-      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="
-    },
-    "node_modules/node-domexception": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/node-domexception/-/node-domexception-1.0.0.tgz",
-      "integrity": "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==",
-      "funding": [
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/jimmywarting"
-        },
-        {
-          "type": "github",
-          "url": "https://paypal.me/jimmywarting"
-        }
-      ],
-      "engines": {
-        "node": ">=10.5.0"
-      }
-    },
-    "node_modules/node-fetch": {
-      "version": "2.7.0",
-      "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
-      "integrity": "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==",
-      "dependencies": {
-        "whatwg-url": "^5.0.0"
-      },
-      "engines": {
-        "node": "4.x || >=6.0.0"
-      },
-      "peerDependencies": {
-        "encoding": "^0.1.0"
-      },
-      "peerDependenciesMeta": {
-        "encoding": {
-          "optional": true
-        }
-      }
-    },
-    "node_modules/num-sort": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/num-sort/-/num-sort-2.1.0.tgz",
-      "integrity": "sha512-1MQz1Ed8z2yckoBeSfkQHHO9K1yDRxxtotKSJ9yvcTUUxSvfvzEq5GwBrjjHEpMlq/k5gvXdmJ1SbYxWtpNoVg==",
-      "engines": {
-        "node": ">=8"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/object-hash": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/object-hash/-/object-hash-3.0.0.tgz",
-      "integrity": "sha512-RSn9F68PjH9HqtltsSnqYC1XXoWe9Bju5+213R98cNGttag9q9yAOTzdbsqvIa7aNm5WffBZFpWYr2aWrklWAw==",
-      "engines": {
-        "node": ">= 6"
-      }
-    },
-    "node_modules/openai": {
-      "version": "4.4.0",
-      "resolved": "https://registry.npmjs.org/openai/-/openai-4.4.0.tgz",
-      "integrity": "sha512-JN0t628Kh95T0IrXl0HdBqnlJg+4Vq0Bnh55tio+dfCnyzHvMLiWyCM9m726MAJD2YkDU4/8RQB6rNbEq9ct2w==",
-      "dependencies": {
-        "@types/node": "^18.11.18",
-        "@types/node-fetch": "^2.6.4",
-        "abort-controller": "^3.0.0",
-        "agentkeepalive": "^4.2.1",
-        "digest-fetch": "^1.3.0",
-        "form-data-encoder": "1.7.2",
-        "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7"
-      },
-      "bin": {
-        "openai": "bin/cli"
-      }
-    },
-    "node_modules/openapi-types": {
-      "version": "12.1.3",
-      "resolved": "https://registry.npmjs.org/openapi-types/-/openapi-types-12.1.3.tgz",
-      "integrity": "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw=="
-    },
-    "node_modules/p-finally": {
-      "version": "1.0.0",
-      "resolved": "https://registry.npmjs.org/p-finally/-/p-finally-1.0.0.tgz",
-      "integrity": "sha512-LICb2p9CB7FS+0eR1oqWnHhp0FljGLZCWBE9aix0Uye9W8LTQPwMTYVGWQWIw9RdQiDg4+epXQODwIYJtSJaow==",
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/p-queue": {
-      "version": "6.6.2",
-      "resolved": "https://registry.npmjs.org/p-queue/-/p-queue-6.6.2.tgz",
-      "integrity": "sha512-RwFpb72c/BhQLEXIZ5K2e+AhgNVmIejGlTgiB9MzZ0e93GRvqZ7uSi0dvRF7/XIXDeNkra2fNHBxTyPDGySpjQ==",
-      "dependencies": {
-        "eventemitter3": "^4.0.4",
-        "p-timeout": "^3.2.0"
-      },
-      "engines": {
-        "node": ">=8"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/p-retry": {
-      "version": "4.6.2",
-      "resolved": "https://registry.npmjs.org/p-retry/-/p-retry-4.6.2.tgz",
-      "integrity": "sha512-312Id396EbJdvRONlngUx0NydfrIQ5lsYu0znKVUzVvArzEIt08V1qhtyESbGVd1FGX7UKtiFp5uwKZdM8wIuQ==",
-      "dependencies": {
-        "@types/retry": "0.12.0",
-        "retry": "^0.13.1"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/p-timeout": {
-      "version": "3.2.0",
-      "resolved": "https://registry.npmjs.org/p-timeout/-/p-timeout-3.2.0.tgz",
-      "integrity": "sha512-rhIwUycgwwKcP9yTOOFK/AKsAopjjCakVqLHePO3CC6Mir1Z99xT+R63jZxAT5lFZLa2inS5h+ZS2GvR99/FBg==",
-      "dependencies": {
-        "p-finally": "^1.0.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/retry": {
-      "version": "0.13.1",
-      "resolved": "https://registry.npmjs.org/retry/-/retry-0.13.1.tgz",
-      "integrity": "sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg==",
-      "engines": {
-        "node": ">= 4"
-      }
-    },
-    "node_modules/tr46": {
-      "version": "0.0.3",
-      "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
-      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="
-    },
-    "node_modules/typescript": {
-      "version": "5.2.2",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.2.2.tgz",
-      "integrity": "sha512-mI4WrpHsbCIcwT9cF4FZvr80QUeKvsUsUvKDoR+X/7XHQH98xYD8YHZg7ANtz2GtZt/CBq2QJ0thkGJMHfqc1w==",
-      "dev": true,
-      "bin": {
-        "tsc": "bin/tsc",
-        "tsserver": "bin/tsserver"
-      },
-      "engines": {
-        "node": ">=14.17"
-      }
-    },
-    "node_modules/uuid": {
-      "version": "9.0.1",
-      "resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz",
-      "integrity": "sha512-b+1eJOlsR9K8HJpow9Ok3fiWOWSIcIzXodvv0rQjVoOVNpWMpxf1wZNpt4y9h10odCNrqnYp1OBzRktckBe3sA==",
-      "funding": [
-        "https://github.com/sponsors/broofa",
-        "https://github.com/sponsors/ctavan"
-      ],
-      "bin": {
-        "uuid": "dist/bin/uuid"
-      }
-    },
-    "node_modules/web-streams-polyfill": {
-      "version": "4.0.0-beta.3",
-      "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-4.0.0-beta.3.tgz",
-      "integrity": "sha512-QW95TCTaHmsYfHDybGMwO5IJIM93I/6vTRk+daHTWFPhwh+C8Cg7j7XyKrwrj8Ib6vYXe0ocYNrmzY4xAAN6ug==",
-      "engines": {
-        "node": ">= 14"
-      }
-    },
-    "node_modules/webidl-conversions": {
-      "version": "3.0.1",
-      "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
-      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="
-    },
-    "node_modules/whatwg-url": {
-      "version": "5.0.0",
-      "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
-      "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
-      "dependencies": {
-        "tr46": "~0.0.3",
-        "webidl-conversions": "^3.0.0"
-      }
-    },
-    "node_modules/yaml": {
-      "version": "2.3.2",
-      "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.3.2.tgz",
-      "integrity": "sha512-N/lyzTPaJasoDmfV7YTrYCI0G/3ivm/9wdG0aHuheKowWQwGTsK0Eoiw6utmzAnI6pkJa0DUVygvp3spqqEKXg==",
-      "engines": {
-        "node": ">= 14"
-      }
-    },
-    "node_modules/zod": {
-      "version": "3.22.4",
-      "resolved": "https://registry.npmjs.org/zod/-/zod-3.22.4.tgz",
-      "integrity": "sha512-iC+8Io04lddc+mVqQ9AZ7OQ2MrUKGN+oIQyq1vemgt46jwCwLfhq7/pwnBnNXXXZb8VTVLKwp9EDkx+ryxIWmg==",
-      "funding": {
-        "url": "https://github.com/sponsors/colinhacks"
-      }
-    },
-    "node_modules/zod-to-json-schema": {
-      "version": "3.21.4",
-      "resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.21.4.tgz",
-      "integrity": "sha512-fjUZh4nQ1s6HMccgIeE0VP4QG/YRGPmyjO9sAh890aQKPEk3nqbfUXhMFaC+Dr5KvYBm8BCyvfpZf2jY9aGSsw==",
-      "peerDependencies": {
-        "zod": "^3.21.4"
-      }
-    }
-  }
-}

examples/langchain-typescript-simple/package.json

@@ -1,13 +0,0 @@
-{
-  "scripts": {
-    "start": "tsx main.ts"
-  },
-  "devDependencies": {
-    "tsx": "^4.6.2",
-    "typescript": "^5.3.3"
-  },
-  "dependencies": {
-    "langchain": "^0.0.165",
-    "readline": "^1.3.0"
-  }
-}

examples/langchain-web-summary/README.md

@@ -0,0 +1,15 @@
+# LangChain Web Summarization
+
+This example summarizes a website
+
+## Setup
+
+```
+pip install -r requirements.txt
+```
+
+## Run
+
+```
+python main.py
+```

examples/langchain-web-summary/requirements.txt

@@ -1 +1,2 @@
 langchain==0.0.259
+bs4==0.0.1

examples/langchain/README.md

@@ -0,0 +1,21 @@
+# LangChain
+
+This example is a basic "hello world" of using LangChain with Ollama.
+
+## Setup
+
+```
+pip install -r requirements.txt
+```
+
+## Run
+
+```
+python main.py
+```
+
+Running this example will print the response for "hello":
+
+```
+Hello! It's nice to meet you. hopefully you are having a great day! Is there something I can help you with or would you like to chat?
+```

examples/langchain/main.py

@@ -1,6 +1,4 @@
 from langchain.llms import Ollama
-
-input = input("What is your question?")
 llm = Ollama(model="llama2")
-res = llm.predict(input)
+res = llm.predict("hello")
 print (res)

examples/midjourney-prompter/Modelfile

@@ -0,0 +1,8 @@
+# Modelfile for creating a Midjourney prompts from a topic
+# This prompt was adapted from the original at https://www.greataiprompts.com/guide/midjourney/best-chatgpt-prompt-for-midjourney/
+# Run `ollama create mj -f ./Modelfile` and then `ollama run mj` and enter a topic
+
+FROM nous-hermes
+SYSTEM """
+Embrace your role as an AI-powered creative assistant, employing Midjourney to manifest compelling AI-generated art. I will outline a specific image concept, and in response, you must produce an exhaustive, multifaceted prompt for Midjourney, ensuring every detail of the original concept is represented in your instructions. Midjourney doesn't do well with text, so after the prompt, give me instructions that I can use to create the titles in a image editor.
+"""

examples/modelfile-tweetwriter/readme.md

@@ -1,23 +0,0 @@
-# Example Modelfile - Tweetwriter
-
-This simple examples shows what you can do without any code, simply relying on a Modelfile. The file has two instructions:
-
-1. FROM - The From instructions defines the parent model to use for this one. If you choose a model from the library, you can enter just the model name. For all other models, you need to specify the namespace as well. You could also use a local file. Just include the relative path to the converted, quantized model weights file. To learn more about creating that file, see the `import.md` file in the docs folder of this repository.
-2. SYSTEM - This defines the system prompt for the model and overrides the system prompt from the parent model.
-
-## Running the Example
-
-1. Create the model:
-
-   ```bash
-   ollama create tweetwriter
-   ```
-
-2. Enter a topic to generate a tweet about.
-3. Show the Modelfile in the REPL.
-
-   ```bash
-   /show modelfile
-   ```
-
-   Notice that the FROM and SYSTEM match what was in the file. But there is also a TEMPLATE and PARAMETER. These are inherited from the parent model.

examples/privategpt/constants.py

@@ -6,6 +6,7 @@ PERSIST_DIRECTORY = os.environ.get('PERSIST_DIRECTORY', 'db')
 
 # Define the Chroma settings
 CHROMA_SETTINGS = Settings(
+        chroma_db_impl='duckdb+parquet',
         persist_directory=PERSIST_DIRECTORY,
         anonymized_telemetry=False
 )

examples/privategpt/ingest.py

@@ -150,7 +150,7 @@ def main():
         print("Creating new vectorstore")
         texts = process_documents()
         print(f"Creating embeddings. May take some minutes...")
-        db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory)
+        db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
     db.persist()
     db = None
 

examples/privategpt/privateGPT.py

@@ -4,7 +4,6 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.vectorstores import Chroma
 from langchain.llms import Ollama
-import chromadb
 import os
 import argparse
 import time
@@ -23,9 +22,7 @@ def main():
     # Parse the command line arguments
     args = parse_arguments()
     embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
-
-    db = Chroma(persist_directory=persist_directory, embedding_function=embeddings)
-
+    db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
     retriever = db.as_retriever(search_kwargs={"k": target_source_chunks})
     # activate/deactivate the streaming StdOut callback for LLMs
     callbacks = [] if args.mute_stream else [StreamingStdOutCallbackHandler()]

examples/python-dockerit/README.md

@@ -1,31 +0,0 @@
-# DockerIt
-
-DockerIt is a tool to help you build and run your application in a Docker container. It consists of a model that defines the system prompt and model weights to use, along with a python script to then build the container and run the image automatically.
-
-## Running the Example
-
-1. Ensure you have the `mattw/dockerit` model installed:
-
-   ```bash
-   ollama pull mattw/dockerit
-   ```
-
-2. Make sure Docker is running on your machine.
-
-3. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-4. Run the example:
-
-   ```bash
-   python dockerit.py "simple postgres server with admin password set to 123"
-   ```
-
-5. Enter the name you would like to use for your container image.
-
-## Caveats
-
-This is a simple example. It's assuming the Dockerfile content generated is going to work. In many cases, even with simple web servers, it fails when trying to copy files that don't exist. It's simply an example of what you could possibly do.

examples/python-json-datagenerator/predefinedschema.py

@@ -1,31 +0,0 @@
-import requests
-import json
-import random
-
-model = "llama2"
-template = {
-  "firstName": "", 
-  "lastName": "", 
-  "address": {
-    "street": "", 
-    "city": "", 
-    "state": "", 
-    "zipCode": ""
-  }, 
-  "phoneNumber": ""
-}
-
-prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in the US, and  phone number. \nUse the following template: {json.dumps(template)}."
-
-data = {
-    "prompt": prompt,
-    "model": model,
-    "format": "json",
-    "stream": False,
-    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
-}
-
-print(f"Generating a sample user")
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
-json_data = json.loads(response.text)
-print(json.dumps(json.loads(json_data["response"]), indent=2))

examples/python-json-datagenerator/randomaddresses.py

@@ -1,31 +0,0 @@
-import requests
-import json
-import random
-
-countries = [
-    "United States",
-    "United Kingdom",
-    "the Netherlands",
-    "Germany",
-    "Mexico",
-    "Canada",
-    "France",
-]
-country = random.choice(countries)
-model = "llama2"
-
-prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and phone number. Do not use common names. Respond using JSON. Key names should have no backslashes, values should use plain ascii with no special characters."
-
-data = {
-    "prompt": prompt,
-    "model": model,
-    "format": "json",
-    "stream": False,
-    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
-}
-
-print(f"Generating a sample user in {country}")
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
-json_data = json.loads(response.text)
-
-print(json.dumps(json.loads(json_data["response"]), indent=2))

examples/python-json-datagenerator/readme.md

@@ -1,60 +0,0 @@
-# JSON Output Example
-
-![llmjson 2023-11-10 15_31_31](https://github.com/jmorganca/ollama/assets/633681/e599d986-9b4a-4118-81a4-4cfe7e22da25)
-
-There are two python scripts in this example. `randomaddresses.py` generates random addresses from different countries. `predefinedschema.py` sets a template for the model to fill in.
-
-## Running the Example
-
-1. Ensure you have the `llama2` model installed:
-
-   ```bash
-   ollama pull llama2
-   ```
-
-2. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Run the Random Addresses example:
-
-   ```bash
-   python randomaddresses.py
-   ```
-
-4. Run the Predefined Schema example:
-
-   ```bash
-   python predefinedschema.py
-   ```
-
-## Review the Code
-
-Both programs are basically the same, with a different prompt for each, demonstrating two different ideas. The key part of getting JSON out of a model is to state in the prompt or system prompt that it should respond using JSON, and specifying the `format` as `json` in the data body.
-
-```python
-prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and  phone number. Do not use common names. Respond using JSON. Key names should with no backslashes, values should use plain ascii with no special characters."
-
-data = {
-    "prompt": prompt,
-    "model": model,
-    "format": "json",
-    "stream": False,
-    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
-}
-```
-
-When running `randomaddresses.py` you will see that the schema changes and adapts to the chosen country.
-
-In `predefinedschema.py`, a template has been specified in the prompt as well. It's been defined as JSON and then dumped into the prompt string to make it easier to work with.
-
-Both examples turn streaming off so that we end up with the completed JSON all at once. We need to convert the `response.text` to JSON so that when we output it as a string we can set the indent spacing to make the output easy to read.
-
-```python
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
-json_data = json.loads(response.text)
-
-print(json.dumps(json.loads(json_data["response"]), indent=2))
-```

examples/python-json-datagenerator/requirements.txt

@@ -1 +0,0 @@
-Requests==2.31.0

examples/python-loganalysis/Modelfile

@@ -1,8 +0,0 @@
-FROM codebooga:latest
-
-SYSTEM """
-You are a log file analyzer. You will receive a set of lines from a log file for some software application, find the errors and other interesting aspects of the logs, and explain them so a new user can understand what they mean. If there are any steps they can do to resolve them, list the steps in your answer.
-"""
-
-PARAMETER TEMPERATURE 0.3
-

examples/python-loganalysis/loganalysis.py

@@ -1,41 +0,0 @@
-import sys
-import re
-import requests
-import json
-
-# prelines and postlines represent the number of lines of context to include in the output around the error
-prelines = 10
-postlines = 10
-
-def find_errors_in_log_file():
-  if len(sys.argv) < 2:
-    print("Usage: python loganalysis.py <filename>")
-    return
-
-  log_file_path = sys.argv[1]
-  with open(log_file_path, 'r') as log_file:
-    log_lines = log_file.readlines()
-
-  error_logs = []
-  for i, line in enumerate(log_lines):
-      if "error" in line.lower():
-          start_index = max(0, i - prelines)
-          end_index = min(len(log_lines), i + postlines + 1)
-          error_logs.extend(log_lines[start_index:end_index])
-
-  return error_logs
-
-error_logs = find_errors_in_log_file()
-
-data = {
-  "prompt": "\n".join(error_logs), 
-  "model": "mattw/loganalyzer"
-}
-
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=True)
-for line in response.iter_lines():
-  if line:
-    json_data = json.loads(line)
-    if json_data['done'] == False:
-      print(json_data['response'], end='', flush=True)
-

examples/python-loganalysis/logtest.logfile

@@ -1,32 +0,0 @@
-2023-11-10 07:17:40 /docker-entrypoint.sh: /docker-entrypoint.d/ is not empty, will attempt to perform configuration
-2023-11-10 07:17:40 /docker-entrypoint.sh: Looking for shell scripts in /docker-entrypoint.d/
-2023-11-10 07:17:40 /docker-entrypoint.sh: Launching /docker-entrypoint.d/10-listen-on-ipv6-by-default.sh
-2023-11-10 07:17:40 10-listen-on-ipv6-by-default.sh: info: Getting the checksum of /etc/nginx/conf.d/default.conf
-2023-11-10 07:17:40 10-listen-on-ipv6-by-default.sh: info: Enabled listen on IPv6 in /etc/nginx/conf.d/default.conf
-2023-11-10 07:17:40 /docker-entrypoint.sh: Sourcing /docker-entrypoint.d/15-local-resolvers.envsh
-2023-11-10 07:17:40 /docker-entrypoint.sh: Launching /docker-entrypoint.d/20-envsubst-on-templates.sh
-2023-11-10 07:17:40 /docker-entrypoint.sh: Launching /docker-entrypoint.d/30-tune-worker-processes.sh
-2023-11-10 07:17:40 /docker-entrypoint.sh: Configuration complete; ready for start up
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: using the "epoll" event method
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: nginx/1.25.3
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: built by gcc 12.2.0 (Debian 12.2.0-14) 
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: OS: Linux 6.4.16-linuxkit
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: getrlimit(RLIMIT_NOFILE): 1048576:1048576
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker processes
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 29
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 30
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 31
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 32
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 33
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 34
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 35
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 36
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 37
-2023-11-10 07:17:40 2023/11/10 13:17:40 [notice] 1#1: start worker process 38
-2023-11-10 07:17:44 192.168.65.1 - - [10/Nov/2023:13:17:43 +0000] "GET / HTTP/1.1" 200 615 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"
-2023-11-10 07:17:44 2023/11/10 13:17:44 [error] 29#29: *1 open() "/usr/share/nginx/html/favicon.ico" failed (2: No such file or directory), client: 192.168.65.1, server: localhost, request: "GET /favicon.ico HTTP/1.1", host: "localhost:8080", referrer: "http://localhost:8080/"
-2023-11-10 07:17:44 192.168.65.1 - - [10/Nov/2023:13:17:44 +0000] "GET /favicon.ico HTTP/1.1" 404 555 "http://localhost:8080/" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"
-2023-11-10 07:17:50 2023/11/10 13:17:50 [error] 29#29: *1 open() "/usr/share/nginx/html/ahstat" failed (2: No such file or directory), client: 192.168.65.1, server: localhost, request: "GET /ahstat HTTP/1.1", host: "localhost:8080"
-2023-11-10 07:17:50 192.168.65.1 - - [10/Nov/2023:13:17:50 +0000] "GET /ahstat HTTP/1.1" 404 555 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"
-2023-11-10 07:18:53 2023/11/10 13:18:53 [error] 29#29: *1 open() "/usr/share/nginx/html/ahstat" failed (2: No such file or directory), client: 192.168.65.1, server: localhost, request: "GET /ahstat HTTP/1.1", host: "localhost:8080"
-2023-11-10 07:18:53 192.168.65.1 - - [10/Nov/2023:13:18:53 +0000] "GET /ahstat HTTP/1.1" 404 555 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36" "-"

examples/python-loganalysis/readme.md

@@ -1,70 +0,0 @@
-# Log Analysis example
-
-![loganalyzer 2023-11-10 08_53_29](https://github.com/jmorganca/ollama/assets/633681/ad30f1fc-321f-4953-8914-e30e24db9921)
-
-This example shows one possible way to create a log file analyzer. It uses the model **mattw/loganalyzer** which is based on **codebooga**, a 34b parameter model.
-
-To use it, run:
-
-`python loganalysis.py <logfile>`
-
-You can try this with the `logtest.logfile` file included in this directory.
-
-## Running the Example
-
-1. Ensure you have the `mattw/loganalyzer` model installed:
-
-   ```bash
-   ollama pull mattw/loganalyzer
-   ```
-
-2. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Run the example:
-
-   ```bash
-   python loganalysis.py logtest.logfile
-   ```
-
-## Review the code
-
-The first part of this example is a Modelfile that takes `codebooga` and applies a new System Prompt:
-
-```plaintext
-SYSTEM """
-You are a log file analyzer. You will receive a set of lines from a log file for some software application, find the errors and other interesting aspects of the logs, and explain them so a new user can understand what they mean. If there are any steps they can do to resolve them, list the steps in your answer.
-"""
-```
-
-This model is available at https://ollama.ai/mattw/loganalyzer. You can customize it and add to your own namespace using the command `ollama create <namespace/modelname> -f <path-to-modelfile>` then `ollama push <namespace/modelname>`.
-
-Then loganalysis.py scans all the lines in the given log file and searches for the word 'error'. When the word is found, the 10 lines before and after are set as the prompt for a call to the Generate API.
-
-```python
-data = {
-  "prompt": "\n".join(error_logs), 
-  "model": "mattw/loganalyzer"
-}
-```
-
-Finally, the streamed output is parsed and the response field in the output is printed to the line.
-
-```python
-response = requests.post("http://localhost:11434/api/generate", json=data, stream=True)
-for line in response.iter_lines():
-  if line:
-    json_data = json.loads(line)
-    if json_data['done'] == False:
-      print(json_data['response'], end='')
-
-```
-
-## Next Steps
-
-There is a lot more that can be done here. This is a simple way to detect errors, looking for the word error. Perhaps it would be interesting to find anomalous activity in the logs. It could be interesting to create embeddings for each line and compare them, looking for similar lines. Or look into applying Levenshtein Distance algorithms to find similar lines to help identify the anomalous lines.
-
-Try different models and different prompts to analyze the data. You could consider adding retrieval augmented generation (RAG) to this to help understand newer log formats.

examples/python-loganalysis/requirements.txt

@@ -1 +0,0 @@
-Requests==2.31.0

examples/python-rag-newssummary/README.md

@@ -1,35 +0,0 @@
-# News Summarizer
-
-This example goes through a series of steps:
-
-  1. You choose a topic area (e.g., "news", "NVidia", "music", etc.).
-  2. Gets the most recent articles on that topic from various sources.
-  3. Uses Ollama to summarize each article.
-  4. Creates chunks of sentences from each article.
-  5. Uses Sentence Transformers to generate embeddings for each of those chunks.
-  6. You enter a question regarding the summaries shown.
-  7. Uses Sentence Transformers to generate an embedding for that question.
-  8. Uses the embedded question to find the most similar chunks.
-  9. Feeds all that to Ollama to generate a good answer to your question based on these news articles.
-
-This example lets you pick from a few different topic areas, then summarize the most recent x articles for that topic. It then creates chunks of sentences from each article and then generates embeddings for each of those chunks.
-
-## Running the Example
-
-1. Ensure you have the `mistral-openorca` model installed:
-
-   ```bash
-   ollama pull mistral-openorca
-   ```
-
-2. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Run the example:
-
-   ```bash
-   python summ.py
-   ```

examples/python-rag-newssummary/requirements.txt

@@ -1,9 +0,0 @@
-beautifulsoup4==4.12.2
-feedparser==6.0.10
-mattsollamatools==0.0.8
-newspaper3k==0.2.8
-nltk==3.8.1
-numpy==1.24.3
-Requests==2.31.0
-scikit_learn==1.3.0
-sentence_transformers==2.2.2

examples/python-rag-newssummary/summ.py

@@ -1,86 +0,0 @@
-import curses
-import json
-from utils import get_url_for_topic, topic_urls, menu, getUrls, get_summary, getArticleText, knn_search
-import requests
-from sentence_transformers import SentenceTransformer
-from mattsollamatools import chunker
-
-if __name__ == "__main__":
-    chosen_topic = curses.wrapper(menu)
-    print("Here is your news summary:\n")
-    urls = getUrls(chosen_topic, n=5)
-    model = SentenceTransformer('all-MiniLM-L6-v2')
-    allEmbeddings = []
-
-    for url in urls:
-      article={}
-      article['embeddings'] = []
-      article['url'] = url
-      text = getArticleText(url)
-      summary = get_summary(text)
-      chunks = chunker(text)  # Use the chunk_text function from web_utils
-      embeddings = model.encode(chunks)
-      for (chunk, embedding) in zip(chunks, embeddings):
-        item = {}
-        item['source'] = chunk
-        item['embedding'] = embedding.tolist()  # Convert NumPy array to list
-        item['sourcelength'] = len(chunk)
-        article['embeddings'].append(item)
-    
-      allEmbeddings.append(article)
-
-      print(f"{summary}\n")
-
-    
-    while True:
-      context = []
-      # Input a question from the user
-      question = input("Enter your question about the news, or type quit: ")
-
-      if question.lower() == 'quit':
-        break
-
-      # Embed the user's question
-      question_embedding = model.encode([question])
-
-      # Perform KNN search to find the best matches (indices and source text)
-      best_matches = knn_search(question_embedding, allEmbeddings, k=10)
-
-
-      sourcetext=""
-      for i, (index, source_text) in enumerate(best_matches, start=1):
-          sourcetext += f"{i}. Index: {index}, Source Text: {source_text}"
-
-      systemPrompt = f"Only use the following information to answer the question. Do not use anything else: {sourcetext}"
-
-      url = "http://localhost:11434/api/generate"
-
-      payload = {
-      "model": "mistral-openorca",
-      "prompt": question, 
-      "system": systemPrompt,
-      "stream": False, 
-      "context": context
-      }
-
-      # Convert the payload to a JSON string
-      payload_json = json.dumps(payload)
-
-      # Set the headers to specify JSON content
-      headers = {
-          "Content-Type": "application/json"
-      }
-
-      # Send the POST request
-      response = requests.post(url, data=payload_json, headers=headers)
-
-      # Check the response
-      if response.status_code == 200:
-          output = json.loads(response.text)
-          context = output['context']
-          print(output['response']+ "\n")
-          
-
-      else:
-          print(f"Request failed with status code {response.status_code}")
-

examples/python-rag-newssummary/utils.py

@@ -1,108 +0,0 @@
-import curses
-import feedparser
-import requests
-import unicodedata
-import json
-from newspaper import Article
-from bs4 import BeautifulSoup
-from nltk.tokenize import sent_tokenize, word_tokenize
-import numpy as np
-from sklearn.neighbors import NearestNeighbors
-from mattsollamatools import chunker
-
-# Create a dictionary to store topics and their URLs
-topic_urls = {
-    "Mac": "https://9to5mac.com/guides/mac/feed",
-    "News": "http://www.npr.org/rss/rss.php?id=1001",
-    "Nvidia": "https://nvidianews.nvidia.com/releases.xml",
-    "Raspberry Pi": "https://www.raspberrypi.com/news/feed/", 
-    "Music": "https://www.billboard.com/c/music/music-news/feed/"
-}
-
-# Use curses to create a menu of topics
-def menu(stdscr):
-    chosen_topic = get_url_for_topic(stdscr)  
-    url = topic_urls[chosen_topic] if chosen_topic in topic_urls else "Topic not found"
-    
-    stdscr.addstr(len(topic_urls) + 3, 0, f"Selected URL for {chosen_topic}: {url}")
-    stdscr.refresh()
-    
-    return chosen_topic
-
-# You have chosen a topic. Now return the url for that topic
-def get_url_for_topic(stdscr):
-    curses.curs_set(0)  # Hide the cursor
-    stdscr.clear()
-
-    stdscr.addstr(0, 0, "Choose a topic using the arrow keys (Press Enter to select):")
-
-    # Create a list of topics
-    topics = list(topic_urls.keys())
-    current_topic = 0
-
-    while True:
-        for i, topic in enumerate(topics):
-            if i == current_topic:
-                stdscr.addstr(i + 2, 2, f"> {topic}")
-            else:
-                stdscr.addstr(i + 2, 2, f"  {topic}")
-
-        stdscr.refresh()
-
-        key = stdscr.getch()
-
-        if key == curses.KEY_DOWN and current_topic < len(topics) - 1:
-            current_topic += 1
-        elif key == curses.KEY_UP and current_topic > 0:
-            current_topic -= 1
-        elif key == 10:  # Enter key
-            return topic_urls[topics[current_topic]]
-
-# Get the last N URLs from an RSS feed
-def getUrls(feed_url, n=20):
-    feed = feedparser.parse(feed_url)
-    entries = feed.entries[-n:]
-    urls = [entry.link for entry in entries]
-    return urls
-
-# Often there are a bunch of ads and menus on pages for a news article. This uses newspaper3k to get just the text of just the article.
-def getArticleText(url):
-  article = Article(url)
-  article.download()
-  article.parse()
-  return article.text
-
-def get_summary(text):
-  systemPrompt = "Write a concise summary of the text, return your responses with 5 lines that cover the key points of the text given."
-  prompt = text
-  
-  url = "http://localhost:11434/api/generate"
-
-  payload = {
-    "model": "mistral-openorca",
-    "prompt": prompt, 
-    "system": systemPrompt,
-    "stream": False
-  }
-  payload_json = json.dumps(payload)
-  headers = {"Content-Type": "application/json"}
-  response = requests.post(url, data=payload_json, headers=headers)
-
-  return json.loads(response.text)["response"]
-
-# Perform K-nearest neighbors (KNN) search
-def knn_search(question_embedding, embeddings, k=5):
-    X = np.array([item['embedding'] for article in embeddings for item in article['embeddings']])
-    source_texts = [item['source'] for article in embeddings for item in article['embeddings']]
-    
-    # Fit a KNN model on the embeddings
-    knn = NearestNeighbors(n_neighbors=k, metric='cosine')
-    knn.fit(X)
-    
-    # Find the indices and distances of the k-nearest neighbors
-    distances, indices = knn.kneighbors(question_embedding, n_neighbors=k)
-    
-    # Get the indices and source texts of the best matches
-    best_matches = [(indices[0][i], source_texts[indices[0][i]]) for i in range(k)]
-    
-    return best_matches

examples/python-simplechat/client.py

@@ -1,47 +0,0 @@
-import json
-import requests
-
-# NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve`
-model = "llama2"  # TODO: update this for whatever model you wish to use
-
-
-def chat(messages):
-    r = requests.post(
-        "http://0.0.0.0:11434/api/chat",
-        json={"model": model, "messages": messages, "stream": True},
-    )
-    r.raise_for_status()
-    output = ""
-
-    for line in r.iter_lines():
-        body = json.loads(line)
-        if "error" in body:
-            raise Exception(body["error"])
-        if body.get("done") is False:
-            message = body.get("message", "")
-            content = message.get("content", "")
-            output += content
-            # the response streams one token at a time, print that as we receive it
-            print(content, end="", flush=True)
-
-        if body.get("done", False):
-            message["content"] = output
-            return message
-
-
-def main():
-    messages = []
-
-    while True:
-        user_input = input("Enter a prompt: ")
-        if not user_input:
-            exit()
-        print()
-        messages.append({"role": "user", "content": user_input})
-        message = chat(messages)
-        messages.append(message)
-        print("\n\n")
-
-
-if __name__ == "__main__":
-    main()

examples/python-simplechat/readme.md

@@ -1,44 +0,0 @@
-# Simple Chat Example
-
-The **chat** endpoint is one of two ways to generate text from an LLM with Ollama, and is introduced in version 0.1.14. At a high level, you provide the endpoint an array of objects with a role and content specified. Then with each output and prompt, you add more of those role/content objects, which builds up the history.
-
-## Running the Example
-
-1. Ensure you have the `llama2` model installed:
-
-   ```bash
-   ollama pull llama2
-   ```
-
-2. Install the Python Requirements.
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Run the example:
-
-   ```bash
-   python client.py
-   ```
-
-## Review the Code
-
-You can see in the **chat** function that actually calling the endpoint is done simply with:
-
-```python
-r = requests.post(
-  "http://0.0.0.0:11434/api/chat",
-  json={"model": model, "messages": messages, "stream": True},
-)
-```
-
-With the **generate** endpoint, you need to provide a `prompt`. But with **chat**, you provide `messages`. And the resulting stream of responses includes a `message` object with a `content` field.
-
-The final JSON object doesn't provide the full content, so you will need to build the content yourself.
-
-In the **main** function, we collect `user_input` and add it as a message to our messages and that is passed to the chat function. When the LLM is done responding the output is added as another message.
-
-## Next Steps
-
-In this example, all generations are kept. You might want to experiment with summarizing everything older than 10 conversations to enable longer history with less context being used.

examples/python-simplechat/requirements.txt

@@ -1 +0,0 @@
-Requests==2.31.0