inital pass at replacing ":" with "-" in image on-disk names

---------

Co-authored-by: Chris-AS1 <8493773+Chris-AS1@users.noreply.github.com>

.dockerignore

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

.github/workflows/test.yaml

@@ -0,0 +1,177 @@
+name: test
+
+on:
+  pull_request:
+    paths:
+      - '**/*'
+      - '!docs/**'
+      - '!examples/**'
+      - '!README.md'
+
+jobs:
+  generate:
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-2019]
+        arch: [amd64, arm64]
+        exclude:
+          - os: ubuntu-latest
+            arch: arm64
+          - os: windows-2019
+            arch: arm64
+    runs-on: ${{ matrix.os }}
+    env:
+      GOARCH: ${{ matrix.arch }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version: '1.22'
+          cache: true
+      - run: go get ./...
+      - run: |
+          $gopath=(get-command go).source | split-path -parent
+          & "C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\Common7\Tools\Launch-VsDevShell.ps1"
+          cd $env:GITHUB_WORKSPACE
+          $env:CMAKE_SYSTEM_VERSION="10.0.22621.0"
+          $env:PATH="$gopath;$env:PATH"
+          go generate -x ./...
+        if: ${{ startsWith(matrix.os, 'windows-') }}
+        name: "Windows Go Generate"
+      - run: go generate -x ./...
+        if: ${{ ! startsWith(matrix.os, 'windows-') }}
+        name: "Unix Go Generate"
+      - uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.os }}-${{ matrix.arch }}-libraries
+          path: llm/llama.cpp/build/**/lib/*
+  generate-cuda:
+    strategy:
+      matrix:
+        cuda-version:
+          - '11.8.0'
+    runs-on: linux
+    container: nvidia/cuda:${{ matrix.cuda-version }}-devel-ubuntu20.04
+    steps:
+      - run: |
+          apt-get update && apt-get install -y git build-essential curl
+          curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
+            | tar -zx -C /usr --strip-components 1
+        env:
+          DEBIAN_FRONTEND: noninteractive
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v4
+        with:
+          go-version: '1.22'
+          cache: true
+      - run: go get ./...
+      - run: |
+          git config --global --add safe.directory /__w/ollama/ollama
+          go generate -x ./...
+        env:
+          OLLAMA_SKIP_CPU_GENERATE: '1'
+      - uses: actions/upload-artifact@v4
+        with:
+          name: cuda-${{ matrix.cuda-version }}-libraries
+          path: llm/llama.cpp/build/**/lib/*
+  generate-rocm:
+    strategy:
+      matrix:
+        rocm-version:
+          - '6.0'
+    runs-on: linux
+    container: rocm/dev-ubuntu-20.04:${{ matrix.rocm-version }}
+    steps:
+      - run: |
+          apt-get update && apt-get install -y git build-essential curl rocm-libs
+          curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.28.1/cmake-3.28.1-linux-x86_64.tar.gz \
+            | tar -zx -C /usr --strip-components 1
+        env:
+          DEBIAN_FRONTEND: noninteractive
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v4
+        with:
+          go-version: '1.22'
+          cache: true
+      - run: go get ./...
+      - run: |
+          git config --global --add safe.directory /__w/ollama/ollama
+          go generate -x ./...
+        env:
+          OLLAMA_SKIP_CPU_GENERATE: '1'
+      - uses: actions/upload-artifact@v4
+        with:
+          name: rocm-${{ matrix.rocm-version }}-libraries
+          path: llm/llama.cpp/build/**/lib/*
+  lint:
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-2019]
+        arch: [amd64, arm64]
+        exclude:
+          - os: ubuntu-latest
+            arch: arm64
+          - os: windows-2019
+            arch: arm64
+          - os: macos-latest
+            arch: amd64
+    runs-on: ${{ matrix.os }}
+    env:
+      GOARCH: ${{ matrix.arch }}
+      CGO_ENABLED: '1'
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+      - uses: actions/setup-go@v5
+        with:
+          go-version: '1.22'
+          cache: false
+      - run: |
+          mkdir -p llm/llama.cpp/build/linux/${{ matrix.arch }}/stub/lib/
+          touch llm/llama.cpp/build/linux/${{ matrix.arch }}/stub/lib/stub.so
+        if: ${{ startsWith(matrix.os, 'ubuntu-') }}
+      - run: |
+          mkdir -p llm/llama.cpp/build/darwin/${{ matrix.arch }}/stub/lib/
+          touch llm/llama.cpp/build/darwin/${{ matrix.arch }}/stub/lib/stub.dylib
+          touch llm/llama.cpp/ggml-metal.metal
+        if: ${{ startsWith(matrix.os, 'macos-') }}
+      - run: |
+          mkdir -p llm/llama.cpp/build/windows/${{ matrix.arch }}/stub/lib/
+          touch llm/llama.cpp/build/windows/${{ matrix.arch }}/stub/lib/stub.dll
+        if: ${{ startsWith(matrix.os, 'windows-') }}
+      - uses: golangci/golangci-lint-action@v3
+  test:
+    needs: generate
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-2019]
+        arch: [amd64]
+        exclude:
+          - os: ubuntu-latest
+            arch: arm64
+          - os: windows-2019
+            arch: arm64
+    runs-on: ${{ matrix.os }}
+    env:
+      GOARCH: ${{ matrix.arch }}
+      CGO_ENABLED: '1'
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+      - uses: actions/setup-go@v5
+        with:
+          go-version: '1.22'
+          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 ./...
+      - uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.os }}-binaries
+          path: ollama

.gitignore

@@ -8,4 +8,6 @@ ollama
 ggml-metal.metal
 .cache
 *.exe
-.idea
+.idea
+test_data
+*.crt

.gitmodules

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

.golangci.yaml

@@ -0,0 +1,27 @@
+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 +1,135 @@
-FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
+ARG GOLANG_VERSION=1.22.1
+ARG CMAKE_VERSION=3.22.1
+ARG CUDA_VERSION=11.3.1
+ARG ROCM_VERSION=6.0
 
-ARG TARGETARCH
-ARG GOFLAGS="'-ldflags=-w -s'"
+# Copy the minimal context we need to run the generate scripts
+FROM scratch AS llm-code
+COPY .git .git
+COPY .gitmodules .gitmodules
+COPY llm llm
 
+FROM --platform=linux/amd64 nvidia/cuda:$CUDA_VERSION-devel-centos7 AS cuda-build-amd64
+ARG CMAKE_VERSION
+COPY ./scripts/rh_linux_deps.sh /
+RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
+ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
+COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
+WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
+ARG CGO_CFLAGS
+RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
+
+FROM --platform=linux/arm64 nvidia/cuda:$CUDA_VERSION-devel-rockylinux8 AS cuda-build-arm64
+ARG CMAKE_VERSION
+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
+ARG CGO_CFLAGS
+RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
+
+FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCM_VERSION}-complete AS rocm-build-amd64
+ARG CMAKE_VERSION
+COPY ./scripts/rh_linux_deps.sh /
+RUN CMAKE_VERSION=${CMAKE_VERSION} sh /rh_linux_deps.sh
+ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
+ENV LIBRARY_PATH /opt/amdgpu/lib64
+COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
+WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
+ARG CGO_CFLAGS
+ARG AMDGPU_TARGETS
+RUN OLLAMA_SKIP_CPU_GENERATE=1 sh gen_linux.sh
+RUN mkdir /tmp/scratch && \
+    for dep in $(cat /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/x86_64/rocm*/lib/deps.txt) ; do \
+        cp ${dep} /tmp/scratch/ || exit 1 ; \
+    done && \
+    (cd /opt/rocm/lib && tar cf - rocblas/library) | (cd /tmp/scratch/ && tar xf - ) && \
+    mkdir -p /go/src/github.com/jmorganca/ollama/dist/deps/ && \
+    (cd /tmp/scratch/ && tar czvf /go/src/github.com/jmorganca/ollama/dist/deps/ollama-linux-amd64-rocm.tgz . )
+
+
+FROM --platform=linux/amd64 centos:7 AS cpu-builder-amd64
+ARG CMAKE_VERSION
+ARG GOLANG_VERSION
+COPY ./scripts/rh_linux_deps.sh /
+RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
+ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
+COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
+ARG OLLAMA_CUSTOM_CPU_DEFS
+ARG CGO_CFLAGS
+WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
+
+FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu-build-amd64
+RUN OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
+FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx-build-amd64
+RUN OLLAMA_CPU_TARGET="cpu_avx" sh gen_linux.sh
+FROM --platform=linux/amd64 cpu-builder-amd64 AS cpu_avx2-build-amd64
+RUN OLLAMA_CPU_TARGET="cpu_avx2" sh gen_linux.sh
+
+FROM --platform=linux/arm64 centos:7 AS cpu-build-arm64
+ARG CMAKE_VERSION
+ARG GOLANG_VERSION
+COPY ./scripts/rh_linux_deps.sh /
+RUN CMAKE_VERSION=${CMAKE_VERSION} GOLANG_VERSION=${GOLANG_VERSION} sh /rh_linux_deps.sh
+ENV PATH /opt/rh/devtoolset-10/root/usr/bin:$PATH
+COPY --from=llm-code / /go/src/github.com/jmorganca/ollama/
+WORKDIR /go/src/github.com/jmorganca/ollama/llm/generate
+# Note, we only build the "base" CPU variant on arm since avx/avx2 are x86 features
+ARG OLLAMA_CUSTOM_CPU_DEFS
+ARG CGO_CFLAGS
+RUN OLLAMA_CPU_TARGET="cpu" sh gen_linux.sh
+
+# Intermediate stage used for ./scripts/build_linux.sh
+FROM --platform=linux/amd64 cpu-build-amd64 AS build-amd64
+ENV CGO_ENABLED 1
 WORKDIR /go/src/github.com/jmorganca/ollama
-RUN apt-get update && apt-get install -y git build-essential cmake
-ADD https://dl.google.com/go/go1.21.3.linux-$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
-
 COPY . .
-ENV GOARCH=$TARGETARCH
-ENV GOFLAGS=$GOFLAGS
-RUN /usr/local/go/bin/go generate ./... \
-    && /usr/local/go/bin/go build .
+COPY --from=cpu_avx-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
+COPY --from=cpu_avx2-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
+COPY --from=cuda-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
+COPY --from=rocm-build-amd64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
+COPY --from=rocm-build-amd64 /go/src/github.com/jmorganca/ollama/dist/deps/ ./dist/deps/
+ARG GOFLAGS
+ARG CGO_CFLAGS
+RUN go build -trimpath .
 
-FROM ubuntu:22.04
+# Intermediate stage used for ./scripts/build_linux.sh
+FROM --platform=linux/arm64 cpu-build-arm64 AS build-arm64
+ENV CGO_ENABLED 1
+ARG GOLANG_VERSION
+WORKDIR /go/src/github.com/jmorganca/ollama
+COPY . .
+COPY --from=cuda-build-arm64 /go/src/github.com/jmorganca/ollama/llm/llama.cpp/build/linux/ llm/llama.cpp/build/linux/
+ARG GOFLAGS
+ARG CGO_CFLAGS
+RUN go build -trimpath .
+
+# Runtime stages
+FROM --platform=linux/amd64 ubuntu:22.04 as runtime-amd64
 RUN apt-get update && apt-get install -y ca-certificates
-COPY --from=0 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
+COPY --from=build-amd64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
+FROM --platform=linux/arm64 ubuntu:22.04 as runtime-arm64
+RUN apt-get update && apt-get install -y ca-certificates
+COPY --from=build-arm64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
+
+# Radeon images are much larger so we keep it distinct from the CPU/CUDA image
+FROM --platform=linux/amd64 rocm/dev-centos-7:${ROCM_VERSION}-complete as runtime-rocm
+RUN update-pciids
+COPY --from=build-amd64 /go/src/github.com/jmorganca/ollama/ollama /bin/ollama
 EXPOSE 11434
 ENV OLLAMA_HOST 0.0.0.0
 
-# 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
+ENTRYPOINT ["/bin/ollama"]
+CMD ["serve"]
+
+FROM runtime-$TARGETARCH
+EXPOSE 11434
+ENV OLLAMA_HOST 0.0.0.0
+ENV PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
 ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
+ENV NVIDIA_VISIBLE_DEVICES=all
 
 ENTRYPOINT ["/bin/ollama"]
 CMD ["serve"]

Dockerfile.build

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

README.md

@@ -1,8 +1,5 @@
 <div align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" height="200px" srcset="https://github.com/jmorganca/ollama/assets/3325447/56ea1849-1284-4645-8970-956de6e51c3c">
-    <img alt="logo" height="200px" src="https://github.com/jmorganca/ollama/assets/3325447/0d0b44e2-8f4a-4e99-9b52-a5c1c741c8f7">
-  </picture>
+  <img alt="ollama" height="200px" src="https://github.com/jmorganca/ollama/assets/3325447/0d0b44e2-8f4a-4e99-9b52-a5c1c741c8f7">
 </div>
 
 # Ollama
@@ -13,16 +10,16 @@ Get up and running with large language models locally.
 
 ### macOS
 
-[Download](https://ollama.ai/download/Ollama-darwin.zip)
+[Download](https://ollama.com/download/Ollama-darwin.zip)
 
-### Windows
+### Windows preview
 
-Coming soon!
+[Download](https://ollama.com/download/OllamaSetup.exe)
 
-### Linux & WSL2
+### Linux
 
 ```
-curl https://ollama.ai/install.sh | sh
+curl -fsSL https://ollama.com/install.sh | sh
 ```
 
 [Manual install instructions](https://github.com/jmorganca/ollama/blob/main/docs/linux.md)
@@ -31,9 +28,14 @@ curl https://ollama.ai/install.sh | sh
 
 The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama` is available on Docker Hub.
 
+### Libraries
+
+- [ollama-python](https://github.com/ollama/ollama-python)
+- [ollama-js](https://github.com/ollama/ollama-js)
+
 ## Quickstart
 
-To run and chat with [Llama 2](https://ollama.ai/library/llama2):
+To run and chat with [Llama 2](https://ollama.com/library/llama2):
 
 ```
 ollama run llama2
@@ -41,26 +43,31 @@ ollama run llama2
 
 ## Model library
 
-Ollama supports a list of open-source models available on [ollama.ai/library](https://ollama.ai/library 'ollama model library')
+Ollama supports a list of models available on [ollama.com/library](https://ollama.com/library 'ollama model library')
 
-Here are some example open-source models that can be downloaded:
+Here are some example models that can be downloaded:
 
 | Model              | Parameters | Size  | Download                       |
 | ------------------ | ---------- | ----- | ------------------------------ |
+| Llama 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`       |
-| Mistral            | 7B         | 4.1GB | `ollama run mistral`           |
-| Llama 2            | 7B         | 3.8GB | `ollama run llama2`            |
 | Code Llama         | 7B         | 3.8GB | `ollama run codellama`         |
 | Llama 2 Uncensored | 7B         | 3.8GB | `ollama run llama2-uncensored` |
 | Llama 2 13B        | 13B        | 7.3GB | `ollama run llama2:13b`        |
 | Llama 2 70B        | 70B        | 39GB  | `ollama run llama2:70b`        |
 | Orca Mini          | 3B         | 1.9GB | `ollama run orca-mini`         |
 | Vicuna             | 7B         | 3.8GB | `ollama run vicuna`            |
+| LLaVA              | 7B         | 4.5GB | `ollama run llava`             |
+| Gemma              | 2B         | 1.4GB | `ollama run gemma:2b`          |
+| Gemma              | 7B         | 4.8GB | `ollama run gemma:7b`          |
 
-> Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.
+> Note: You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.
 
-## Customize your own model
+## Customize a model
 
 ### Import from GGUF
 
@@ -104,7 +111,7 @@ FROM llama2
 # set the temperature to 1 [higher is more creative, lower is more coherent]
 PARAMETER temperature 1
 
-# set the system prompt
+# set the system message
 SYSTEM """
 You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
 """
@@ -127,6 +134,10 @@ For more examples, see the [examples](examples) directory. For more information
 
 `ollama create` is used to create a model from a Modelfile.
 
+```
+ollama create mymodel -f ./Modelfile
+```
+
 ### Pull a model
 
 ```
@@ -158,6 +169,13 @@ For multiline input, you can wrap text with `"""`:
 I'm a basic program that prints the famous "Hello, world!" message to the console.
 ```
 
+### Multimodal models
+
+```
+>>> What's in this image? /Users/jmorgan/Desktop/smile.png
+The image features a yellow smiley face, which is likely the central focus of the picture.
+```
+
 ### Pass in prompt as arguments
 
 ```
@@ -183,13 +201,22 @@ Install `cmake` and `go`:
 brew install cmake go
 ```
 
-Then generate dependencies and build:
+Then generate dependencies:
 
 ```
 go generate ./...
+```
+
+Then build the binary:
+
+```
 go build .
 ```
 
+More detailed instructions can be found in the [developer guide](https://github.com/jmorganca/ollama/blob/main/docs/development.md)
+
+### Running local builds
+
 Next, start the server:
 
 ```
@@ -205,7 +232,8 @@ Finally, in a separate shell, run a model:
 ## REST API
 
 Ollama has a REST API for running and managing models.
-For example, to generate text from a model:
+
+### Generate a response
 
 ```
 curl http://localhost:11434/api/generate -d '{
@@ -214,26 +242,44 @@ curl http://localhost:11434/api/generate -d '{
 }'
 ```
 
+### Chat with a model
+
+```
+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.
 
 ## Community Integrations
 
-### Mobile
-
-- [Mobile Artificial Intelligence Distribution](https://github.com/MaidFoundation/Maid) (Maid)
-
 ### Web & Desktop
 
+- [Bionic GPT](https://github.com/bionic-gpt/bionic-gpt)
+- [Enchanted (macOS native)](https://github.com/AugustDev/enchanted)
 - [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)
+- [Open WebUI](https://github.com/open-webui/open-webui)
 - [Ollamac](https://github.com/kevinhermawan/Ollamac)
-- [big-AGI](https://github.com/enricoros/big-agi/blob/main/docs/config-ollama.md)
+- [big-AGI](https://github.com/enricoros/big-AGI/blob/main/docs/config-local-ollama.md)
 - [Cheshire Cat assistant framework](https://github.com/cheshire-cat-ai/core)
 - [Amica](https://github.com/semperai/amica)
 - [chatd](https://github.com/BruceMacD/chatd)
+- [Ollama-SwiftUI](https://github.com/kghandour/Ollama-SwiftUI)
+- [MindMac](https://mindmac.app)
+- [NextJS Web Interface for Ollama](https://github.com/jakobhoeg/nextjs-ollama-llm-ui)
+- [Msty](https://msty.app)
+- [Chatbox](https://github.com/Bin-Huang/Chatbox)
+- [WinForm Ollama Copilot](https://github.com/tgraupmann/WinForm_Ollama_Copilot)
+- [NextChat](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web) with [Get Started Doc](https://docs.nextchat.dev/models/ollama)
+- [Odin Runes](https://github.com/leonid20000/OdinRunes)
+- [LLM-X: Progressive Web App](https://github.com/mrdjohnson/llm-x)
 
 ### Terminal
 
@@ -242,31 +288,52 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [Emacs client](https://github.com/zweifisch/ollama)
 - [gen.nvim](https://github.com/David-Kunz/gen.nvim)
 - [ollama.nvim](https://github.com/nomnivore/ollama.nvim)
+- [ollama-chat.nvim](https://github.com/gerazov/ollama-chat.nvim)
 - [ogpt.nvim](https://github.com/huynle/ogpt.nvim)
 - [gptel Emacs client](https://github.com/karthink/gptel)
 - [Oatmeal](https://github.com/dustinblackman/oatmeal)
+- [cmdh](https://github.com/pgibler/cmdh)
+- [tenere](https://github.com/pythops/tenere)
+- [llm-ollama](https://github.com/taketwo/llm-ollama) for [Datasette's LLM CLI](https://llm.datasette.io/en/stable/).
+- [ShellOracle](https://github.com/djcopley/ShellOracle)
+
+### 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/)
+- [Helm Chart](https://artifacthub.io/packages/helm/ollama-helm/ollama)
 
 ### Libraries
 
 - [LangChain](https://python.langchain.com/docs/integrations/llms/ollama) and [LangChain.js](https://js.langchain.com/docs/modules/model_io/models/llms/integrations/ollama) with [example](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa)
 - [LangChainGo](https://github.com/tmc/langchaingo/) with [example](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example)
+- [LangChain4j](https://github.com/langchain4j/langchain4j) with [example](https://github.com/langchain4j/langchain4j-examples/tree/main/ollama-examples/src/main/java)
 - [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/llm/ollama.html)
+- [LangChain4j](https://github.com/langchain4j/langchain4j/tree/main/langchain4j-ollama)
 - [LiteLLM](https://github.com/BerriAI/litellm)
 - [OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp)
+- [Ollama for Ruby](https://github.com/gbaptista/ollama-ai)
 - [Ollama-rs for Rust](https://github.com/pepperoni21/ollama-rs)
 - [Ollama4j for Java](https://github.com/amithkoujalgi/ollama4j)
 - [ModelFusion Typescript Library](https://modelfusion.dev/integration/model-provider/ollama)
 - [OllamaKit for Swift](https://github.com/kevinhermawan/OllamaKit)
 - [Ollama for Dart](https://github.com/breitburg/dart-ollama)
 - [Ollama for Laravel](https://github.com/cloudstudio/ollama-laravel)
+- [LangChainDart](https://github.com/davidmigloz/langchain_dart)
+- [Semantic Kernel - Python](https://github.com/microsoft/semantic-kernel/tree/main/python/semantic_kernel/connectors/ai/ollama)
+- [Haystack](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/ollama.md)
+- [Elixir LangChain](https://github.com/brainlid/langchain)
+- [Ollama for R - rollama](https://github.com/JBGruber/rollama)
+- [Ollama-ex for Elixir](https://github.com/lebrunel/ollama-ex)
+- [Ollama Connector for SAP ABAP](https://github.com/b-tocs/abap_btocs_ollama)
 
 ### Mobile
 
-- [Maid](https://github.com/danemadsen/Maid) (Mobile Artificial Intelligence Distribution)
+- [Enchanted](https://github.com/AugustDev/enchanted)
+- [Maid](https://github.com/Mobile-Artificial-Intelligence/maid)
 
 ### Extensions & Plugins
 
@@ -275,9 +342,17 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [Continue](https://github.com/continuedev/continue)
 - [Obsidian Ollama plugin](https://github.com/hinterdupfinger/obsidian-ollama)
 - [Logseq Ollama plugin](https://github.com/omagdy7/ollama-logseq)
+- [NotesOllama](https://github.com/andersrex/notesollama) (Apple Notes Ollama plugin)
 - [Dagger Chatbot](https://github.com/samalba/dagger-chatbot)
 - [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)
+- [Copilot for Obsidian plugin](https://github.com/logancyang/obsidian-copilot)
+- [Obsidian Local GPT plugin](https://github.com/pfrankov/obsidian-local-gpt)
+- [Open Interpreter](https://docs.openinterpreter.com/language-model-setup/local-models/ollama)
+- [twinny](https://github.com/rjmacarthy/twinny) (Copilot and Copilot chat alternative using Ollama)
+- [Wingman-AI](https://github.com/RussellCanfield/wingman-ai) (Copilot code and chat alternative using Ollama and HuggingFace)
+- [Page Assist](https://github.com/n4ze3m/page-assist) (Chrome Extension)

api/client.go

@@ -21,7 +21,7 @@ import (
 
 type Client struct {
 	base *url.URL
-	http http.Client
+	http *http.Client
 }
 
 func checkError(resp *http.Response, body []byte) error {
@@ -66,30 +66,13 @@ func ClientFromEnvironment() (*Client, error) {
 		}
 	}
 
-	client := Client{
+	return &Client{
 		base: &url.URL{
 			Scheme: scheme,
 			Host:   net.JoinHostPort(host, port),
 		},
-	}
-
-	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
+		http: http.DefaultClient,
+	}, nil
 }
 
 func (c *Client) do(ctx context.Context, method, path string, reqData, respData any) error {
@@ -221,6 +204,19 @@ 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 {
@@ -296,6 +292,13 @@ 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 {
@@ -311,3 +314,15 @@ func (c *Client) CreateBlob(ctx context.Context, digest string, r io.Reader) 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.py

@@ -1,284 +0,0 @@
-import os
-import json
-import requests
-import os
-import hashlib
-import json
-from pathlib import Path
-
-BASE_URL = os.environ.get('OLLAMA_HOST', 'http://localhost:11434')
-
-# Generate a response for a given prompt with a provided model. This is a streaming endpoint, so will be a series of responses.
-# The final response object will include statistics and additional data from the request. Use the callback function to override
-# the default handler.
-def generate(model_name, prompt, system=None, template=None, format="", context=None, options=None, callback=None):
-    try:
-        url = f"{BASE_URL}/api/generate"
-        payload = {
-            "model": model_name, 
-            "prompt": prompt, 
-            "system": system, 
-            "template": template, 
-            "context": context, 
-            "options": options,
-            "format": format,
-        }
-        
-        # Remove keys with None values
-        payload = {k: v for k, v in payload.items() if v is not None}
-        
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-            
-            # Creating a variable to hold the context history of the final chunk
-            final_context = None
-            
-            # Variable to hold concatenated response strings if no callback is provided
-            full_response = ""
-
-            # Iterating over the response line by line and displaying the details
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the details
-                    chunk = json.loads(line)
-                    
-                    # If a callback function is provided, call it with the chunk
-                    if callback:
-                        callback(chunk)
-                    else:
-                        # If this is not the last chunk, add the "response" field value to full_response and print it
-                        if not chunk.get("done"):
-                            response_piece = chunk.get("response", "")
-                            full_response += response_piece
-                            print(response_piece, end="", flush=True)
-                    
-                    # Check if it's the last chunk (done is true)
-                    if chunk.get("done"):
-                        final_context = chunk.get("context")
-            
-            # Return the full response and the final context
-            return full_response, final_context
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None, None
-    
-
-# Create a blob file on the server if it doesn't exist.
-def create_blob(digest, file_path):
-    url = f"{BASE_URL}/api/blobs/{digest}"
-
-    # Check if the blob exists
-    response = requests.head(url)
-    if response.status_code != 404:
-        return  # Blob already exists, no need to upload
-    response.raise_for_status()
-
-    # Upload the blob
-    with open(file_path, 'rb') as file_data:
-        requests.post(url, data=file_data)
-
-
-# Create a model from a Modelfile. Use the callback function to override the default handler.
-def create(model_name, filename, callback=None):
-    try:
-        file_path = Path(filename).expanduser().resolve()
-        processed_lines = []
-
-        # Read and process the modelfile
-        with open(file_path, 'r') as f:
-            for line in f:            
-                # Skip empty or whitespace-only lines
-                if not line.strip():
-                    continue
-            
-                command, args = line.split(maxsplit=1)
-
-                if command.upper() in ["FROM", "ADAPTER"]:
-                    path = Path(args.strip()).expanduser()
-
-                    # Check if path is relative and resolve it
-                    if not path.is_absolute():
-                        path = (file_path.parent / path)
-
-                    # Skip if file does not exist for "model", this is handled by the server
-                    if not path.exists():
-                        processed_lines.append(line)
-                        continue
-
-                    # Calculate SHA-256 hash
-                    with open(path, 'rb') as bin_file:
-                        hash = hashlib.sha256()
-                        hash.update(bin_file.read())
-                        blob = f"sha256:{hash.hexdigest()}"
-                
-                    # Add the file to the remote server
-                    create_blob(blob, path)
-
-                    # Replace path with digest in the line
-                    line = f"{command} @{blob}\n"
-
-                processed_lines.append(line)
-
-        # Combine processed lines back into a single string
-        modelfile_content = '\n'.join(processed_lines)
-
-        url = f"{BASE_URL}/api/create"
-        payload = {"name": model_name, "modelfile": modelfile_content}
-
-        # Making a POST request with the stream parameter set to True to handle streaming responses
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-            # Iterating over the response line by line and displaying the status
-            for line in response.iter_lines():
-                if line:
-                    chunk = json.loads(line)
-                    if callback:
-                        callback(chunk)
-                    else:
-                        print(f"Status: {chunk.get('status')}")
-
-    except Exception as e:
-        print(f"An error occurred: {e}")
-
-
-# Pull a model from a the model registry. Cancelled pulls are resumed from where they left off, and multiple
-# calls to will share the same download progress. Use the callback function to override the default handler.
-def pull(model_name, insecure=False, callback=None):
-    try:
-        url = f"{BASE_URL}/api/pull"
-        payload = {
-            "name": model_name,
-            "insecure": insecure
-        }
-
-        # Making a POST request with the stream parameter set to True to handle streaming responses
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-
-            # Iterating over the response line by line and displaying the details
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the details
-                    chunk = json.loads(line)
-
-                    # If a callback function is provided, call it with the chunk
-                    if callback:
-                        callback(chunk)
-                    else:
-                        # Print the status message directly to the console
-                        print(chunk.get('status', ''), end='', flush=True)
-                    
-                    # If there's layer data, you might also want to print that (adjust as necessary)
-                    if 'digest' in chunk:
-                        print(f" - Digest: {chunk['digest']}", end='', flush=True)
-                        print(f" - Total: {chunk['total']}", end='', flush=True)
-                        print(f" - Completed: {chunk['completed']}", end='\n', flush=True)
-                    else:
-                        print()
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-
-# Push a model to the model registry. Use the callback function to override the default handler.
-def push(model_name, insecure=False, callback=None):
-    try:
-        url = f"{BASE_URL}/api/push"
-        payload = {
-            "name": model_name,
-            "insecure": insecure
-        }
-
-        # Making a POST request with the stream parameter set to True to handle streaming responses
-        with requests.post(url, json=payload, stream=True) as response:
-            response.raise_for_status()
-
-            # Iterating over the response line by line and displaying the details
-            for line in response.iter_lines():
-                if line:
-                    # Parsing each line (JSON chunk) and extracting the details
-                    chunk = json.loads(line)
-
-                    # If a callback function is provided, call it with the chunk
-                    if callback:
-                        callback(chunk)
-                    else:
-                        # Print the status message directly to the console
-                        print(chunk.get('status', ''), end='', flush=True)
-                    
-                    # If there's layer data, you might also want to print that (adjust as necessary)
-                    if 'digest' in chunk:
-                        print(f" - Digest: {chunk['digest']}", end='', flush=True)
-                        print(f" - Total: {chunk['total']}", end='', flush=True)
-                        print(f" - Completed: {chunk['completed']}", end='\n', flush=True)
-                    else:
-                        print()
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-
-# List models that are available locally.
-def list():
-    try:
-        response = requests.get(f"{BASE_URL}/api/tags")
-        response.raise_for_status()
-        data = response.json()
-        models = data.get('models', [])
-        return models
-
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-# Copy a model. Creates a model with another name from an existing model.
-def copy(source, destination):
-    try:
-        # Create the JSON payload
-        payload = {
-            "source": source,
-            "destination": destination
-        }
-        
-        response = requests.post(f"{BASE_URL}/api/copy", json=payload)
-        response.raise_for_status()
-        
-        # If the request was successful, return a message indicating that the copy was successful
-        return "Copy successful"
-
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-# Delete a model and its data.
-def delete(model_name):
-    try:
-        url = f"{BASE_URL}/api/delete"
-        payload = {"name": model_name}
-        response = requests.delete(url, json=payload)
-        response.raise_for_status()
-        return "Delete successful"
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-# Show info about a model.
-def show(model_name):
-    try:
-        url = f"{BASE_URL}/api/show"
-        payload = {"name": model_name}
-        response = requests.post(url, json=payload)
-        response.raise_for_status()
-        
-        # Parse the JSON response and return it
-        data = response.json()
-        return data
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return None
-
-def heartbeat():
-    try:
-        url = f"{BASE_URL}/"
-        response = requests.head(url)
-        response.raise_for_status()
-        return "Ollama is running"
-    except requests.exceptions.RequestException as e:
-        print(f"An error occurred: {e}")
-        return "Ollama is not running"

api/types.go

@@ -31,20 +31,59 @@ 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"`
+	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"`
+	KeepAlive *Duration   `json:"keep_alive,omitempty"`
+	Images    []ImageData `json:"images,omitempty"`
 
 	Options map[string]interface{} `json:"options"`
 }
 
-// Options specfied in GenerateRequest, if you add a new option here add it to the API docs also
+type ChatRequest struct {
+	Model     string    `json:"model"`
+	Messages  []Message `json:"messages"`
+	Stream    *bool     `json:"stream,omitempty"`
+	Format    string    `json:"format"`
+	KeepAlive *Duration `json:"keep_alive,omitempty"`
+
+	Options map[string]interface{} `json:"options"`
+}
+
+type Message struct {
+	Role    string      `json:"role"` // one of ["system", "user", "assistant"]
+	Content string      `json:"content"`
+	Images  []ImageData `json:"images,omitempty"`
+}
+
+type ChatResponse struct {
+	Model     string    `json:"model"`
+	CreatedAt time.Time `json:"created_at"`
+	Message   Message   `json:"message"`
+
+	Done bool `json:"done"`
+
+	Metrics
+}
+
+type Metrics struct {
+	TotalDuration      time.Duration `json:"total_duration,omitempty"`
+	LoadDuration       time.Duration `json:"load_duration,omitempty"`
+	PromptEvalCount    int           `json:"prompt_eval_count,omitempty"`
+	PromptEvalDuration time.Duration `json:"prompt_eval_duration,omitempty"`
+	EvalCount          int           `json:"eval_count,omitempty"`
+	EvalDuration       time.Duration `json:"eval_duration,omitempty"`
+}
+
+// Options specified in GenerateRequest, if you add a new option here add it to the API docs also
 type Options struct {
 	Runner
 
@@ -82,15 +121,15 @@ type Runner struct {
 	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"`
+	Model     string    `json:"model"`
+	Prompt    string    `json:"prompt"`
+	KeepAlive *Duration `json:"keep_alive,omitempty"`
 
 	Options map[string]interface{} `json:"options"`
 }
@@ -100,26 +139,41 @@ type EmbeddingResponse struct {
 }
 
 type CreateRequest struct {
-	Name      string `json:"name"`
+	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"`
+	License    string       `json:"license,omitempty"`
+	Modelfile  string       `json:"modelfile,omitempty"`
+	Parameters string       `json:"parameters,omitempty"`
+	Template   string       `json:"template,omitempty"`
+	System     string       `json:"system,omitempty"`
+	Details    ModelDetails `json:"details,omitempty"`
+	Messages   []Message    `json:"messages,omitempty"`
 }
 
 type CopyRequest struct {
@@ -128,11 +182,14 @@ type CopyRequest struct {
 }
 
 type PullRequest struct {
-	Name     string `json:"name"`
+	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 {
@@ -143,11 +200,14 @@ type ProgressResponse struct {
 }
 
 type PushRequest struct {
-	Name     string `json:"name"`
+	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 {
@@ -155,10 +215,12 @@ type ListResponse struct {
 }
 
 type ModelResponse struct {
-	Name       string    `json:"name"`
-	ModifiedAt time.Time `json:"modified_at"`
-	Size       int64     `json:"size"`
-	Digest     string    `json:"digest"`
+	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 {
@@ -173,39 +235,43 @@ type GenerateResponse struct {
 	Done    bool  `json:"done"`
 	Context []int `json:"context,omitempty"`
 
-	TotalDuration      time.Duration `json:"total_duration,omitempty"`
-	LoadDuration       time.Duration `json:"load_duration,omitempty"`
-	PromptEvalCount    int           `json:"prompt_eval_count,omitempty"`
-	PromptEvalDuration time.Duration `json:"prompt_eval_duration,omitempty"`
-	EvalCount          int           `json:"eval_count,omitempty"`
-	EvalDuration       time.Duration `json:"eval_duration,omitempty"`
+	Metrics
 }
 
-func (r *GenerateResponse) Summary() {
-	if r.TotalDuration > 0 {
-		fmt.Fprintf(os.Stderr, "total duration:       %v\n", r.TotalDuration)
+type ModelDetails struct {
+	ParentModel       string   `json:"parent_model"`
+	Format            string   `json:"format"`
+	Family            string   `json:"family"`
+	Families          []string `json:"families"`
+	ParameterSize     string   `json:"parameter_size"`
+	QuantizationLevel string   `json:"quantization_level"`
+}
+
+func (m *Metrics) Summary() {
+	if m.TotalDuration > 0 {
+		fmt.Fprintf(os.Stderr, "total duration:       %v\n", m.TotalDuration)
 	}
 
-	if r.LoadDuration > 0 {
-		fmt.Fprintf(os.Stderr, "load duration:        %v\n", r.LoadDuration)
+	if m.LoadDuration > 0 {
+		fmt.Fprintf(os.Stderr, "load duration:        %v\n", m.LoadDuration)
 	}
 
-	if r.PromptEvalCount > 0 {
-		fmt.Fprintf(os.Stderr, "prompt eval count:    %d token(s)\n", r.PromptEvalCount)
+	if m.PromptEvalCount > 0 {
+		fmt.Fprintf(os.Stderr, "prompt eval count:    %d token(s)\n", m.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 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 r.EvalCount > 0 {
-		fmt.Fprintf(os.Stderr, "eval count:           %d token(s)\n", r.EvalCount)
+	if m.EvalCount > 0 {
+		fmt.Fprintf(os.Stderr, "eval count:           %d token(s)\n", m.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())
+	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())
 	}
 }
 
@@ -328,7 +394,6 @@ func DefaultOptions() Options {
 			UseMLock:           false,
 			UseMMap:            true,
 			UseNUMA:            false,
-			EmbeddingOnly:      true,
 		},
 	}
 }
@@ -348,15 +413,18 @@ func (d *Duration) UnmarshalJSON(b []byte) (err error) {
 	switch t := v.(type) {
 	case float64:
 		if t < 0 {
-			t = math.MaxFloat64
+			d.Duration = time.Duration(math.MaxInt64)
+		} else {
+			d.Duration = time.Duration(t * float64(time.Second))
 		}
-
-		d.Duration = time.Duration(t)
 	case string:
 		d.Duration, err = time.ParseDuration(t)
 		if err != nil {
 			return err
 		}
+		if d.Duration < 0 {
+			d.Duration = time.Duration(math.MaxInt64)
+		}
 	}
 
 	return nil

api/types_test.go

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

app/.gitignore

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

app/README.md

@@ -1,21 +1,22 @@
-# Desktop
+# Ollama App
 
-This app builds upon Ollama to provide a desktop experience for running models.
+## Linux
 
-## Developing
+TODO
 
-First, build the `ollama` binary:
+## MacOS
+
+TODO
+
+## Windows
+
+If you want to build the installer, youll need to install
+- https://jrsoftware.org/isinfo.php
+
+
+In the top directory of this repo, run the following powershell script
+to build the ollama CLI, ollama app, and ollama installer.
 
 ```
-cd ..
-go build .
+powershell -ExecutionPolicy Bypass -File .\scripts\build_windows.ps1
 ```
-
-Then run the desktop app with `npm start`:
-
-```
-cd app
-npm install
-npm start
-```
-

app/assets/assets.go

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

app/lifecycle/getstarted_nonwindows.go

@@ -0,0 +1,9 @@
+//go:build !windows
+
+package lifecycle
+
+import "fmt"
+
+func GetStarted() error {
+	return fmt.Errorf("GetStarted not implemented")
+}

app/lifecycle/getstarted_windows.go

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

app/lifecycle/lifecycle.go

@@ -0,0 +1,92 @@
+package lifecycle
+
+import (
+	"context"
+	"fmt"
+	"log"
+	"log/slog"
+	"os"
+	"os/signal"
+	"syscall"
+
+	"github.com/jmorganca/ollama/app/store"
+	"github.com/jmorganca/ollama/app/tray"
+)
+
+func Run() {
+	InitLogging()
+
+	ctx, cancel := context.WithCancel(context.Background())
+	var done chan int
+
+	t, err := tray.NewTray()
+	if err != nil {
+		log.Fatalf("Failed to start: %s", err)
+	}
+	callbacks := t.GetCallbacks()
+
+	signals := make(chan os.Signal, 1)
+	signal.Notify(signals, syscall.SIGINT, syscall.SIGTERM)
+
+	go func() {
+		slog.Debug("starting callback loop")
+		for {
+			select {
+			case <-callbacks.Quit:
+				slog.Debug("quit called")
+				t.Quit()
+			case <-signals:
+				slog.Debug("shutting down due to signal")
+				t.Quit()
+			case <-callbacks.Update:
+				err := DoUpgrade(cancel, done)
+				if err != nil {
+					slog.Warn(fmt.Sprintf("upgrade attempt failed: %s", err))
+				}
+			case <-callbacks.ShowLogs:
+				ShowLogs()
+			case <-callbacks.DoFirstUse:
+				err := GetStarted()
+				if err != nil {
+					slog.Warn(fmt.Sprintf("Failed to launch getting started shell: %s", err))
+				}
+			}
+		}
+	}()
+
+	// Are we first use?
+	if !store.GetFirstTimeRun() {
+		slog.Debug("First time run")
+		err = t.DisplayFirstUseNotification()
+		if err != nil {
+			slog.Debug(fmt.Sprintf("XXX failed to display first use notification %v", err))
+		}
+		store.SetFirstTimeRun(true)
+	} else {
+		slog.Debug("Not first time, skipping first run notification")
+	}
+
+	if IsServerRunning(ctx) {
+		slog.Info("Detected another instance of ollama running, exiting")
+		os.Exit(1)
+	} else {
+		done, err = SpawnServer(ctx, CLIName)
+		if err != nil {
+			// TODO - should we retry in a backoff loop?
+			// TODO - should we pop up a warning and maybe add a menu item to view application logs?
+			slog.Error(fmt.Sprintf("Failed to spawn ollama server %s", err))
+			done = make(chan int, 1)
+			done <- 1
+		}
+	}
+
+	StartBackgroundUpdaterChecker(ctx, t.UpdateAvailable)
+
+	t.Run()
+	cancel()
+	slog.Info("Waiting for ollama server to shutdown...")
+	if done != nil {
+		<-done
+	}
+	slog.Info("Ollama app exiting")
+}

app/lifecycle/logging.go

@@ -0,0 +1,46 @@
+package lifecycle
+
+import (
+	"fmt"
+	"log/slog"
+	"os"
+	"path/filepath"
+)
+
+func InitLogging() {
+	level := slog.LevelInfo
+
+	if debug := os.Getenv("OLLAMA_DEBUG"); debug != "" {
+		level = slog.LevelDebug
+	}
+
+	var logFile *os.File
+	var err error
+	// Detect if we're a GUI app on windows, and if not, send logs to console
+	if os.Stderr.Fd() != 0 {
+		// Console app detected
+		logFile = os.Stderr
+		// TODO - write one-line to the app.log file saying we're running in console mode to help avoid confusion
+	} else {
+		logFile, err = os.OpenFile(AppLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0755)
+		if err != nil {
+			slog.Error(fmt.Sprintf("failed to create server log %v", err))
+			return
+		}
+	}
+	handler := slog.NewTextHandler(logFile, &slog.HandlerOptions{
+		Level:     level,
+		AddSource: true,
+		ReplaceAttr: func(_ []string, attr slog.Attr) slog.Attr {
+			if attr.Key == slog.SourceKey {
+				source := attr.Value.Any().(*slog.Source)
+				source.File = filepath.Base(source.File)
+			}
+			return attr
+		},
+	})
+
+	slog.SetDefault(slog.New(handler))
+
+	slog.Info("ollama app started")
+}

app/lifecycle/logging_nonwindows.go

@@ -0,0 +1,9 @@
+//go:build !windows
+
+package lifecycle
+
+import "log/slog"
+
+func ShowLogs() {
+	slog.Warn("ShowLogs not yet implemented")
+}

app/lifecycle/logging_windows.go

@@ -0,0 +1,19 @@
+package lifecycle
+
+import (
+	"fmt"
+	"log/slog"
+	"os/exec"
+	"syscall"
+)
+
+func ShowLogs() {
+	cmd_path := "c:\\Windows\\system32\\cmd.exe"
+	slog.Debug(fmt.Sprintf("viewing logs with start %s", AppDataDir))
+	cmd := exec.Command(cmd_path, "/c", "start", AppDataDir)
+	cmd.SysProcAttr = &syscall.SysProcAttr{HideWindow: false, CreationFlags: 0x08000000}
+	err := cmd.Start()
+	if err != nil {
+		slog.Error(fmt.Sprintf("Failed to open log dir: %s", err))
+	}
+}

app/lifecycle/paths.go

@@ -0,0 +1,79 @@
+package lifecycle
+
+import (
+	"errors"
+	"fmt"
+	"log/slog"
+	"os"
+	"path/filepath"
+	"runtime"
+	"strings"
+)
+
+var (
+	AppName    = "ollama app"
+	CLIName    = "ollama"
+	AppDir     = "/opt/Ollama"
+	AppDataDir = "/opt/Ollama"
+	// TODO - should there be a distinct log dir?
+	UpdateStageDir = "/tmp"
+	AppLogFile     = "/tmp/ollama_app.log"
+	ServerLogFile  = "/tmp/ollama.log"
+	UpgradeLogFile = "/tmp/ollama_update.log"
+	Installer      = "OllamaSetup.exe"
+)
+
+func init() {
+	if runtime.GOOS == "windows" {
+		AppName += ".exe"
+		CLIName += ".exe"
+		// Logs, configs, downloads go to LOCALAPPDATA
+		localAppData := os.Getenv("LOCALAPPDATA")
+		AppDataDir = filepath.Join(localAppData, "Ollama")
+		UpdateStageDir = filepath.Join(AppDataDir, "updates")
+		AppLogFile = filepath.Join(AppDataDir, "app.log")
+		ServerLogFile = filepath.Join(AppDataDir, "server.log")
+		UpgradeLogFile = filepath.Join(AppDataDir, "upgrade.log")
+
+		// Executables are stored in APPDATA
+		AppDir = filepath.Join(localAppData, "Programs", "Ollama")
+
+		// Make sure we have PATH set correctly for any spawned children
+		paths := strings.Split(os.Getenv("PATH"), ";")
+		// Start with whatever we find in the PATH/LD_LIBRARY_PATH
+		found := false
+		for _, path := range paths {
+			d, err := filepath.Abs(path)
+			if err != nil {
+				continue
+			}
+			if strings.EqualFold(AppDir, d) {
+				found = true
+			}
+		}
+		if !found {
+			paths = append(paths, AppDir)
+
+			pathVal := strings.Join(paths, ";")
+			slog.Debug("setting PATH=" + pathVal)
+			err := os.Setenv("PATH", pathVal)
+			if err != nil {
+				slog.Error(fmt.Sprintf("failed to update PATH: %s", err))
+			}
+		}
+
+		// Make sure our logging dir exists
+		_, err := os.Stat(AppDataDir)
+		if errors.Is(err, os.ErrNotExist) {
+			if err := os.MkdirAll(AppDataDir, 0o755); err != nil {
+				slog.Error(fmt.Sprintf("create ollama dir %s: %v", AppDataDir, err))
+			}
+		}
+
+	} else if runtime.GOOS == "darwin" {
+		// TODO
+		AppName += ".app"
+		// } else if runtime.GOOS == "linux" {
+		// TODO
+	}
+}

app/lifecycle/server.go

@@ -0,0 +1,139 @@
+package lifecycle
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"time"
+
+	"github.com/jmorganca/ollama/api"
+)
+
+func getCLIFullPath(command string) string {
+	cmdPath := ""
+	appExe, err := os.Executable()
+	if err == nil {
+		cmdPath = filepath.Join(filepath.Dir(appExe), command)
+		_, err := os.Stat(cmdPath)
+		if err == nil {
+			return cmdPath
+		}
+	}
+	cmdPath, err = exec.LookPath(command)
+	if err == nil {
+		_, err := os.Stat(cmdPath)
+		if err == nil {
+			return cmdPath
+		}
+	}
+	pwd, err := os.Getwd()
+	if err == nil {
+		cmdPath = filepath.Join(pwd, command)
+		_, err = os.Stat(cmdPath)
+		if err == nil {
+			return cmdPath
+		}
+	}
+
+	return command
+}
+
+func SpawnServer(ctx context.Context, command string) (chan int, error) {
+	done := make(chan int)
+
+	logDir := filepath.Dir(ServerLogFile)
+	_, err := os.Stat(logDir)
+	if errors.Is(err, os.ErrNotExist) {
+		if err := os.MkdirAll(logDir, 0o755); err != nil {
+			return done, fmt.Errorf("create ollama server log dir %s: %v", logDir, err)
+		}
+	}
+
+	cmd := getCmd(ctx, getCLIFullPath(command))
+	// send stdout and stderr to a file
+	stdout, err := cmd.StdoutPipe()
+	if err != nil {
+		return done, fmt.Errorf("failed to spawn server stdout pipe %s", err)
+	}
+	stderr, err := cmd.StderrPipe()
+	if err != nil {
+		return done, fmt.Errorf("failed to spawn server stderr pipe %s", err)
+	}
+	stdin, err := cmd.StdinPipe()
+	if err != nil {
+		return done, fmt.Errorf("failed to spawn server stdin pipe %s", err)
+	}
+
+	// TODO - rotation
+	logFile, err := os.OpenFile(ServerLogFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0755)
+	if err != nil {
+		return done, fmt.Errorf("failed to create server log %w", err)
+	}
+	go func() {
+		defer logFile.Close()
+		io.Copy(logFile, stdout) //nolint:errcheck
+	}()
+	go func() {
+		defer logFile.Close()
+		io.Copy(logFile, stderr) //nolint:errcheck
+	}()
+
+	// run the command and wait for it to finish
+	if err := cmd.Start(); err != nil {
+		return done, fmt.Errorf("failed to start server %w", err)
+	}
+	if cmd.Process != nil {
+		slog.Info(fmt.Sprintf("started ollama server with pid %d", cmd.Process.Pid))
+	}
+	slog.Info(fmt.Sprintf("ollama server logs %s", ServerLogFile))
+
+	go func() {
+		// Keep the server running unless we're shuttind down the app
+		crashCount := 0
+		for {
+			cmd.Wait() //nolint:errcheck
+			stdin.Close()
+			var code int
+			if cmd.ProcessState != nil {
+				code = cmd.ProcessState.ExitCode()
+			}
+
+			select {
+			case <-ctx.Done():
+				slog.Debug(fmt.Sprintf("server shutdown with exit code %d", code))
+				done <- code
+				return
+			default:
+				crashCount++
+				slog.Warn(fmt.Sprintf("server crash %d - exit code %d - respawning", crashCount, code))
+				time.Sleep(500 * time.Millisecond)
+				if err := cmd.Start(); err != nil {
+					slog.Error(fmt.Sprintf("failed to restart server %s", err))
+					// Keep trying, but back off if we keep failing
+					time.Sleep(time.Duration(crashCount) * time.Second)
+				}
+			}
+		}
+	}()
+	return done, nil
+}
+
+func IsServerRunning(ctx context.Context) bool {
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		slog.Info("unable to connect to server")
+		return false
+	}
+	err = client.Heartbeat(ctx)
+	if err != nil {
+		slog.Debug(fmt.Sprintf("heartbeat from server: %s", err))
+		slog.Info("unable to connect to server")
+		return false
+	}
+	return true
+}

app/lifecycle/server_unix.go

@@ -0,0 +1,12 @@
+//go:build !windows
+
+package lifecycle
+
+import (
+	"context"
+	"os/exec"
+)
+
+func getCmd(ctx context.Context, cmd string) *exec.Cmd {
+	return exec.CommandContext(ctx, cmd, "serve")
+}

app/lifecycle/server_windows.go

@@ -0,0 +1,13 @@
+package lifecycle
+
+import (
+	"context"
+	"os/exec"
+	"syscall"
+)
+
+func getCmd(ctx context.Context, exePath string) *exec.Cmd {
+	cmd := exec.CommandContext(ctx, exePath, "serve")
+	cmd.SysProcAttr = &syscall.SysProcAttr{HideWindow: true, CreationFlags: 0x08000000}
+	return cmd
+}

app/lifecycle/updater.go

@@ -0,0 +1,228 @@
+package lifecycle
+
+import (
+	"context"
+	"crypto/rand"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"mime"
+	"net/http"
+	"net/url"
+	"os"
+	"path"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"time"
+
+	"github.com/jmorganca/ollama/auth"
+	"github.com/jmorganca/ollama/version"
+)
+
+var (
+	UpdateCheckURLBase  = "https://ollama.com/api/update"
+	UpdateDownloaded    = false
+	UpdateCheckInterval = 60 * 60 * time.Second
+)
+
+// TODO - maybe move up to the API package?
+type UpdateResponse struct {
+	UpdateURL     string `json:"url"`
+	UpdateVersion string `json:"version"`
+}
+
+func IsNewReleaseAvailable(ctx context.Context) (bool, UpdateResponse) {
+	var updateResp UpdateResponse
+
+	requestURL, err := url.Parse(UpdateCheckURLBase)
+	if err != nil {
+		return false, updateResp
+	}
+
+	query := requestURL.Query()
+	query.Add("os", runtime.GOOS)
+	query.Add("arch", runtime.GOARCH)
+	query.Add("version", version.Version)
+	query.Add("ts", fmt.Sprintf("%d", time.Now().Unix()))
+
+	nonce, err := auth.NewNonce(rand.Reader, 16)
+	if err != nil {
+		return false, updateResp
+	}
+
+	query.Add("nonce", nonce)
+	requestURL.RawQuery = query.Encode()
+
+	data := []byte(fmt.Sprintf("%s,%s", http.MethodGet, requestURL.RequestURI()))
+	signature, err := auth.Sign(ctx, data)
+	if err != nil {
+		return false, updateResp
+	}
+
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, requestURL.String(), nil)
+	if err != nil {
+		slog.Warn(fmt.Sprintf("failed to check for update: %s", err))
+		return false, updateResp
+	}
+	req.Header.Set("Authorization", signature)
+	req.Header.Set("User-Agent", fmt.Sprintf("ollama/%s (%s %s) Go/%s", version.Version, runtime.GOARCH, runtime.GOOS, runtime.Version()))
+
+	slog.Debug("checking for available update", "requestURL", requestURL)
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		slog.Warn(fmt.Sprintf("failed to check for update: %s", err))
+		return false, updateResp
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode == 204 {
+		slog.Debug("check update response 204 (current version is up to date)")
+		return false, updateResp
+	}
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		slog.Warn(fmt.Sprintf("failed to read body response: %s", err))
+	}
+
+	if resp.StatusCode != 200 {
+		slog.Info(fmt.Sprintf("check update error %d - %.96s", resp.StatusCode, string(body)))
+		return false, updateResp
+	}
+	err = json.Unmarshal(body, &updateResp)
+	if err != nil {
+		slog.Warn(fmt.Sprintf("malformed response checking for update: %s", err))
+		return false, updateResp
+	}
+	// Extract the version string from the URL in the github release artifact path
+	updateResp.UpdateVersion = path.Base(path.Dir(updateResp.UpdateURL))
+
+	slog.Info("New update available at " + updateResp.UpdateURL)
+	return true, updateResp
+}
+
+func DownloadNewRelease(ctx context.Context, updateResp UpdateResponse) error {
+	// Do a head first to check etag info
+	req, err := http.NewRequestWithContext(ctx, http.MethodHead, updateResp.UpdateURL, nil)
+	if err != nil {
+		return err
+	}
+
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return fmt.Errorf("error checking update: %w", err)
+	}
+	if resp.StatusCode != 200 {
+		return fmt.Errorf("unexpected status attempting to download update %d", resp.StatusCode)
+	}
+	resp.Body.Close()
+	etag := strings.Trim(resp.Header.Get("etag"), "\"")
+	if etag == "" {
+		slog.Debug("no etag detected, falling back to filename based dedup")
+		etag = "_"
+	}
+	filename := Installer
+	_, params, err := mime.ParseMediaType(resp.Header.Get("content-disposition"))
+	if err == nil {
+		filename = params["filename"]
+	}
+
+	stageFilename := filepath.Join(UpdateStageDir, etag, filename)
+
+	// Check to see if we already have it downloaded
+	_, err = os.Stat(stageFilename)
+	if err == nil {
+		slog.Info("update already downloaded")
+		return nil
+	}
+
+	cleanupOldDownloads()
+
+	req.Method = http.MethodGet
+	resp, err = http.DefaultClient.Do(req)
+	if err != nil {
+		return fmt.Errorf("error checking update: %w", err)
+	}
+	defer resp.Body.Close()
+	etag = strings.Trim(resp.Header.Get("etag"), "\"")
+	if etag == "" {
+		slog.Debug("no etag detected, falling back to filename based dedup") // TODO probably can get rid of this redundant log
+		etag = "_"
+	}
+
+	stageFilename = filepath.Join(UpdateStageDir, etag, filename)
+
+	_, err = os.Stat(filepath.Dir(stageFilename))
+	if errors.Is(err, os.ErrNotExist) {
+		if err := os.MkdirAll(filepath.Dir(stageFilename), 0o755); err != nil {
+			return fmt.Errorf("create ollama dir %s: %v", filepath.Dir(stageFilename), err)
+		}
+	}
+
+	payload, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return fmt.Errorf("failed to read body response: %w", err)
+	}
+	fp, err := os.OpenFile(stageFilename, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0o755)
+	if err != nil {
+		return fmt.Errorf("write payload %s: %w", stageFilename, err)
+	}
+	defer fp.Close()
+	if n, err := fp.Write(payload); err != nil || n != len(payload) {
+		return fmt.Errorf("write payload %s: %d vs %d -- %w", stageFilename, n, len(payload), err)
+	}
+	slog.Info("new update downloaded " + stageFilename)
+
+	UpdateDownloaded = true
+	return nil
+}
+
+func cleanupOldDownloads() {
+	files, err := os.ReadDir(UpdateStageDir)
+	if err != nil && errors.Is(err, os.ErrNotExist) {
+		// Expected behavior on first run
+		return
+	} else if err != nil {
+		slog.Warn(fmt.Sprintf("failed to list stage dir: %s", err))
+		return
+	}
+	for _, file := range files {
+		fullname := filepath.Join(UpdateStageDir, file.Name())
+		slog.Debug("cleaning up old download: " + fullname)
+		err = os.RemoveAll(fullname)
+		if err != nil {
+			slog.Warn(fmt.Sprintf("failed to cleanup stale update download %s", err))
+		}
+	}
+}
+
+func StartBackgroundUpdaterChecker(ctx context.Context, cb func(string) error) {
+	go func() {
+		// Don't blast an update message immediately after startup
+		// time.Sleep(30 * time.Second)
+		time.Sleep(3 * time.Second)
+
+		for {
+			available, resp := IsNewReleaseAvailable(ctx)
+			if available {
+				err := DownloadNewRelease(ctx, resp)
+				if err != nil {
+					slog.Error(fmt.Sprintf("failed to download new release: %s", err))
+				}
+				err = cb(resp.UpdateVersion)
+				if err != nil {
+					slog.Warn(fmt.Sprintf("failed to register update available with tray: %s", err))
+				}
+			}
+			select {
+			case <-ctx.Done():
+				slog.Debug("stopping background update checker")
+				return
+			default:
+				time.Sleep(UpdateCheckInterval)
+			}
+		}
+	}()
+}

app/lifecycle/updater_nonwindows.go

@@ -0,0 +1,12 @@
+//go:build !windows
+
+package lifecycle
+
+import (
+	"context"
+	"fmt"
+)
+
+func DoUpgrade(cancel context.CancelFunc, done chan int) error {
+	return fmt.Errorf("DoUpgrade not yet implemented")
+}

app/lifecycle/updater_windows.go

@@ -0,0 +1,80 @@
+package lifecycle
+
+import (
+	"context"
+	"fmt"
+	"log/slog"
+	"os"
+	"os/exec"
+	"path/filepath"
+)
+
+func DoUpgrade(cancel context.CancelFunc, done chan int) error {
+	files, err := filepath.Glob(filepath.Join(UpdateStageDir, "*", "*.exe")) // TODO generalize for multiplatform
+	if err != nil {
+		return fmt.Errorf("failed to lookup downloads: %s", err)
+	}
+	if len(files) == 0 {
+		return fmt.Errorf("no update downloads found")
+	} else if len(files) > 1 {
+		// Shouldn't happen
+		slog.Warn(fmt.Sprintf("multiple downloads found, using first one %v", files))
+	}
+	installerExe := files[0]
+
+	slog.Info("starting upgrade with " + installerExe)
+	slog.Info("upgrade log file " + UpgradeLogFile)
+
+	// When running in debug mode, we'll be "verbose" and let the installer pop up and prompt
+	installArgs := []string{
+		"/CLOSEAPPLICATIONS",                    // Quit the tray app if it's still running
+		"/LOG=" + filepath.Base(UpgradeLogFile), // Only relative seems reliable, so set pwd
+		"/FORCECLOSEAPPLICATIONS",               // Force close the tray app - might be needed
+	}
+	// When we're not in debug mode, make the upgrade as quiet as possible (no GUI, no prompts)
+	// TODO - temporarily disable since we're pinning in debug mode for the preview
+	// if debug := os.Getenv("OLLAMA_DEBUG"); debug == "" {
+	installArgs = append(installArgs,
+		"/SP", // Skip the "This will install... Do you wish to continue" prompt
+		"/SUPPRESSMSGBOXES",
+		"/SILENT",
+		"/VERYSILENT",
+	)
+	// }
+
+	// Safeguard in case we have requests in flight that need to drain...
+	slog.Info("Waiting for server to shutdown")
+	cancel()
+	if done != nil {
+		<-done
+	} else {
+		// Shouldn't happen
+		slog.Warn("done chan was nil, not actually waiting")
+	}
+
+	slog.Debug(fmt.Sprintf("starting installer: %s %v", installerExe, installArgs))
+	os.Chdir(filepath.Dir(UpgradeLogFile)) //nolint:errcheck
+	cmd := exec.Command(installerExe, installArgs...)
+
+	if err := cmd.Start(); err != nil {
+		return fmt.Errorf("unable to start ollama app %w", err)
+	}
+
+	if cmd.Process != nil {
+		err = cmd.Process.Release()
+		if err != nil {
+			slog.Error(fmt.Sprintf("failed to release server process: %s", err))
+		}
+	} else {
+		// TODO - some details about why it didn't start, or is this a pedantic error case?
+		return fmt.Errorf("installer process did not start")
+	}
+
+	// TODO should we linger for a moment and check to make sure it's actually running by checking the pid?
+
+	slog.Info("Installer started in background, exiting")
+
+	os.Exit(0)
+	// Not reached
+	return nil
+}

app/main.go

@@ -0,0 +1,12 @@
+package main
+
+// Compile with the following to get rid of the cmd pop up on windows
+// go build -ldflags="-H windowsgui" .
+
+import (
+	"github.com/jmorganca/ollama/app/lifecycle"
+)
+
+func main() {
+	lifecycle.Run()
+}

app/ollama.iss

@@ -0,0 +1,159 @@
+; Inno Setup Installer for Ollama
+;
+; To build the installer use the build script invoked from the top of the source tree
+; 
+; powershell -ExecutionPolicy Bypass -File .\scripts\build_windows.ps
+
+
+#define MyAppName "Ollama"
+#if GetEnv("PKG_VERSION") != ""
+  #define MyAppVersion GetEnv("PKG_VERSION")
+#else
+  #define MyAppVersion "0.0.0"
+#endif
+#define MyAppPublisher "Ollama"
+#define MyAppURL "https://ollama.com/"
+#define MyAppExeName "ollama app.exe"
+#define MyIcon ".\assets\app.ico"
+
+[Setup]
+; NOTE: The value of AppId uniquely identifies this application. Do not use the same AppId value in installers for other applications.
+; (To generate a new GUID, click Tools | Generate GUID inside the IDE.)
+AppId={{44E83376-CE68-45EB-8FC1-393500EB558C}
+AppName={#MyAppName}
+AppVersion={#MyAppVersion}
+VersionInfoVersion={#MyAppVersion}
+;AppVerName={#MyAppName} {#MyAppVersion}
+AppPublisher={#MyAppPublisher}
+AppPublisherURL={#MyAppURL}
+AppSupportURL={#MyAppURL}
+AppUpdatesURL={#MyAppURL}
+ArchitecturesAllowed=x64
+ArchitecturesInstallIn64BitMode=x64
+DefaultDirName={localappdata}\Programs\{#MyAppName}
+DefaultGroupName={#MyAppName}
+DisableProgramGroupPage=yes
+PrivilegesRequired=lowest
+OutputBaseFilename="OllamaSetup"
+SetupIconFile={#MyIcon}
+UninstallDisplayIcon={uninstallexe}
+Compression=lzma2
+SolidCompression=no
+WizardStyle=modern
+ChangesEnvironment=yes
+OutputDir=..\dist\
+
+; Disable logging once everything's battle tested
+; Filename will be %TEMP%\Setup Log*.txt
+SetupLogging=yes
+CloseApplications=yes
+RestartApplications=no
+
+; https://jrsoftware.org/ishelp/index.php?topic=setup_wizardimagefile
+WizardSmallImageFile=.\assets\setup.bmp
+
+; TODO verifty actual min windows version...
+; OG Win 10
+MinVersion=10.0.10240
+
+; First release that supports WinRT UI Composition for win32 apps
+; MinVersion=10.0.17134
+; First release with XAML Islands - possible UI path forward
+; MinVersion=10.0.18362
+
+; quiet...
+DisableDirPage=yes
+DisableFinishedPage=yes
+DisableReadyMemo=yes
+DisableReadyPage=yes
+DisableStartupPrompt=yes
+DisableWelcomePage=yes
+
+; TODO - percentage can't be set less than 100, so how to make it shorter?
+; WizardSizePercent=100,80
+
+#if GetEnv("KEY_CONTAINER")
+SignTool=MySignTool
+SignedUninstaller=yes
+#endif
+
+SetupMutex=OllamaSetupMutex
+
+[Languages]
+Name: "english"; MessagesFile: "compiler:Default.isl"
+
+[LangOptions]
+DialogFontSize=12
+
+[Files]
+Source: ".\app.exe"; DestDir: "{app}"; DestName: "{#MyAppExeName}" ; Flags: ignoreversion 64bit
+Source: "..\ollama.exe"; DestDir: "{app}"; Flags: ignoreversion 64bit
+Source: "..\dist\windeps\*.dll"; DestDir: "{app}"; Flags: ignoreversion 64bit
+Source: "..\dist\ollama_welcome.ps1"; DestDir: "{app}"; Flags: ignoreversion
+Source: ".\assets\app.ico"; DestDir: "{app}"; Flags: ignoreversion
+; Assumes v5.7, may need adjustments for v6
+#if GetEnv("HIP_PATH") != ""
+  Source: "{#GetEnv('HIP_PATH')}\bin\hipblas.dll"; DestDir: "{app}\rocm\"; Flags: ignoreversion
+  Source: "{#GetEnv('HIP_PATH')}\bin\rocblas.dll"; DestDir: "{app}\rocm\"; Flags: ignoreversion
+  ; amdhip64.dll dependency comes from the driver and must be installed already
+  Source: "{#GetEnv('HIP_PATH')}\bin\rocblas\library\*"; DestDir: "{app}\rocm\rocblas\library\"; Flags: ignoreversion
+#endif
+
+
+[Icons]
+Name: "{group}\{#MyAppName}"; Filename: "{app}\{#MyAppExeName}"; IconFilename: "{app}\app.ico"
+Name: "{userstartup}\{#MyAppName}"; Filename: "{app}\{#MyAppExeName}"; IconFilename: "{app}\app.ico"
+Name: "{userprograms}\{#MyAppName}"; Filename: "{app}\{#MyAppExeName}"; IconFilename: "{app}\app.ico"
+
+[Run]
+Filename: "{cmd}"; Parameters: "/C set PATH={app};%PATH% & ""{app}\{#MyAppExeName}"""; Flags: postinstall nowait runhidden
+
+[UninstallRun]
+; Filename: "{cmd}"; Parameters: "/C ""taskkill /im ''{#MyAppExeName}'' /f /t"; Flags: runhidden
+; Filename: "{cmd}"; Parameters: "/C ""taskkill /im ollama.exe /f /t"; Flags: runhidden
+Filename: "taskkill"; Parameters: "/im ""{#MyAppExeName}"" /f /t"; Flags: runhidden
+Filename: "taskkill"; Parameters: "/im ""ollama.exe"" /f /t"; Flags: runhidden
+; HACK!  need to give the server and app enough time to exit
+; TODO - convert this to a Pascal code script so it waits until they're no longer running, then completes
+Filename: "{cmd}"; Parameters: "/c timeout 5"; Flags: runhidden
+
+[UninstallDelete]
+Type: filesandordirs; Name: "{%TEMP}\ollama*"
+Type: filesandordirs; Name: "{%LOCALAPPDATA}\Ollama"
+Type: filesandordirs; Name: "{%LOCALAPPDATA}\Programs\Ollama"
+Type: filesandordirs; Name: "{%USERPROFILE}\.ollama\models"
+Type: filesandordirs; Name: "{%USERPROFILE}\.ollama\history"
+; NOTE: if the user has a custom OLLAMA_MODELS it will be preserved
+
+[Messages]
+WizardReady=Ollama Windows Preview
+ReadyLabel1=%nLet's get you up and running with your own large language models.
+SetupAppRunningError=Another Ollama installer is running.%n%nPlease cancel or finish the other installer, then click OK to continue with this install, or Cancel to exit.
+
+
+;FinishedHeadingLabel=Run your first model
+;FinishedLabel=%nRun this command in a PowerShell or cmd terminal.%n%n%n    ollama run llama2
+;ClickFinish=%n
+
+[Registry]
+Root: HKCU; Subkey: "Environment"; \
+    ValueType: expandsz; ValueName: "Path"; ValueData: "{olddata};{app}"; \
+    Check: NeedsAddPath('{app}')
+
+[Code]
+
+function NeedsAddPath(Param: string): boolean;
+var
+  OrigPath: string;
+begin
+  if not RegQueryStringValue(HKEY_CURRENT_USER,
+    'Environment',
+    'Path', OrigPath)
+  then begin
+    Result := True;
+    exit;
+  end;
+  { look for the path with leading and trailing semicolon }
+  { Pos() returns 0 if not found }
+  Result := Pos(';' + ExpandConstant(Param) + ';', ';' + OrigPath + ';') = 0;
+end;

app/ollama.rc

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

app/ollama_welcome.ps1

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

app/store/store.go

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

app/store/store_darwin.go

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

app/store/store_linux.go

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

app/store/store_windows.go

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

app/tray/commontray/types.go

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

app/tray/tray.go

@@ -0,0 +1,33 @@
+package tray
+
+import (
+	"fmt"
+	"runtime"
+
+	"github.com/jmorganca/ollama/app/assets"
+	"github.com/jmorganca/ollama/app/tray/commontray"
+)
+
+func NewTray() (commontray.OllamaTray, error) {
+	extension := ".png"
+	if runtime.GOOS == "windows" {
+		extension = ".ico"
+	}
+	iconName := commontray.UpdateIconName + extension
+	updateIcon, err := assets.GetIcon(iconName)
+	if err != nil {
+		return nil, fmt.Errorf("failed to load icon %s: %w", iconName, err)
+	}
+	iconName = commontray.IconName + extension
+	icon, err := assets.GetIcon(iconName)
+	if err != nil {
+		return nil, fmt.Errorf("failed to load icon %s: %w", iconName, err)
+	}
+
+	tray, err := InitPlatformTray(icon, updateIcon)
+	if err != nil {
+		return nil, err
+	}
+
+	return tray, nil
+}

app/tray/tray_nonwindows.go

@@ -0,0 +1,13 @@
+//go:build !windows
+
+package tray
+
+import (
+	"fmt"
+
+	"github.com/jmorganca/ollama/app/tray/commontray"
+)
+
+func InitPlatformTray(icon, updateIcon []byte) (commontray.OllamaTray, error) {
+	return nil, fmt.Errorf("NOT IMPLEMENTED YET")
+}

app/tray/tray_windows.go

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

app/tray/wintray/eventloop.go

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

app/tray/wintray/menus.go

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

app/tray/wintray/messages.go

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

app/tray/wintray/notifyicon.go

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

app/tray/wintray/tray.go

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

app/tray/wintray/w32api.go

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

app/tray/wintray/winclass.go

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

auth/auth.go

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

cmd/interactive.go

@@ -0,0 +1,663 @@
+package cmd
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+	"path/filepath"
+	"regexp"
+	"sort"
+	"strings"
+
+	"github.com/spf13/cobra"
+	"golang.org/x/exp/slices"
+
+	"github.com/jmorganca/ollama/api"
+	"github.com/jmorganca/ollama/progress"
+	"github.com/jmorganca/ollama/readline"
+)
+
+type MultilineState int
+
+const (
+	MultilineNone MultilineState = iota
+	MultilinePrompt
+	MultilineSystem
+	MultilineTemplate
+)
+
+func loadModel(cmd *cobra.Command, opts *runOptions) error {
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		return err
+	}
+
+	p := progress.NewProgress(os.Stderr)
+	defer p.StopAndClear()
+
+	spinner := progress.NewSpinner("")
+	p.Add("", spinner)
+
+	showReq := api.ShowRequest{Name: opts.Model}
+	showResp, err := client.Show(cmd.Context(), &showReq)
+	if err != nil {
+		return err
+	}
+	opts.MultiModal = slices.Contains(showResp.Details.Families, "clip")
+	opts.ParentModel = showResp.Details.ParentModel
+
+	if len(showResp.Messages) > 0 {
+		opts.Messages = append(opts.Messages, showResp.Messages...)
+	}
+
+	chatReq := &api.ChatRequest{
+		Model:    opts.Model,
+		Messages: []api.Message{},
+	}
+	err = client.Chat(cmd.Context(), chatReq, func(resp api.ChatResponse) error {
+		p.StopAndClear()
+		if len(opts.Messages) > 0 {
+			for _, msg := range opts.Messages {
+				switch msg.Role {
+				case "user":
+					fmt.Printf(">>> %s\n", msg.Content)
+				case "assistant":
+					state := &displayResponseState{}
+					displayResponse(msg.Content, opts.WordWrap, state)
+					fmt.Println()
+					fmt.Println()
+				}
+			}
+		}
+		return nil
+	})
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+func generateInteractive(cmd *cobra.Command, opts runOptions) error {
+	opts.Messages = make([]api.Message, 0)
+
+	err := loadModel(cmd, &opts)
+	if err != nil {
+		return err
+	}
+
+	usage := func() {
+		fmt.Fprintln(os.Stderr, "Available Commands:")
+		fmt.Fprintln(os.Stderr, "  /set            Set session variables")
+		fmt.Fprintln(os.Stderr, "  /show           Show model information")
+		fmt.Fprintln(os.Stderr, "  /load <model>   Load a session or model")
+		fmt.Fprintln(os.Stderr, "  /save <model>   Save your current session")
+		fmt.Fprintln(os.Stderr, "  /bye            Exit")
+		fmt.Fprintln(os.Stderr, "  /?, /help       Help for a command")
+		fmt.Fprintln(os.Stderr, "  /? shortcuts    Help for keyboard shortcuts")
+		fmt.Fprintln(os.Stderr, "")
+		fmt.Fprintln(os.Stderr, "Use \"\"\" to begin a multi-line message.")
+
+		if opts.MultiModal {
+			fmt.Fprintf(os.Stderr, "Use %s to include .jpg or .png images.\n", filepath.FromSlash("/path/to/file"))
+		}
+
+		fmt.Fprintln(os.Stderr, "")
+	}
+
+	usageSet := func() {
+		fmt.Fprintln(os.Stderr, "Available Commands:")
+		fmt.Fprintln(os.Stderr, "  /set parameter ...     Set a parameter")
+		fmt.Fprintln(os.Stderr, "  /set system <string>   Set system message")
+		fmt.Fprintln(os.Stderr, "  /set template <string> Set prompt template")
+		fmt.Fprintln(os.Stderr, "  /set history           Enable history")
+		fmt.Fprintln(os.Stderr, "  /set nohistory         Disable history")
+		fmt.Fprintln(os.Stderr, "  /set wordwrap          Enable wordwrap")
+		fmt.Fprintln(os.Stderr, "  /set nowordwrap        Disable wordwrap")
+		fmt.Fprintln(os.Stderr, "  /set format json       Enable JSON mode")
+		fmt.Fprintln(os.Stderr, "  /set noformat          Disable formatting")
+		fmt.Fprintln(os.Stderr, "  /set verbose           Show LLM stats")
+		fmt.Fprintln(os.Stderr, "  /set quiet             Disable LLM stats")
+		fmt.Fprintln(os.Stderr, "")
+	}
+
+	usageShortcuts := func() {
+		fmt.Fprintln(os.Stderr, "Available keyboard shortcuts:")
+		fmt.Fprintln(os.Stderr, "  Ctrl + a            Move to the beginning of the line (Home)")
+		fmt.Fprintln(os.Stderr, "  Ctrl + e            Move to the end of the line (End)")
+		fmt.Fprintln(os.Stderr, "   Alt + b            Move back (left) one word")
+		fmt.Fprintln(os.Stderr, "   Alt + f            Move forward (right) one word")
+		fmt.Fprintln(os.Stderr, "  Ctrl + k            Delete the sentence after the cursor")
+		fmt.Fprintln(os.Stderr, "  Ctrl + u            Delete the sentence before the cursor")
+		fmt.Fprintln(os.Stderr, "")
+		fmt.Fprintln(os.Stderr, "  Ctrl + l            Clear the screen")
+		fmt.Fprintln(os.Stderr, "  Ctrl + c            Stop the model from responding")
+		fmt.Fprintln(os.Stderr, "  Ctrl + d            Exit ollama (/bye)")
+		fmt.Fprintln(os.Stderr, "")
+	}
+
+	usageShow := func() {
+		fmt.Fprintln(os.Stderr, "Available Commands:")
+		fmt.Fprintln(os.Stderr, "  /show info         Show details for this model")
+		fmt.Fprintln(os.Stderr, "  /show license      Show model license")
+		fmt.Fprintln(os.Stderr, "  /show modelfile    Show Modelfile for this model")
+		fmt.Fprintln(os.Stderr, "  /show parameters   Show parameters for this model")
+		fmt.Fprintln(os.Stderr, "  /show system       Show system message")
+		fmt.Fprintln(os.Stderr, "  /show template     Show prompt template")
+		fmt.Fprintln(os.Stderr, "")
+	}
+
+	// only list out the most common parameters
+	usageParameters := func() {
+		fmt.Fprintln(os.Stderr, "Available Parameters:")
+		fmt.Fprintln(os.Stderr, "  /set parameter seed <int>             Random number seed")
+		fmt.Fprintln(os.Stderr, "  /set parameter num_predict <int>      Max number of tokens to predict")
+		fmt.Fprintln(os.Stderr, "  /set parameter top_k <int>            Pick from top k num of tokens")
+		fmt.Fprintln(os.Stderr, "  /set parameter top_p <float>          Pick token based on sum of probabilities")
+		fmt.Fprintln(os.Stderr, "  /set parameter num_ctx <int>          Set the context size")
+		fmt.Fprintln(os.Stderr, "  /set parameter temperature <float>    Set creativity level")
+		fmt.Fprintln(os.Stderr, "  /set parameter repeat_penalty <float> How strongly to penalize repetitions")
+		fmt.Fprintln(os.Stderr, "  /set parameter repeat_last_n <int>    Set how far back to look for repetitions")
+		fmt.Fprintln(os.Stderr, "  /set parameter num_gpu <int>          The number of layers to send to the GPU")
+		fmt.Fprintln(os.Stderr, "  /set parameter stop \"<string>\", ...   Set the stop parameters")
+		fmt.Fprintln(os.Stderr, "")
+	}
+
+	scanner, err := readline.New(readline.Prompt{
+		Prompt:         ">>> ",
+		AltPrompt:      "... ",
+		Placeholder:    "Send a message (/? for help)",
+		AltPlaceholder: `Use """ to end multi-line input`,
+	})
+	if err != nil {
+		return err
+	}
+
+	fmt.Print(readline.StartBracketedPaste)
+	defer fmt.Printf(readline.EndBracketedPaste)
+
+	var sb strings.Builder
+	var multiline MultilineState
+
+	for {
+		line, err := scanner.Readline()
+		switch {
+		case errors.Is(err, io.EOF):
+			fmt.Println()
+			return nil
+		case errors.Is(err, readline.ErrInterrupt):
+			if line == "" {
+				fmt.Println("\nUse Ctrl + d or /bye to exit.")
+			}
+
+			scanner.Prompt.UseAlt = false
+			sb.Reset()
+
+			continue
+		case err != nil:
+			return err
+		}
+
+		switch {
+		case multiline != MultilineNone:
+			// check if there's a multiline terminating string
+			before, ok := strings.CutSuffix(line, `"""`)
+			sb.WriteString(before)
+			if !ok {
+				fmt.Fprintln(&sb)
+				continue
+			}
+
+			switch multiline {
+			case MultilineSystem:
+				opts.System = sb.String()
+				opts.Messages = append(opts.Messages, api.Message{Role: "system", Content: opts.System})
+				fmt.Println("Set system message.")
+				sb.Reset()
+			case MultilineTemplate:
+				opts.Template = sb.String()
+				fmt.Println("Set prompt template.")
+				sb.Reset()
+			}
+
+			multiline = MultilineNone
+			scanner.Prompt.UseAlt = false
+		case strings.HasPrefix(line, `"""`):
+			line := strings.TrimPrefix(line, `"""`)
+			line, ok := strings.CutSuffix(line, `"""`)
+			sb.WriteString(line)
+			if !ok {
+				// no multiline terminating string; need more input
+				fmt.Fprintln(&sb)
+				multiline = MultilinePrompt
+				scanner.Prompt.UseAlt = true
+			}
+		case scanner.Pasting:
+			fmt.Fprintln(&sb, line)
+			continue
+		case strings.HasPrefix(line, "/list"):
+			args := strings.Fields(line)
+			if err := ListHandler(cmd, args[1:]); err != nil {
+				return err
+			}
+		case strings.HasPrefix(line, "/load"):
+			args := strings.Fields(line)
+			if len(args) != 2 {
+				fmt.Println("Usage:\n  /load <modelname>")
+				continue
+			}
+			opts.Model = args[1]
+			opts.Messages = []api.Message{}
+			fmt.Printf("Loading model '%s'\n", opts.Model)
+			if err := loadModel(cmd, &opts); err != nil {
+				return err
+			}
+			continue
+		case strings.HasPrefix(line, "/save"):
+			args := strings.Fields(line)
+			if len(args) != 2 {
+				fmt.Println("Usage:\n  /save <modelname>")
+				continue
+			}
+
+			client, err := api.ClientFromEnvironment()
+			if err != nil {
+				fmt.Println("error: couldn't connect to ollama server")
+				return err
+			}
+
+			req := &api.CreateRequest{
+				Name:      args[1],
+				Modelfile: buildModelfile(opts),
+			}
+			fn := func(resp api.ProgressResponse) error { return nil }
+			err = client.Create(cmd.Context(), req, fn)
+			if err != nil {
+				fmt.Println("error: couldn't save model")
+				return err
+			}
+			fmt.Printf("Created new model '%s'\n", args[1])
+			continue
+		case strings.HasPrefix(line, "/set"):
+			args := strings.Fields(line)
+			if len(args) > 1 {
+				switch args[1] {
+				case "history":
+					scanner.HistoryEnable()
+				case "nohistory":
+					scanner.HistoryDisable()
+				case "wordwrap":
+					opts.WordWrap = true
+					fmt.Println("Set 'wordwrap' mode.")
+				case "nowordwrap":
+					opts.WordWrap = false
+					fmt.Println("Set 'nowordwrap' mode.")
+				case "verbose":
+					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() // for display in modelfile
+						newMessage := api.Message{Role: "system", Content: sb.String()}
+						// Check if the slice is not empty and the last message is from 'system'
+						if len(opts.Messages) > 0 && opts.Messages[len(opts.Messages)-1].Role == "system" {
+							// Replace the last message
+							opts.Messages[len(opts.Messages)-1] = newMessage
+						} else {
+							opts.Messages = append(opts.Messages, newMessage)
+						}
+						fmt.Println("Set system message.")
+						sb.Reset()
+					} else if args[1] == "template" {
+						opts.Template = sb.String()
+						fmt.Println("Set prompt template.")
+						sb.Reset()
+					}
+
+					sb.Reset()
+					continue
+				default:
+					fmt.Printf("Unknown command '/set %s'. Type /? for help\n", args[1])
+				}
+			} else {
+				usageSet()
+			}
+		case strings.HasPrefix(line, "/show"):
+			args := strings.Fields(line)
+			if len(args) > 1 {
+				client, err := api.ClientFromEnvironment()
+				if err != nil {
+					fmt.Println("error: couldn't connect to ollama server")
+					return err
+				}
+				req := &api.ShowRequest{
+					Name:     opts.Model,
+					System:   opts.System,
+					Template: opts.Template,
+					Options:  opts.Options,
+				}
+				resp, err := client.Show(cmd.Context(), req)
+				if err != nil {
+					fmt.Println("error: couldn't get model")
+					return err
+				}
+
+				switch args[1] {
+				case "info":
+					fmt.Println("Model details:")
+					if len(resp.Details.Families) > 0 {
+						fmt.Printf("Family              %s\n", strings.Join(resp.Details.Families, ", "))
+					} else if resp.Details.Family != "" {
+						fmt.Printf("Family              %s\n", resp.Details.Family)
+					}
+					fmt.Printf("Parameter Size      %s\n", resp.Details.ParameterSize)
+					fmt.Printf("Quantization Level  %s\n", resp.Details.QuantizationLevel)
+					fmt.Println("")
+				case "license":
+					if resp.License == "" {
+						fmt.Println("No license was specified for this model.")
+					} else {
+						fmt.Println(resp.License)
+					}
+				case "modelfile":
+					fmt.Println(resp.Modelfile)
+				case "parameters":
+					if resp.Parameters == "" {
+						fmt.Println("No parameters were specified for this model.")
+					} else {
+						if len(opts.Options) > 0 {
+							fmt.Println("User defined parameters:")
+							for k, v := range opts.Options {
+								fmt.Printf("%-*s %v\n", 30, k, v)
+							}
+							fmt.Println()
+						}
+						fmt.Println("Model defined parameters:")
+						fmt.Println(resp.Parameters)
+					}
+				case "system":
+					switch {
+					case opts.System != "":
+						fmt.Println(opts.System + "\n")
+					case resp.System != "":
+						fmt.Println(resp.System + "\n")
+					default:
+						fmt.Println("No system message was specified for this model.")
+					}
+				case "template":
+					switch {
+					case opts.Template != "":
+						fmt.Println(opts.Template + "\n")
+					case resp.Template != "":
+						fmt.Println(resp.Template)
+					default:
+						fmt.Println("No prompt template was specified for this model.")
+					}
+				default:
+					fmt.Printf("Unknown command '/show %s'. Type /? for help\n", args[1])
+				}
+			} else {
+				usageShow()
+			}
+		case strings.HasPrefix(line, "/help"), strings.HasPrefix(line, "/?"):
+			args := strings.Fields(line)
+			if len(args) > 1 {
+				switch args[1] {
+				case "set", "/set":
+					usageSet()
+				case "show", "/show":
+					usageShow()
+				case "shortcut", "shortcuts":
+					usageShortcuts()
+				}
+			} else {
+				usage()
+			}
+		case strings.HasPrefix(line, "/exit"), strings.HasPrefix(line, "/bye"):
+			return nil
+		case strings.HasPrefix(line, "/"):
+			args := strings.Fields(line)
+			isFile := false
+
+			if opts.MultiModal {
+				for _, f := range extractFileNames(line) {
+					if strings.HasPrefix(f, args[0]) {
+						isFile = true
+						break
+					}
+				}
+			}
+
+			if !isFile {
+				fmt.Printf("Unknown command '%s'. Type /? for help\n", args[0])
+				continue
+			}
+
+			sb.WriteString(line)
+		default:
+			sb.WriteString(line)
+		}
+
+		if sb.Len() > 0 && multiline == MultilineNone {
+			newMessage := api.Message{Role: "user", Content: sb.String()}
+
+			if opts.MultiModal {
+				msg, images, err := extractFileData(sb.String())
+				if err != nil {
+					return err
+				}
+
+				// clear all previous images for better responses
+				if len(images) > 0 {
+					for i := range opts.Messages {
+						opts.Messages[i].Images = nil
+					}
+				}
+
+				newMessage.Content = msg
+				newMessage.Images = images
+			}
+
+			opts.Messages = append(opts.Messages, newMessage)
+
+			assistant, err := chat(cmd, opts)
+			if err != nil {
+				return err
+			}
+			if assistant != nil {
+				opts.Messages = append(opts.Messages, *assistant)
+			}
+
+			sb.Reset()
+		}
+	}
+}
+
+func buildModelfile(opts runOptions) string {
+	var mf strings.Builder
+	model := opts.ParentModel
+	if model == "" {
+		model = opts.Model
+	}
+	fmt.Fprintf(&mf, "FROM %s\n", model)
+	if opts.System != "" {
+		fmt.Fprintf(&mf, "SYSTEM \"\"\"%s\"\"\"\n", opts.System)
+	}
+
+	if opts.Template != "" {
+		fmt.Fprintf(&mf, "TEMPLATE \"\"\"%s\"\"\"\n", opts.Template)
+	}
+
+	keys := make([]string, 0)
+	for k := range opts.Options {
+		keys = append(keys, k)
+	}
+	sort.Strings(keys)
+	for _, k := range keys {
+		fmt.Fprintf(&mf, "PARAMETER %s %v\n", k, opts.Options[k])
+	}
+	fmt.Fprintln(&mf)
+
+	for _, msg := range opts.Messages {
+		fmt.Fprintf(&mf, "MESSAGE %s \"\"\"%s\"\"\"\n", msg.Role, msg.Content)
+	}
+
+	return mf.String()
+}
+
+func normalizeFilePath(fp string) string {
+	// Define a map of escaped characters and their replacements
+	replacements := map[string]string{
+		"\\ ":  " ",  // Escaped space
+		"\\(":  "(",  // Escaped left parenthesis
+		"\\)":  ")",  // Escaped right parenthesis
+		"\\[":  "[",  // Escaped left square bracket
+		"\\]":  "]",  // Escaped right square bracket
+		"\\{":  "{",  // Escaped left curly brace
+		"\\}":  "}",  // Escaped right curly brace
+		"\\$":  "$",  // Escaped dollar sign
+		"\\&":  "&",  // Escaped ampersand
+		"\\;":  ";",  // Escaped semicolon
+		"\\'":  "'",  // Escaped single quote
+		"\\\\": "\\", // Escaped backslash
+		"\\*":  "*",  // Escaped asterisk
+		"\\?":  "?",  // Escaped question mark
+	}
+
+	for escaped, actual := range replacements {
+		fp = strings.ReplaceAll(fp, escaped, actual)
+	}
+	return fp
+}
+
+func extractFileNames(input string) []string {
+	// Regex to match file paths starting with optional drive letter, / ./ \ or .\ and include escaped or unescaped spaces (\ or %20)
+	// and followed by more characters and a file extension
+	// This will capture non filename strings, but we'll check for file existence to remove mismatches
+	regexPattern := `(?:[a-zA-Z]:)?(?:\./|/|\\)[\S\\ ]+?\.(?i:jpg|jpeg|png|svg)\b`
+	re := regexp.MustCompile(regexPattern)
+
+	return re.FindAllString(input, -1)
+}
+
+func extractFileData(input string) (string, []api.ImageData, error) {
+	filePaths := extractFileNames(input)
+	var imgs []api.ImageData
+
+	for _, fp := range filePaths {
+		nfp := normalizeFilePath(fp)
+		data, err := getImageData(nfp)
+		if err != nil {
+			if os.IsNotExist(err) {
+				continue
+			}
+			fmt.Fprintf(os.Stderr, "Couldn't process image: %q\n", err)
+			return "", imgs, err
+		}
+		fmt.Fprintf(os.Stderr, "Added image '%s'\n", nfp)
+		input = strings.ReplaceAll(input, fp, "")
+		imgs = append(imgs, data)
+	}
+	return input, imgs, nil
+}
+
+func getImageData(filePath string) ([]byte, error) {
+	file, err := os.Open(filePath)
+	if err != nil {
+		return nil, err
+	}
+	defer file.Close()
+
+	buf := make([]byte, 512)
+	_, err = file.Read(buf)
+	if err != nil {
+		return nil, err
+	}
+
+	contentType := http.DetectContentType(buf)
+	allowedTypes := []string{"image/jpeg", "image/jpg", "image/png"}
+	if !slices.Contains(allowedTypes, contentType) {
+		return nil, fmt.Errorf("invalid image type: %s", contentType)
+	}
+
+	info, err := file.Stat()
+	if err != nil {
+		return nil, err
+	}
+
+	// Check if the file size exceeds 100MB
+	var maxSize int64 = 100 * 1024 * 1024 // 100MB in bytes
+	if info.Size() > maxSize {
+		return nil, fmt.Errorf("file size exceeds maximum limit (100MB)")
+	}
+
+	buf = make([]byte, info.Size())
+	_, err = file.Seek(0, 0)
+	if err != nil {
+		return nil, err
+	}
+
+	_, err = io.ReadFull(file, buf)
+	if err != nil {
+		return nil, err
+	}
+
+	return buf, nil
+}

cmd/interactive_test.go

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

cmd/start_darwin.go

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

cmd/start_default.go

@@ -0,0 +1,14 @@
+//go:build !windows && !darwin
+
+package cmd
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/jmorganca/ollama/api"
+)
+
+func startApp(ctx context.Context, client *api.Client) error {
+	return fmt.Errorf("could not connect to ollama server, run 'ollama serve' to start it")
+}

cmd/start_windows.go

@@ -0,0 +1,58 @@
+package cmd
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"syscall"
+
+	"github.com/jmorganca/ollama/api"
+)
+
+func startApp(ctx context.Context, client *api.Client) error {
+	// log.Printf("XXX Attempting to find and start ollama app")
+	AppName := "ollama app.exe"
+	exe, err := os.Executable()
+	if err != nil {
+		return err
+	}
+	appExe := filepath.Join(filepath.Dir(exe), AppName)
+	_, err = os.Stat(appExe)
+	if errors.Is(err, os.ErrNotExist) {
+		// Try the standard install location
+		localAppData := os.Getenv("LOCALAPPDATA")
+		appExe = filepath.Join(localAppData, "Ollama", AppName)
+		_, err := os.Stat(appExe)
+		if errors.Is(err, os.ErrNotExist) {
+			// Finally look in the path
+			appExe, err = exec.LookPath(AppName)
+			if err != nil {
+				return fmt.Errorf("could not locate ollama app")
+			}
+		}
+	}
+	// log.Printf("XXX attempting to start app %s", appExe)
+
+	cmd_path := "c:\\Windows\\system32\\cmd.exe"
+	cmd := exec.Command(cmd_path, "/c", appExe)
+	// TODO - these hide flags aren't working - still pops up a command window for some reason
+	cmd.SysProcAttr = &syscall.SysProcAttr{CreationFlags: 0x08000000, HideWindow: true}
+
+	// TODO this didn't help either...
+	cmd.Stdin = strings.NewReader("")
+	cmd.Stdout = os.Stdout
+	cmd.Stderr = os.Stderr
+
+	if err := cmd.Start(); err != nil {
+		return fmt.Errorf("unable to start ollama app %w", err)
+	}
+
+	if cmd.Process != nil {
+		defer cmd.Process.Release() //nolint:errcheck
+	}
+	return waitForServer(ctx, client)
+}

convert/convert.go

@@ -0,0 +1,331 @@
+package convert
+
+import (
+	"bytes"
+	"cmp"
+	"encoding/binary"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"os"
+	"path/filepath"
+	"regexp"
+	"slices"
+
+	"github.com/mitchellh/mapstructure"
+	"google.golang.org/protobuf/proto"
+
+	"github.com/jmorganca/ollama/convert/sentencepiece"
+	"github.com/jmorganca/ollama/llm"
+)
+
+type Params struct {
+	Architectures    []string `json:"architectures"`
+	VocabSize        int      `json:"vocab_size"`
+	HiddenSize       int      `json:"hidden_size"`       // n_embd
+	HiddenLayers     int      `json:"num_hidden_layers"` // n_layer
+	ContextSize      int      `json:"max_position_embeddings"`
+	IntermediateSize int      `json:"intermediate_size"`
+	AttentionHeads   int      `json:"num_attention_heads"` // n_head
+	KeyValHeads      int      `json:"num_key_value_heads"`
+	NormEPS          float64  `json:"rms_norm_eps"`
+	RopeFreqBase     float64  `json:"rope_theta"`
+	BoSTokenID       int      `json:"bos_token_id"`
+	EoSTokenID       int      `json:"eos_token_id"`
+}
+
+type MetaData struct {
+	Type    string `mapstructure:"dtype"`
+	Shape   []int  `mapstructure:"shape"`
+	Offsets []int  `mapstructure:"data_offsets"`
+}
+
+func ReadSafeTensors(fn string, offset uint64) ([]llm.Tensor, uint64, error) {
+	f, err := os.Open(fn)
+	if err != nil {
+		return []llm.Tensor{}, 0, err
+	}
+	defer f.Close()
+
+	var jsonSize uint64
+	binary.Read(f, binary.LittleEndian, &jsonSize)
+
+	buf := make([]byte, jsonSize)
+	_, err = io.ReadFull(f, buf)
+	if err != nil {
+		return []llm.Tensor{}, 0, err
+	}
+
+	d := json.NewDecoder(bytes.NewBuffer(buf))
+	d.UseNumber()
+	var parsed map[string]interface{}
+	if err = d.Decode(&parsed); err != nil {
+		return []llm.Tensor{}, 0, err
+	}
+
+	var keys []string
+	for k := range parsed {
+		keys = append(keys, k)
+	}
+
+	slices.Sort(keys)
+
+	slog.Info("converting layers")
+
+	var tensors []llm.Tensor
+	for _, k := range keys {
+		vals := parsed[k].(map[string]interface{})
+		var data MetaData
+		if err = mapstructure.Decode(vals, &data); err != nil {
+			return []llm.Tensor{}, 0, err
+		}
+
+		var size uint64
+		var kind uint32
+		switch len(data.Shape) {
+		case 0:
+			// metadata
+			continue
+		case 1:
+			// convert to float32
+			kind = 0
+			size = uint64(data.Shape[0] * 4)
+		case 2:
+			// convert to float16
+			kind = 1
+			size = uint64(data.Shape[0] * data.Shape[1] * 2)
+		}
+
+		ggufName, err := GetTensorName(k)
+		if err != nil {
+			slog.Error("%v", err)
+			return []llm.Tensor{}, 0, err
+		}
+
+		shape := []uint64{0, 0, 0, 0}
+		for i := range data.Shape {
+			shape[i] = uint64(data.Shape[i])
+		}
+
+		t := llm.Tensor{
+			Name:          ggufName,
+			Kind:          kind,
+			Offset:        offset,
+			Shape:         shape[:],
+			FileName:      fn,
+			OffsetPadding: 8 + jsonSize,
+			FileOffsets:   []uint64{uint64(data.Offsets[0]), uint64(data.Offsets[1])},
+		}
+		slog.Debug(fmt.Sprintf("%v", t))
+		tensors = append(tensors, t)
+		offset += size
+	}
+	return tensors, offset, nil
+}
+
+func GetSafeTensors(dirpath string) ([]llm.Tensor, error) {
+	var tensors []llm.Tensor
+	files, err := filepath.Glob(filepath.Join(dirpath, "/model-*.safetensors"))
+	if err != nil {
+		return []llm.Tensor{}, err
+	}
+
+	var offset uint64
+	for _, f := range files {
+		var t []llm.Tensor
+		var err error
+		t, offset, err = ReadSafeTensors(f, offset)
+		if err != nil {
+			slog.Error("%v", err)
+			return []llm.Tensor{}, err
+		}
+		tensors = append(tensors, t...)
+	}
+	return tensors, nil
+}
+
+func GetParams(dirpath string) (*Params, error) {
+	f, err := os.Open(filepath.Join(dirpath, "config.json"))
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	var params Params
+
+	d := json.NewDecoder(f)
+	err = d.Decode(&params)
+	if err != nil {
+		return nil, err
+	}
+
+	return &params, nil
+}
+
+// Details on gguf's tokenizer can be found at:
+// https://github.com/ggerganov/ggml/blob/master/docs/gguf.md#tokenizer
+type Vocab struct {
+	Tokens []string
+	Scores []float32
+	Types  []int32
+}
+
+func LoadTokens(dirpath string) (*Vocab, error) {
+	slog.Info(fmt.Sprintf("reading vocab from %s", filepath.Join(dirpath, "tokenizer.model")))
+	in, err := os.ReadFile(filepath.Join(dirpath, "tokenizer.model"))
+	if err != nil {
+		return nil, err
+	}
+
+	// To regenerate sentencepiece from the protobufs use:
+	// protoc -I=./ --go_out=./ sentencepiece_model.proto
+	modelProto := &sentencepiece.ModelProto{}
+	if err := proto.Unmarshal(in, modelProto); err != nil {
+		return nil, err
+	}
+
+	v := &Vocab{
+		Tokens: make([]string, 0),
+		Scores: make([]float32, 0),
+		Types:  make([]int32, 0),
+	}
+
+	pieces := modelProto.GetPieces()
+	for _, p := range pieces {
+		v.Tokens = append(v.Tokens, p.GetPiece())
+		v.Scores = append(v.Scores, p.GetScore())
+		t := p.GetType()
+		v.Types = append(v.Types, int32(t))
+	}
+
+	slog.Info(fmt.Sprintf("vocab size: %d", len(v.Tokens)))
+
+	// add any additional tokens
+	addIn, err := os.ReadFile(filepath.Join(dirpath, "added_tokens.json"))
+	if os.IsNotExist(err) {
+		return v, nil
+	} else if err != nil {
+		return nil, err
+	}
+
+	slog.Info("reading user defined tokens")
+
+	var extraTokenData map[string]int
+	if err := json.Unmarshal(addIn, &extraTokenData); err != nil {
+		return nil, err
+	}
+
+	type token struct {
+		key string
+		pos int
+	}
+
+	extraTokens := make([]token, 0)
+	for k, id := range extraTokenData {
+		extraTokens = append(extraTokens, token{k, id})
+	}
+
+	slices.SortFunc(extraTokens, func(a, b token) int {
+		return cmp.Compare(a.pos, b.pos)
+	})
+
+	numToks := len(v.Tokens)
+
+	for cnt, t := range extraTokens {
+		// the token id should match the specific index for the total number of tokens
+		if t.pos != cnt+numToks {
+			return nil, fmt.Errorf("token ID '%d' for '%s' doesn't match total token size", t.pos, t.key)
+		}
+		v.Tokens = append(v.Tokens, t.key)
+		v.Scores = append(v.Scores, -1000.0)
+		v.Types = append(v.Types, int32(llm.GGUFTokenUserDefined))
+	}
+	slog.Info(fmt.Sprintf("vocab size w/ extra tokens: %d", len(v.Tokens)))
+
+	return v, nil
+}
+
+func GetTensorName(n string) (string, error) {
+	tMap := map[string]string{
+		"model.embed_tokens.weight":                           "token_embd.weight",
+		"model.layers.(\\d+).input_layernorm.weight":          "blk.$1.attn_norm.weight",
+		"model.layers.(\\d+).mlp.down_proj.weight":            "blk.$1.ffn_down.weight",
+		"model.layers.(\\d+).mlp.gate_proj.weight":            "blk.$1.ffn_gate.weight",
+		"model.layers.(\\d+).mlp.up_proj.weight":              "blk.$1.ffn_up.weight",
+		"model.layers.(\\d+).post_attention_layernorm.weight": "blk.$1.ffn_norm.weight",
+		"model.layers.(\\d+).self_attn.k_proj.weight":         "blk.$1.attn_k.weight",
+		"model.layers.(\\d+).self_attn.o_proj.weight":         "blk.$1.attn_output.weight",
+		"model.layers.(\\d+).self_attn.q_proj.weight":         "blk.$1.attn_q.weight",
+		"model.layers.(\\d+).self_attn.v_proj.weight":         "blk.$1.attn_v.weight",
+		"lm_head.weight":    "output.weight",
+		"model.norm.weight": "output_norm.weight",
+	}
+
+	v, ok := tMap[n]
+	if ok {
+		return v, nil
+	}
+
+	// quick hack to rename the layers to gguf format
+	for k, v := range tMap {
+		re := regexp.MustCompile(k)
+		newName := re.ReplaceAllString(n, v)
+		if newName != n {
+			return newName, nil
+		}
+	}
+
+	return "", fmt.Errorf("couldn't find a layer name for '%s'", n)
+}
+
+func WriteGGUF(name string, tensors []llm.Tensor, params *Params, vocab *Vocab) (string, error) {
+	c := llm.ContainerGGUF{
+		ByteOrder: binary.LittleEndian,
+	}
+
+	m := llm.NewGGUFModel(&c)
+	m.Tensors = tensors
+	m.KV["general.architecture"] = "llama"
+	m.KV["general.name"] = name
+	m.KV["llama.context_length"] = uint32(params.ContextSize)
+	m.KV["llama.embedding_length"] = uint32(params.HiddenSize)
+	m.KV["llama.block_count"] = uint32(params.HiddenLayers)
+	m.KV["llama.feed_forward_length"] = uint32(params.IntermediateSize)
+	m.KV["llama.rope.dimension_count"] = uint32(128)
+	m.KV["llama.attention.head_count"] = uint32(params.AttentionHeads)
+	m.KV["llama.attention.head_count_kv"] = uint32(params.KeyValHeads)
+	m.KV["llama.attention.layer_norm_rms_epsilon"] = float32(params.NormEPS)
+	m.KV["llama.rope.freq_base"] = float32(params.RopeFreqBase)
+	m.KV["general.file_type"] = uint32(1)
+	m.KV["tokenizer.ggml.model"] = "llama"
+
+	m.KV["tokenizer.ggml.tokens"] = vocab.Tokens
+	m.KV["tokenizer.ggml.scores"] = vocab.Scores
+	m.KV["tokenizer.ggml.token_type"] = vocab.Types
+
+	m.KV["tokenizer.ggml.bos_token_id"] = uint32(params.BoSTokenID)
+	m.KV["tokenizer.ggml.eos_token_id"] = uint32(params.EoSTokenID)
+	m.KV["tokenizer.ggml.unknown_token_id"] = uint32(0)
+	m.KV["tokenizer.ggml.add_bos_token"] = true
+	m.KV["tokenizer.ggml.add_eos_token"] = false
+
+	// llamacpp sets the chat template, however we don't need to set it since we pass it in through a layer
+	// m.KV["tokenizer.chat_template"] = "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}" // XXX removeme
+
+	c.V3.NumTensor = uint64(len(tensors))
+	c.V3.NumKV = uint64(len(m.KV))
+
+	f, err := os.CreateTemp("", "ollama-gguf")
+	if err != nil {
+		return "", err
+	}
+	defer f.Close()
+
+	err = m.Encode(f)
+	if err != nil {
+		return "", err
+	}
+
+	return f.Name(), nil
+}

convert/sentencepiece_model.proto

@@ -0,0 +1,333 @@
+// Copyright 2016 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.!
+
+syntax = "proto2";
+
+// TODO(taku): Needs to use LITE RUNTIME in OSS release.
+option optimize_for = LITE_RUNTIME;
+option go_package = "./sentencepiece";
+
+package sentencepiece;
+
+// TrainerSpec encodes a various parameters for SentencePiece training.
+// Next id: 55
+message TrainerSpec {
+  ///////////////////////////////////////////////////////////////////
+  // General parameters
+  //
+  // Input corpus files.
+  //  Trainer accepts the following two formats:
+  //  A) Monolingual: plain text, one sentence per line.
+  //  B) Bilingual:   TSV, source sentence <tab> target sentence
+  //  When bilingual data is passed, shared vocabulary model is built.
+  //  Note that the input file must be raw corpus, not a preprocessed corpus.
+  //  Trainer only loads the first `input_sentence_size` sentences specified
+  //  with this parameter.
+  repeated string input = 1;
+
+  // Input corpus format:
+  // "text": one-sentence-per-line text format (default)
+  // "tsv":  sentence <tab> freq
+  optional string input_format = 7;
+
+  // Output model file prefix.
+  // <model_prefix>.model and <model_prefix>.vocab are generated.
+  optional string model_prefix = 2;
+
+  // Model type. only have UNIGRAM now.
+  enum ModelType {
+    UNIGRAM = 1;  // Unigram language model with dynamic algorithm
+    BPE = 2;      // Byte Pair Encoding
+    WORD = 3;     // Delimitered by whitespace.
+    CHAR = 4;     // tokenizes into character sequence
+  }
+  optional ModelType model_type = 3 [default = UNIGRAM];
+
+  // Vocabulary size. 8k is the default size.
+  optional int32 vocab_size = 4 [default = 8000];
+
+  // List of the languages this model can accept.
+  // Since the model is language-agnostic, this field is used as a reference.
+  repeated string accept_language = 5;
+
+  // Size of self-test samples, which are encoded in the model file.
+  optional int32 self_test_sample_size = 6 [default = 0];
+
+  // Whether to use DP version of sentencepiece. Use it with TSV input format
+  // (requires precomputed word tab counts to work).
+  optional bool enable_differential_privacy = 50 [default = false];
+  // Set these parameters if you need DP version of sentencepiece.
+  // std of noise to add.
+  optional float differential_privacy_noise_level = 51 [default = 0.0];
+  // Clipping threshold to apply after adding noise. All the words with
+  // frequency less than this value are dropped.
+  optional uint64 differential_privacy_clipping_threshold = 52 [default = 0];
+
+  ///////////////////////////////////////////////////////////////////
+  // Training parameters.
+  //
+  // Uses characters which cover the corpus with the ratio of `chars_coverage`.
+  // This parameter determines the set of basic Alphabet of sentence piece.
+  // 1.0 - `chars_coverage` characters are treated as UNK.
+  // See also required_chars field.
+  optional float character_coverage = 10 [default = 0.9995];
+
+  // Maximum size of sentences the trainer loads from `input` parameter.
+  // Trainer simply loads the `input` files in sequence.
+  // It is better to shuffle the input corpus randomly.
+  optional uint64 input_sentence_size = 11 [default = 0];
+  optional bool shuffle_input_sentence = 19 [default = true];
+
+  // Maximum size of sentences to make seed sentence pieces.
+  // Extended suffix array is constructed to extract frequent
+  // sub-strings from the corpus. This uses 20N working space,
+  // where N is the size of corpus.
+  optional int32 mining_sentence_size = 12 [deprecated = true];
+
+  // Maximum size of sentences to train sentence pieces.
+  optional int32 training_sentence_size = 13 [deprecated = true];
+
+  // The size of seed sentencepieces.
+  // `seed_sentencepiece_size` must be larger than `vocab_size`.
+  optional int32 seed_sentencepiece_size = 14 [default = 1000000];
+
+  // In every EM sub-iterations, keeps top
+  // `shrinking_factor` * `current sentencepieces size` with respect to
+  // the loss of the sentence piece. This value should be smaller than 1.0.
+  optional float shrinking_factor = 15 [default = 0.75];
+
+  // The maximum sentence length in byte. The sentences with the length
+  // larger than `max_sentence_length` is simply ignored.
+  // Longer input tends to bring the following risks:
+  //  * Overflow during EM training (unigram language model only)
+  //  * Performance drop because of O(n log n) cost in BPE.
+  optional int32 max_sentence_length = 18 [default = 4192];
+
+  // Number of threads in the training.
+  optional int32 num_threads = 16 [default = 16];
+
+  // Number of EM sub iterations.
+  optional int32 num_sub_iterations = 17 [default = 2];
+
+  ///////////////////////////////////////////////////////////////////
+  // SentencePiece parameters which control the shapes of sentence piece.
+  //
+  // Maximum length of sentencepiece.
+  optional int32 max_sentencepiece_length = 20 [default = 16];
+
+  // Uses Unicode script to split sentence pieces.
+  // When `split_by_unicode_script` is true, we do not allow sentence piece to
+  // include multiple Unicode scripts, e.g. "F1" is not a valid piece.
+  // Exception: CJ characters (Hiragana/Katakana/Han) are all handled
+  // as one script type, since Japanese word can consist of multiple scripts.
+  // This exception is always applied regardless of the accept-language
+  // parameter.
+  optional bool split_by_unicode_script = 21 [default = true];
+
+  // When `split_by_number` is true, put a boundary between number and
+  // non-number transition. If we want to treat "F1" is one token, set this flag
+  // to be false.
+  optional bool split_by_number = 23 [default = true];
+
+  // Use a white space to split sentence pieces.
+  // When `split_by_whitespace` is false, we may have the piece containing
+  // a white space in the middle. e.g., "in_the".
+  optional bool split_by_whitespace = 22 [default = true];
+
+  // Adds whitespace symbol (_) as a suffix instead of prefix. e.g., _hello =>
+  // hello_. When `treat_whitespace_as_suffix` is true,
+  // NormalizerSpec::add_dummy_prefix will add the dummy whitespace to the end
+  // of sentence.
+  optional bool treat_whitespace_as_suffix = 24 [default = false];
+
+  // Allows pieces that only contain whitespaces instead of appearing only as
+  // prefix or suffix of other pieces.
+  optional bool allow_whitespace_only_pieces = 26 [default = false];
+
+  // Split all digits (0-9) into separate pieces.
+  optional bool split_digits = 25 [default = false];
+
+  // Defines the pre-tokenization delimiter.
+  // When specified, no pieces crossing this delimiter is not included
+  // in the vocab. Then the delimiter string is virtually ignored
+  // during the training. This field can allows constraints on the vocabulary
+  // selection. Note that this field is available on unigram mode.
+  optional string pretokenization_delimiter = 53 [ default = ""];
+
+  ///////////////////////////////////////////////////////////////////
+  // Vocabulary management
+  //
+  // Defines control symbols used as an indicator to
+  // change the behavior of the decoder. <s> and </s> are pre-defined.
+  // We can use this field to encode various meta information,
+  // including language indicator in multilingual model.
+  // These symbols are not visible to users, but visible to
+  // the decoder. Note that when the input sentence contains control symbols,
+  // they are not treated as one token, but segmented into normal pieces.
+  // Control symbols must be inserted independently from the segmentation.
+  repeated string control_symbols = 30;
+
+  // Defines user defined symbols.
+  // These symbols are added with extremely high score
+  // so they are always treated as one unique symbol in any context.
+  // Typical usage of user_defined_symbols is placeholder for named entities.
+  repeated string user_defined_symbols = 31;
+
+  // Defines required characters. Each UTF8 character in this string is included
+  // in the character set regardless of character_coverage value. Unlike
+  // user_defined_symbols, these characters have scores based on the frequency
+  // on input sentences, and the model can form subwords using characters
+  // in this field.
+  optional string required_chars = 36;
+
+  // Decomposes unknown pieces into UTF-8 bytes.
+  optional bool byte_fallback = 35 [default = false];
+
+  // When creating the vocabulary file, defines whether or not to additionally
+  // output the score for each piece.
+  optional bool vocabulary_output_piece_score = 32 [default = true];
+
+  // `vocab_size` is treated as hard limit. Crash if
+  // the model can not produce the vocab of size `vocab_size`,
+  // When `hard_vocab_limit` is false, vocab_size is treated
+  // as soft limit. Note that when model_type=char,
+  // always assumes hard_vocab_limit = false.
+  optional bool hard_vocab_limit = 33 [default = true];
+
+  // use all symbols for vocab extraction. This flag is valid
+  // if model type is either CHAR or WORD
+  optional bool use_all_vocab = 34 [default = false];
+
+  ///////////////////////////////////////////////////////////////////
+  // Reserved special meta tokens.
+  // * -1 is not used.
+  // * unk_id must not be -1.
+  // Id must starts with 0 and be contigous.
+  optional int32 unk_id = 40 [default = 0];   // <unk>
+  optional int32 bos_id = 41 [default = 1];   // <s>
+  optional int32 eos_id = 42 [default = 2];   // </s>
+  optional int32 pad_id = 43 [default = -1];  // <pad> (padding)
+  optional string unk_piece = 45 [default = "<unk>"];
+  optional string bos_piece = 46 [default = "<s>"];
+  optional string eos_piece = 47 [default = "</s>"];
+  optional string pad_piece = 48 [default = "<pad>"];
+
+  // Encodes <unk> into U+2047 (DOUBLE QUESTION MARK),
+  // since this character can be useful both for user and
+  // developer. We can easily figure out that <unk> is emitted.
+  optional string unk_surface = 44 [default = " \xE2\x81\x87 "];
+
+  // Increase bit depth to allow unigram model training on large
+  // (>10M sentences) corpora. A Side-effect of enabling this flag
+  // is increased memory usage.
+  optional bool train_extremely_large_corpus = 49 [default = false];
+
+ // Path to a seed sentencepieces file, with one tab-separated
+  // seed sentencepiece <tab> frequency per line.
+  optional string seed_sentencepieces_file = 54 [default = ""];
+
+  // Customized extensions: the range of field numbers
+  // are open to third-party extensions.
+  extensions 200 to max;
+}
+
+// NormalizerSpec encodes a various parameters for string normalizaiton
+message NormalizerSpec {
+  // name of normalization rule.
+  optional string name = 1;
+
+  // Pre-compiled normalization rule created by
+  // Builder::GetPrecompiledCharsMap() or Builder::CompileCharsMap() method.
+  // Usually this field is set by Builder::GetNormalizerSpec() method.
+  optional bytes precompiled_charsmap = 2;
+
+  // Adds dummy whitespace at the beginning of text in order to
+  // treat "world" in "world" and "hello world" in the same way.
+  optional bool add_dummy_prefix = 3 [default = true];
+
+  // Removes leading, trailing, and duplicate internal whitespace.
+  optional bool remove_extra_whitespaces = 4 [default = true];
+
+  // Replaces whitespace with meta symbol.
+  // This field must be true to train sentence piece model.
+  optional bool escape_whitespaces = 5 [default = true];
+
+  // Custom normalization rule file in TSV format.
+  // https://github.com/google/sentencepiece/blob/master/doc/normalization.md
+  // This field is only used in SentencePieceTrainer::Train() method, which
+  // compiles the rule into the binary rule stored in `precompiled_charsmap`.
+  optional string normalization_rule_tsv = 6;
+
+  // Customized extensions: the range of field numbers
+  // are open to third-party extensions.
+  extensions 200 to max;
+}
+
+// Proto to store samples for self-testing.
+message SelfTestData {
+  message Sample {
+    optional string input = 1;
+    optional string expected = 2;
+  }
+  repeated Sample samples = 1;
+
+  // Customized extensions: the range of field numbers
+  // are open to third-party extensions.
+  extensions 200 to max;
+}
+
+// ModelProto stores model parameters.
+// SentencePieceProcessor is supposed to be self-contained.
+// All settings/parameters which may change the behavior must be encoded
+// in ModelProto.
+message ModelProto {
+  message SentencePiece {
+    enum Type {
+      NORMAL = 1;        // normal symbol
+      UNKNOWN = 2;       // unknown symbol. only <unk> for now.
+      CONTROL = 3;       // control symbols. </s>, <s>, <2ja> etc.
+      USER_DEFINED = 4;  // user defined symbols.
+                         // Typical usage of USER_DEFINED symbol
+                         // is placeholder.
+      BYTE = 6;          // byte symbols. Used when `byte_fallback` is true.
+      UNUSED = 5;        // this piece is not used.
+    }
+    optional string piece = 1;  // piece must not be empty.
+    optional float score = 2;
+    optional Type type = 3 [default = NORMAL];
+
+    // Customized extensions: the range of field numbers
+    // are open to third-party extensions.
+    extensions 200 to max;
+  }
+
+  // Sentence pieces with scores.
+  repeated SentencePiece pieces = 1;
+
+  // Spec used to generate this model file.
+  optional TrainerSpec trainer_spec = 2;
+
+  // Spec for text normalization.
+  optional NormalizerSpec normalizer_spec = 3;
+
+  // Stores sample input and its expected segmentation to verify the model.
+  optional SelfTestData self_test_data = 4;
+
+  // Spec for text de-normalization.
+  optional NormalizerSpec denormalizer_spec = 5;
+
+  // Customized extensions: the range of field numbers
+  // are open to third-party extensions.
+  extensions 200 to max;
+}

docs/README.md

@@ -1,6 +1,21 @@
 # Documentation
 
-- [Modelfile](./modelfile.md)
-- [How to develop Ollama](./development.md)
-- [API](./api.md)
-- [Tutorials](./tutorials.md)
+### Getting Started
+* [Quickstart](../README.md#quickstart)
+* [Examples](../examples)
+* [Importing models](./import.md)
+* [Linux Documentation](./linux.md)
+* [Windows Documentation](./windows.md)
+* [Docker Documentation](https://hub.docker.com/r/ollama/ollama)
+
+### Reference
+
+* [API Reference](./api.md)
+* [Modelfile Reference](./modelfile.md)
+* [OpenAI Compatibility](./openai.md)
+
+### Resources
+
+* [Troubleshooting Guide](./troubleshooting.md)
+* [FAQ](./faq.md)
+* [Development guide](./development.md)

docs/api.md

@@ -3,6 +3,7 @@
 ## Endpoints
 
 - [Generate a completion](#generate-a-completion)
+- [Generate a chat completion](#generate-a-chat-completion)
 - [Create a Model](#create-a-model)
 - [List Local Models](#list-local-models)
 - [Show Model Information](#show-model-information)
@@ -16,7 +17,7 @@
 
 ### Model names
 
-Model names follow a `model:tag` format. Some examples are `orca-mini:3b-q4_1` and `llama2:70b`. The tag is optional and, if not provided, will default to `latest`. The tag is used to identify a specific version.
+Model names follow a `model:tag` format, where `model` can have an optional namespace such as `example/model`. Some examples are `orca-mini:3b-q4_1` and `llama2:70b`. The tag is optional and, if not provided, will default to `latest`. The tag is used to identify a specific version.
 
 ### Durations
 
@@ -24,7 +25,7 @@ All durations are returned in nanoseconds.
 
 ### Streaming responses
 
-Certain endpoints stream responses as JSON objects delineated with the newline (`\n`) character.
+Certain endpoints stream responses as JSON objects and can optional return non-streamed responses.
 
 ## Generate a completion
 
@@ -32,32 +33,36 @@ Certain endpoints stream responses as JSON objects delineated with the newline (
 POST /api/generate
 ```
 
-Generate a response for a given prompt with a provided model. This is a streaming endpoint, so will be a series of responses. The final response object will include statistics and additional data from the request.
+Generate a response for a given prompt with a provided model. This is a streaming endpoint, so there will be a series of responses. The final response object will include statistics and additional data from the request.
 
 ### Parameters
 
 - `model`: (required) the [model name](#model-names)
 - `prompt`: the prompt to generate a response for
+- `images`: (optional) a list of base64-encoded images (for multimodal models such as `llava`)
 
 Advanced parameters (optional):
 
 - `format`: the format to return a response in. Currently the only accepted value is `json`
 - `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
-- `system`: system prompt to (overrides what is defined in the `Modelfile`)
-- `template`: the full prompt or prompt template (overrides what is defined in the `Modelfile`)
+- `system`: system message to (overrides what is defined in the `Modelfile`)
+- `template`: the prompt template to use (overrides what is defined in the `Modelfile`)
 - `context`: the context parameter returned from a previous request to `/generate`, this can be used to keep a short conversational memory
 - `stream`: if `false` the response will be returned as a single response object, rather than a stream of objects
-- `raw`: if `true` no formatting will be applied to the prompt and no context will be returned. You may choose to use the `raw` parameter if you are specifying a full templated prompt in your request to the API, and are managing history yourself.
+- `raw`: if `true` no formatting will be applied to the prompt. You may choose to use the `raw` parameter if you are specifying a full templated prompt in your request to the API
+- `keep_alive`: controls how long the model will stay loaded into memory following the request (default: `5m`)
 
-### JSON mode
+#### JSON mode
 
-Enable JSON mode by setting the `format` parameter to `json`. This will structure the response as valid JSON. See the JSON mode [example](#request-json-mode) below.
+Enable JSON mode by setting the `format` parameter to `json`. This will structure the response as a valid JSON object. See the JSON mode [example](#request-json-mode) below.
 
 > Note: it's important to instruct the model to use JSON in the `prompt`. Otherwise, the model may generate large amounts whitespace.
 
 ### Examples
 
-#### Request
+#### Generate request (Streaming)
+
+##### Request
 
 ```shell
 curl http://localhost:11434/api/generate -d '{
@@ -66,7 +71,7 @@ curl http://localhost:11434/api/generate -d '{
 }'
 ```
 
-#### Response
+##### Response
 
 A stream of JSON objects is returned:
 
@@ -83,8 +88,6 @@ The final response in the stream also includes additional data about the generat
 
 - `total_duration`: time spent generating the response
 - `load_duration`: time spent in nanoseconds loading the model
-- `sample_count`: number of samples generated
-- `sample_duration`: time spent generating samples
 - `prompt_eval_count`: number of tokens in the prompt
 - `prompt_eval_duration`: time spent in nanoseconds evaluating the prompt
 - `eval_count`: number of tokens the response
@@ -99,21 +102,23 @@ To calculate how fast the response is generated in tokens per second (token/s),
   "model": "llama2",
   "created_at": "2023-08-04T19:22:45.499127Z",
   "response": "",
-  "context": [1, 2, 3],
   "done": true,
-  "total_duration": 5589157167,
-  "load_duration": 3013701500,
-  "sample_count": 114,
-  "sample_duration": 81442000,
-  "prompt_eval_count": 46,
-  "prompt_eval_duration": 1160282000,
-  "eval_count": 113,
-  "eval_duration": 1325948000
+  "context": [1, 2, 3],
+  "total_duration": 10706818083,
+  "load_duration": 6338219291,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 130079000,
+  "eval_count": 259,
+  "eval_duration": 4232710000
 }
 ```
 
 #### Request (No streaming)
 
+##### Request
+
+A response can be received in one reply when streaming is off.
+
 ```shell
 curl http://localhost:11434/api/generate -d '{
   "model": "llama2",
@@ -122,7 +127,7 @@ curl http://localhost:11434/api/generate -d '{
 }'
 ```
 
-#### Response
+##### Response
 
 If `stream` is set to `false`, the response will be a single JSON object:
 
@@ -131,51 +136,23 @@ If `stream` is set to `false`, the response will be a single JSON object:
   "model": "llama2",
   "created_at": "2023-08-04T19:22:45.499127Z",
   "response": "The sky is blue because it is the color of the sky.",
+  "done": true,
   "context": [1, 2, 3],
-  "done": true,
-  "total_duration": 5589157167,
-  "load_duration": 3013701500,
-  "sample_count": 114,
-  "sample_duration": 81442000,
-  "prompt_eval_count": 46,
-  "prompt_eval_duration": 1160282000,
-  "eval_count": 13,
-  "eval_duration": 1325948000
-}
-```
-
-#### Request (Raw mode)
-
-In some cases you may wish to bypass the templating system and provide a full prompt. In this case, you can use the `raw` parameter to disable formatting and context.
-
-```shell
-curl http://localhost:11434/api/generate -d '{
-  "model": "mistral",
-  "prompt": "[INST] why is the sky blue? [/INST]",
-  "raw": true,
-  "stream": false
-}'
-```
-
-#### Response
-
-```json
-{
-  "model": "mistral",
-  "created_at": "2023-11-03T15:36:02.583064Z",
-  "response": " The sky appears blue because of a phenomenon called Rayleigh scattering.",
-  "done": true,
-  "total_duration": 14648695333,
-  "load_duration": 3302671417,
-  "prompt_eval_count": 14,
-  "prompt_eval_duration": 286243000,
-  "eval_count": 129,
-  "eval_duration": 10931424000
+  "total_duration": 5043500667,
+  "load_duration": 5025959,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 325953000,
+  "eval_count": 290,
+  "eval_duration": 4709213000
 }
 ```
 
 #### Request (JSON mode)
 
+> When `format` is set to `json`, the output will always be a well-formed JSON object. It's important to also instruct the model to respond in JSON.
+
+##### Request
+
 ```shell
 curl http://localhost:11434/api/generate -d '{
   "model": "llama2",
@@ -185,7 +162,7 @@ curl http://localhost:11434/api/generate -d '{
 }'
 ```
 
-#### Response
+##### Response
 
 ```json
 {
@@ -193,12 +170,13 @@ curl http://localhost:11434/api/generate -d '{
   "created_at": "2023-11-09T21:07:55.186497Z",
   "response": "{\n\"morning\": {\n\"color\": \"blue\"\n},\n\"noon\": {\n\"color\": \"blue-gray\"\n},\n\"afternoon\": {\n\"color\": \"warm gray\"\n},\n\"evening\": {\n\"color\": \"orange\"\n}\n}\n",
   "done": true,
-  "total_duration": 4661289125,
-  "load_duration": 1714434500,
+  "context": [1, 2, 3],
+  "total_duration": 4648158584,
+  "load_duration": 4071084,
   "prompt_eval_count": 36,
-  "prompt_eval_duration": 264132000,
-  "eval_count": 75,
-  "eval_duration": 2112149000
+  "prompt_eval_duration": 439038000,
+  "eval_count": 180,
+  "eval_duration": 4196918000
 }
 ```
 
@@ -221,10 +199,94 @@ The value of `response` will be a string containing JSON similar to:
 }
 ```
 
-#### Request (With options)
+#### Request (with images)
+
+To submit images to multimodal models such as `llava` or `bakllava`, provide a list of base64-encoded `images`:
+
+#### Request
+
+```shell
+curl http://localhost:11434/api/generate -d '{
+  "model": "llava",
+  "prompt":"What is in this picture?",
+  "stream": false,
+  "images": ["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"]
+}'
+```
+
+#### Response
+
+```
+{
+  "model": "llava",
+  "created_at": "2023-11-03T15:36:02.583064Z",
+  "response": "A happy cartoon character, which is cute and cheerful.",
+  "done": true,
+  "context": [1, 2, 3],
+  "total_duration": 2938432250,
+  "load_duration": 2559292,
+  "prompt_eval_count": 1,
+  "prompt_eval_duration": 2195557000,
+  "eval_count": 44,
+  "eval_duration": 736432000
+}
+```
+
+#### Request (Raw Mode)
+
+In some cases, you may wish to bypass the templating system and provide a full prompt. In this case, you can use the `raw` parameter to disable templating. Also note that raw mode will not return a context.
+
+##### Request
+
+```shell
+curl http://localhost:11434/api/generate -d '{
+  "model": "mistral",
+  "prompt": "[INST] why is the sky blue? [/INST]",
+  "raw": true,
+  "stream": false
+}'
+```
+
+#### Request (Reproducible outputs)
+
+For reproducible outputs, set `temperature` to 0 and `seed` to a number:
+
+##### Request
+
+```shell
+curl http://localhost:11434/api/generate -d '{
+  "model": "mistral",
+  "prompt": "Why is the sky blue?",
+  "options": {
+    "seed": 123,
+    "temperature": 0
+  }
+}'
+```
+
+##### Response
+
+```json
+{
+  "model": "mistral",
+  "created_at": "2023-11-03T15:36:02.583064Z",
+  "response": " The sky appears blue because of a phenomenon called Rayleigh scattering.",
+  "done": true,
+  "total_duration": 8493852375,
+  "load_duration": 6589624375,
+  "prompt_eval_count": 14,
+  "prompt_eval_duration": 119039000,
+  "eval_count": 110,
+  "eval_duration": 1779061000
+}
+```
+
+#### Generate request (With options)
 
 If you want to set custom options for the model at runtime rather than in the Modelfile, you can do so with the `options` parameter. This example sets every available option, but you can set any of them individually and omit the ones you do not want to override.
 
+##### Request
+
 ```shell
 curl http://localhost:11434/api/generate -d '{
   "model": "llama2",
@@ -249,42 +311,318 @@ curl http://localhost:11434/api/generate -d '{
     "penalize_newline": true,
     "stop": ["\n", "user:"],
     "numa": false,
-    "num_ctx": 4,
+    "num_ctx": 1024,
     "num_batch": 2,
     "num_gqa": 1,
     "num_gpu": 1,
     "main_gpu": 0,
     "low_vram": false,
     "f16_kv": true,
-    "logits_all": false,
     "vocab_only": false,
     "use_mmap": true,
     "use_mlock": false,
-    "embedding_only": false,
     "rope_frequency_base": 1.1,
     "rope_frequency_scale": 0.8,
     "num_thread": 8
-    }
+  }
 }'
 ```
 
-#### Response
+##### Response
 
 ```json
 {
   "model": "llama2",
   "created_at": "2023-08-04T19:22:45.499127Z",
   "response": "The sky is blue because it is the color of the sky.",
-  "context": [1, 2, 3],
   "done": true,
-  "total_duration": 5589157167,
-  "load_duration": 3013701500,
-  "sample_count": 114,
-  "sample_duration": 81442000,
-  "prompt_eval_count": 46,
-  "prompt_eval_duration": 1160282000,
-  "eval_count": 13,
-  "eval_duration": 1325948000
+  "context": [1, 2, 3],
+  "total_duration": 4935886791,
+  "load_duration": 534986708,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 107345000,
+  "eval_count": 237,
+  "eval_duration": 4289432000
+}
+```
+
+#### Load a model
+
+If an empty prompt is provided, the model will be loaded into memory.
+
+##### Request
+
+```shell
+curl http://localhost:11434/api/generate -d '{
+  "model": "llama2"
+}'
+```
+
+##### Response
+
+A single JSON object is returned:
+
+```json
+{
+  "model": "llama2",
+  "created_at": "2023-12-18T19:52:07.071755Z",
+  "response": "",
+  "done": true
+}
+```
+
+## Generate a chat completion
+
+```shell
+POST /api/chat
+```
+
+Generate the next message in a chat with a provided model. This is a streaming endpoint, so there will be a series of responses. Streaming can be disabled using `"stream": false`. The final response object will include statistics and additional data from the request.
+
+### Parameters
+
+- `model`: (required) the [model name](#model-names)
+- `messages`: the messages of the chat, this can be used to keep a chat memory
+
+The `message` object has the following fields:
+
+- `role`: the role of the message, either `system`, `user` or `assistant`
+- `content`: the content of the message
+- `images` (optional): a list of images to include in the message (for multimodal models such as `llava`)
+
+Advanced parameters (optional):
+
+- `format`: the format to return a response in. Currently the only accepted value is `json`
+- `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
+- `template`: the prompt template to use (overrides what is defined in the `Modelfile`)
+- `stream`: if `false` the response will be returned as a single response object, rather than a stream of objects
+- `keep_alive`: controls how long the model will stay loaded into memory following the request (default: `5m`)
+
+### Examples
+
+#### Chat Request (Streaming)
+
+##### Request
+
+Send a chat message with a streaming response.
+
+```shell
+curl http://localhost:11434/api/chat -d '{
+  "model": "llama2",
+  "messages": [
+    {
+      "role": "user",
+      "content": "why is the sky blue?"
+    }
+  ]
+}'
+```
+
+##### Response
+
+A stream of JSON objects is returned:
+
+```json
+{
+  "model": "llama2",
+  "created_at": "2023-08-04T08:52:19.385406455-07:00",
+  "message": {
+    "role": "assistant",
+    "content": "The",
+    "images": null
+  },
+  "done": false
+}
+```
+
+Final response:
+
+```json
+{
+  "model": "llama2",
+  "created_at": "2023-08-04T19:22:45.499127Z",
+  "done": true,
+  "total_duration": 4883583458,
+  "load_duration": 1334875,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 342546000,
+  "eval_count": 282,
+  "eval_duration": 4535599000
+}
+```
+
+#### Chat request (No streaming)
+
+##### Request
+
+```shell
+curl http://localhost:11434/api/chat -d '{
+  "model": "llama2",
+  "messages": [
+    {
+      "role": "user",
+      "content": "why is the sky blue?"
+    }
+  ],
+  "stream": false
+}'
+```
+
+##### Response
+
+```json
+{
+  "model": "registry.ollama.ai/library/llama2:latest",
+  "created_at": "2023-12-12T14:13:43.416799Z",
+  "message": {
+    "role": "assistant",
+    "content": "Hello! How are you today?"
+  },
+  "done": true,
+  "total_duration": 5191566416,
+  "load_duration": 2154458,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 383809000,
+  "eval_count": 298,
+  "eval_duration": 4799921000
+}
+```
+
+#### Chat request (With History)
+
+Send a chat message with a conversation history. You can use this same approach to start the conversation using multi-shot or chain-of-thought prompting.
+
+##### Request
+
+```shell
+curl http://localhost:11434/api/chat -d '{
+  "model": "llama2",
+  "messages": [
+    {
+      "role": "user",
+      "content": "why is the sky blue?"
+    },
+    {
+      "role": "assistant",
+      "content": "due to rayleigh scattering."
+    },
+    {
+      "role": "user",
+      "content": "how is that different than mie scattering?"
+    }
+  ]
+}'
+```
+
+##### Response
+
+A stream of JSON objects is returned:
+
+```json
+{
+  "model": "llama2",
+  "created_at": "2023-08-04T08:52:19.385406455-07:00",
+  "message": {
+    "role": "assistant",
+    "content": "The"
+  },
+  "done": false
+}
+```
+
+Final response:
+
+```json
+{
+  "model": "llama2",
+  "created_at": "2023-08-04T19:22:45.499127Z",
+  "done": true,
+  "total_duration": 8113331500,
+  "load_duration": 6396458,
+  "prompt_eval_count": 61,
+  "prompt_eval_duration": 398801000,
+  "eval_count": 468,
+  "eval_duration": 7701267000
+}
+```
+
+#### Chat request (with images)
+
+##### Request
+
+Send a chat message with a conversation history.
+
+```shell
+curl http://localhost:11434/api/chat -d '{
+  "model": "llava",
+  "messages": [
+    {
+      "role": "user",
+      "content": "what is in this image?",
+      "images": ["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"]
+    }
+  ]
+}'
+```
+
+##### Response
+
+```json
+{
+  "model": "llava",
+  "created_at": "2023-12-13T22:42:50.203334Z",
+  "message": {
+    "role": "assistant",
+    "content": " The image features a cute, little pig with an angry facial expression. It's wearing a heart on its shirt and is waving in the air. This scene appears to be part of a drawing or sketching project.",
+    "images": null
+  },
+  "done": true,
+  "total_duration": 1668506709,
+  "load_duration": 1986209,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 359682000,
+  "eval_count": 83,
+  "eval_duration": 1303285000
+}
+```
+
+#### Chat request (Reproducible outputs)
+
+##### Request
+
+```shell
+curl http://localhost:11434/api/chat -d '{
+  "model": "llama2",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Hello!"
+    }
+  ],
+  "options": {
+    "seed": 101,
+    "temperature": 0
+  }
+}'
+```
+
+##### Response
+
+```json
+{
+  "model": "registry.ollama.ai/library/llama2:latest",
+  "created_at": "2023-12-12T14:13:43.416799Z",
+  "message": {
+    "role": "assistant",
+    "content": "Hello! How are you today?"
+  },
+  "done": true,
+  "total_duration": 5191566416,
+  "load_duration": 2154458,
+  "prompt_eval_count": 26,
+  "prompt_eval_duration": 383809000,
+  "eval_count": 298,
+  "eval_duration": 4799921000
 }
 ```
 
@@ -294,7 +632,7 @@ curl http://localhost:11434/api/generate -d '{
 POST /api/create
 ```
 
-Create a model from a [`Modelfile`](./modelfile.md). It is recommended to set `modelfile` to the content of the Modelfile rather than just set `path`. This is a requirement for remote create. Remote model creation should also create any file blobs, fields such as `FROM` and `ADAPTER`, explicitly with the server using [Create a Blob](#create-a-blob) and the value to the path indicated in the response.
+Create a model from a [`Modelfile`](./modelfile.md). It is recommended to set `modelfile` to the content of the Modelfile rather than just set `path`. This is a requirement for remote create. Remote model creation must also create any file blobs, fields such as `FROM` and `ADAPTER`, explicitly with the server using [Create a Blob](#create-a-blob) and the value to the path indicated in the response.
 
 ### Parameters
 
@@ -305,7 +643,11 @@ Create a model from a [`Modelfile`](./modelfile.md). It is recommended to set `m
 
 ### Examples
 
-#### Request
+#### Create a new model
+
+Create a new model from a `Modelfile`.
+
+##### Request
 
 ```shell
 curl http://localhost:11434/api/create -d '{
@@ -314,14 +656,22 @@ curl http://localhost:11434/api/create -d '{
 }'
 ```
 
-#### Response
+##### Response
 
-A stream of JSON objects. When finished, `status` is `success`.
+A stream of JSON objects. Notice that the final JSON object shows a `"status": "success"`.
 
 ```json
-{
-  "status": "parsing modelfile"
-}
+{"status":"reading model metadata"}
+{"status":"creating system layer"}
+{"status":"using already created layer sha256:22f7f8ef5f4c791c1b03d7eb414399294764d7cc82c7e94aa81a1feb80a983a2"}
+{"status":"using already created layer sha256:8c17c2ebb0ea011be9981cc3922db8ca8fa61e828c5d3f44cb6ae342bf80460b"}
+{"status":"using already created layer sha256:7c23fb36d80141c4ab8cdbb61ee4790102ebd2bf7aeff414453177d4f2110e5d"}
+{"status":"using already created layer sha256:2e0493f67d0c8c9c68a8aeacdf6a38a2151cb3c4c1d42accf296e19810527988"}
+{"status":"using already created layer sha256:2759286baa875dc22de5394b4a925701b1896a7e3f8e53275c36f75a877a82c9"}
+{"status":"writing layer sha256:df30045fe90f0d750db82a058109cecd6d4de9c90a3d75b19c09e5f64580bb42"}
+{"status":"writing layer sha256:f18a68eb09bf925bb1b669490407c1b1251c5db98dc4d3d81f3088498ea55690"}
+{"status":"writing manifest"}
+{"status":"success"}
 ```
 
 ### Check if a Blob Exists
@@ -330,7 +680,7 @@ A stream of JSON objects. When finished, `status` is `success`.
 HEAD /api/blobs/:digest
 ```
 
-Check if a blob is known to the server.
+Ensures that the file blob used for a FROM or ADAPTER field exists on the server. This is checking your Ollama server and not Ollama.ai.
 
 #### Query Parameters
 
@@ -354,7 +704,7 @@ Return 200 OK if the blob exists, 404 Not Found if it does not.
 POST /api/blobs/:digest
 ```
 
-Create a blob from a file. Returns the server file path.
+Create a blob from a file on the server. Returns the server file path.
 
 #### Query Parameters
 
@@ -370,7 +720,7 @@ curl -T model.bin -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf08
 
 ##### Response
 
-Return 201 Created if the blob was successfully created.
+Return 201 Created if the blob was successfully created, 400 Bad Request if the digest used is not expected.
 
 ## List Local Models
 
@@ -396,14 +746,30 @@ A single JSON object will be returned.
 {
   "models": [
     {
-      "name": "llama2",
-      "modified_at": "2023-08-02T17:02:23.713454393-07:00",
-      "size": 3791730596
+      "name": "codellama:13b",
+      "modified_at": "2023-11-04T14:56:49.277302595-07:00",
+      "size": 7365960935,
+      "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697",
+      "details": {
+        "format": "gguf",
+        "family": "llama",
+        "families": null,
+        "parameter_size": "13B",
+        "quantization_level": "Q4_0"
+      }
     },
     {
-      "name": "llama2:13b",
-      "modified_at": "2023-08-08T12:08:38.093596297-07:00",
-      "size": 7323310500
+      "name": "llama2:latest",
+      "modified_at": "2023-12-07T09:32:18.757212583-08:00",
+      "size": 3825819519,
+      "digest": "fe938a131f40e6f6d40083c9f0f430a515233eb2edaa6d72eb85c50d64f2300e",
+      "details": {
+        "format": "gguf",
+        "family": "llama",
+        "families": null,
+        "parameter_size": "7B",
+        "quantization_level": "Q4_0"
+      }
     }
   ]
 }
@@ -415,7 +781,7 @@ A single JSON object will be returned.
 POST /api/show
 ```
 
-Show details about a model including modelfile, template, parameters, license, and system prompt.
+Show information about a model including details, modelfile, template, parameters, license, and system prompt.
 
 ### Parameters
 
@@ -435,10 +801,16 @@ curl http://localhost:11434/api/show -d '{
 
 ```json
 {
-  "license": "<contents of license block>",
-  "modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llama2:latest\n\nFROM /Users/username/.ollama/models/blobs/sha256:8daa9615cce30c259a9555b1cc250d461d1bc69980a274b44d7eda0be78076d8\nTEMPLATE \"\"\"[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>\n\n{{ end }}{{ .Prompt }} [/INST] \"\"\"\nSYSTEM \"\"\"\"\"\"\nPARAMETER stop [INST]\nPARAMETER stop [/INST]\nPARAMETER stop <<SYS>>\nPARAMETER stop <</SYS>>\n",
-  "parameters": "stop                           [INST]\nstop                           [/INST]\nstop                           <<SYS>>\nstop                           <</SYS>>",
-  "template": "[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>\n\n{{ end }}{{ .Prompt }} [/INST] "
+  "modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llava:latest\n\nFROM /Users/matt/.ollama/models/blobs/sha256:200765e1283640ffbd013184bf496e261032fa75b99498a9613be4e94d63ad52\nTEMPLATE \"\"\"{{ .System }}\nUSER: {{ .Prompt }}\nASSSISTANT: \"\"\"\nPARAMETER num_ctx 4096\nPARAMETER stop \"\u003c/s\u003e\"\nPARAMETER stop \"USER:\"\nPARAMETER stop \"ASSSISTANT:\"",
+  "parameters": "num_ctx                        4096\nstop                           \u003c/s\u003e\nstop                           USER:\nstop                           ASSSISTANT:",
+  "template": "{{ .System }}\nUSER: {{ .Prompt }}\nASSSISTANT: ",
+  "details": {
+    "format": "gguf",
+    "family": "llama",
+    "families": ["llama", "clip"],
+    "parameter_size": "7B",
+    "quantization_level": "Q4_0"
+  }
 }
 ```
 
@@ -463,7 +835,7 @@ curl http://localhost:11434/api/copy -d '{
 
 #### Response
 
-The only response is a 200 OK if successful.
+Returns a 200 OK if successful, or a 404 Not Found if the source model doesn't exist.
 
 ## Delete a Model
 
@@ -489,7 +861,7 @@ curl -X DELETE http://localhost:11434/api/delete -d '{
 
 #### Response
 
-If successful, the only response is a 200 OK.
+Returns a 200 OK if successful, 404 Not Found if the model to be deleted doesn't exist.
 
 ## Pull a Model
 
@@ -644,6 +1016,7 @@ Generate embeddings from a model
 Advanced parameters:
 
 - `options`: additional model parameters listed in the documentation for the [Modelfile](./modelfile.md#valid-parameters-and-values) such as `temperature`
+- `keep_alive`: controls how long the model will stay loaded into memory following the request (default: `5m`)
 
 ### Examples
 
@@ -651,7 +1024,7 @@ Advanced parameters:
 
 ```shell
 curl http://localhost:11434/api/embeddings -d '{
-  "model": "llama2",
+  "model": "all-minilm",
   "prompt": "Here is an article about llamas..."
 }'
 ```

docs/development.md

@@ -1,20 +1,26 @@
 # 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 1.20 or higher
+- go version 1.22 or higher
 - gcc version 11.4.0 or higher
 
 ```bash
 brew install go cmake gcc
 ```
 
-Get the required libraries:
+Optionally enable debugging and more verbose logging:
+
+```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 ./...
@@ -32,8 +38,107 @@ Now you can run `ollama`:
 ./ollama
 ```
 
-## Building on Linux with GPU support
+### Linux
 
-- Install cmake and nvidia-cuda-toolkit
-- run `go generate ./...`
-- run `go build .`
+#### 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. You can customize
+set set of target CUDA architectues by setting `CMAKE_CUDA_ARCHITECTURES` (e.g. "50;60;70")
+
+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) development 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`). You can also customize
+the AMD GPU targets by setting AMDGPU_TARGETS (e.g. `AMDGPU_TARGETS="gfx1101;gfx1102"`)
+
+```
+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 - You must build from a "Developer Shell" with the environment variables set
+- go version 1.22 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 CUDA **AFTER** you install MSVC.
+
+- [NVIDIA CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html)
+
+
+#### Windows ROCm (AMD Radeon)
+
+In addition to the common Windows development tools described above, install AMDs HIP package **AFTER** you install MSVC
+
+- [AMD HIP](https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html)

docs/faq.md

@@ -1,138 +1,135 @@
 # FAQ
 
+## How can I upgrade Ollama?
+
+Ollama on macOS and Windows will automatically download updates. Click on the taskbar or menubar item and then click "Restart to update" to apply the update. Updates can also be installed by downloading the latest version [manually](https://ollama.com/download/).
+
+On Linux, re-run the install script:
+
+```
+curl -fsSL https://ollama.com/install.sh | sh
+```
+
 ## How can I view the logs?
 
-On macOS:
+Review the [Troubleshooting](./troubleshooting.md) docs for more about using logs.
+
+## How can I specify the context window size?
+
+By default, Ollama uses a context window size of 2048 tokens.
+
+To change this when using `ollama run`, use `/set parameter`:
 
 ```
-cat ~/.ollama/logs/server.log
+/set parameter num_ctx 4096
 ```
 
-On Linux:
+When using the API, specify the `num_ctx` parameter:
 
 ```
-journalctl -u ollama
+curl http://localhost:11434/api/generate -d '{
+  "model": "llama2",
+  "prompt": "Why is the sky blue?",
+  "options": {
+    "num_ctx": 4096
+  }
+}'
 ```
 
-If you're running `ollama serve` directly, the logs will be printed to the console.
+## How do I configure Ollama server?
+
+Ollama server can be configured with environment variables.
+
+### Setting environment variables on Mac
+
+If Ollama is run as a macOS application, environment variables should be set using `launchctl`:
+
+1. For each environment variable, call `launchctl setenv`.
+
+    ```bash
+    launchctl setenv OLLAMA_HOST "0.0.0.0"
+    ```
+
+2. Restart Ollama application.
+
+### Setting environment variables on Linux
+
+If Ollama is run as a systemd service, environment variables should be set using `systemctl`:
+
+1. Edit the systemd service by calling `systemctl edit ollama.service`. This will open an editor.
+
+2. For each environment variable, add a line `Environment` under section `[Service]`:
+
+    ```ini
+    [Service]
+    Environment="OLLAMA_HOST=0.0.0.0"
+    ```
+
+3. Save and exit.
+
+4. Reload `systemd` and restart Ollama:
+
+   ```bash
+   systemctl daemon-reload
+   systemctl restart ollama
+   ```
+
+### Setting environment variables on Windows
+
+On windows, Ollama inherits your user and system environment variables.
+
+1. First Quit Ollama by clicking on it in the task bar
+
+2. Edit system environment variables from the control panel
+
+3. Edit or create New variable(s) for your user account for `OLLAMA_HOST`, `OLLAMA_MODELS`, etc.
+
+4. Click OK/Apply to save 
+
+5. Run `ollama` from a new terminal window 
+
 
 ## 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.
+Ollama binds 127.0.0.1 port 11434 by default. Change the bind address with the `OLLAMA_HOST` environment variable.
 
-On macOS:
-
-```bash
-OLLAMA_HOST=0.0.0.0:11434 ollama serve
-```
-
-On Linux:
-
-Create a `systemd` drop-in directory and set `Environment=OLLAMA_HOST`
-
-```bash
-mkdir -p /etc/systemd/system/ollama.service.d
-echo '[Service]' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-```bash
-echo 'Environment="OLLAMA_HOST=0.0.0.0:11434"' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-Reload `systemd` and restart Ollama:
-
-```bash
-systemctl daemon-reload
-systemctl restart ollama
-```
+Refer to the section [above](#how-do-i-configure-ollama-server) for how to set 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:
+Ollama allows cross-origin requests from `127.0.0.1` and `0.0.0.0` by default. Additional origins can be configured with `OLLAMA_ORIGINS`.
 
-On macOS:
-
-```bash
-OLLAMA_ORIGINS=http://192.168.1.1:*,https://example.com ollama serve
-```
-
-On Linux:
-
-```bash
-echo 'Environment="OLLAMA_ORIGINS=http://192.168.1.1:*,https://example.com"' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-Reload `systemd` and restart Ollama:
-
-```bash
-systemctl daemon-reload
-systemctl restart ollama
-```
+Refer to the section [above](#how-do-i-configure-ollama-server) for how to set environment variables on your platform.
 
 ## Where are models stored?
 
-- macOS: Raw model data is stored under `~/.ollama/models`.
-- Linux: Raw model data is stored under `/usr/share/ollama/.ollama/models`
+- macOS: `~/.ollama/models`
+- Linux: `/usr/share/ollama/.ollama/models`
+- Windows: `C:\Users\<username>\.ollama\models`
 
-Below the models directory you will find a structure similar to the following:
+### How do I set them to a different location?
 
-```shell
-.
-├── blobs
-└── manifests
-   └── registry.ollama.ai
-      ├── f0rodo
-      ├── library
-      ├── mattw
-      └── saikatkumardey
-```
+If a different directory needs to be used, set the environment variable `OLLAMA_MODELS` to the chosen directory.
 
-There is a `manifests/registry.ollama.ai/namespace` path. In example above, the user has downloaded models from the official `library`, `f0rodo`, `mattw`, and `saikatkumardey` namespaces. Within each of those directories, you will find directories for each of the models downloaded. And in there you will find a file name representing each tag. Each tag file is the manifest for the model.  
+Refer to the section [above](#how-do-i-configure-ollama-server) for how to set environment variables on your platform.
 
-The manifest lists all the layers used in this model. You will see a `media type` for each layer, along with a digest. That digest corresponds with a file in the `models/blobs directory`.
+## Does Ollama send my prompts and answers back to ollama.com?
 
-### How can I change where Ollama stores models?
-
-To modify where models are stored, you can use the `OLLAMA_MODELS` environment variable. Note that on Linux this means defining `OLLAMA_MODELS` in a drop-in `/etc/systemd/system/ollama.service.d` service file, reloading systemd, and restarting the ollama service.
-
-## Does Ollama send my prompts and answers back to Ollama.ai to use in any way?
-
-No. Anything you do with Ollama, such as generate a response from the model, stays with you. We don't collect any data about how you use the model. You are always in control of your own data.
+No. Ollama runs locally, and conversation data does not 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. You can see the list of [extensions & plugins](https://github.com/jmorganca/ollama#extensions--plugins) at the bottom of the main repository readme.
+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.
-
-On macOS:
-
-```bash
-HTTPS_PROXY=http://proxy.example.com ollama serve
-```
-
-On Linux:
-
-```bash
-echo 'Environment="HTTPS_PROXY=https://proxy.example.com"' >>/etc/systemd/system/ollama.service.d/environment.conf
-```
-
-Reload `systemd` and restart Ollama:
-
-```bash
-systemctl daemon-reload
-systemctl restart ollama
-```
+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, 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).
+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.
 
@@ -154,3 +151,55 @@ docker run -d -e HTTPS_PROXY=https://my.proxy.example.com -p 11434:11434 ollama-
 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.
+
+## How can I pre-load a model to get faster response times?
+
+If you are using the API you can preload a model by sending the Ollama server an empty request. This works with both the `/api/generate` and `/api/chat` API endpoints.
+
+To preload the mistral model using the generate endpoint, use:
+```shell
+curl http://localhost:11434/api/generate -d '{"model": "mistral"}'
+```
+
+To use the chat completions endpoint, use:
+```shell
+curl http://localhost:11434/api/chat -d '{"model": "mistral"}'
+```
+
+## How do I keep a model loaded in memory or make it unload immediately?
+
+By default models are kept in memory for 5 minutes before being unloaded. This allows for quicker response times if you are making numerous requests to the LLM. You may, however, want to free up the memory before the 5 minutes have elapsed or keep the model loaded indefinitely. Use the `keep_alive` parameter with either the `/api/generate` and `/api/chat` API endpoints to control how long the model is left in memory.
+
+The `keep_alive` parameter can be set to:
+* a duration string (such as "10m" or "24h")
+* a number in seconds (such as 3600)
+* any negative number which will keep the model loaded in memory (e.g. -1 or "-1m")
+* '0' which will unload the model immediately after generating a response
+
+For example, to preload a model and leave it in memory use:
+```shell
+curl http://localhost:11434/api/generate -d '{"model": "llama2", "keep_alive": -1}'
+```
+
+To unload the model and free up memory use:
+```shell
+curl http://localhost:11434/api/generate -d '{"model": "llama2", "keep_alive": 0}'
+```
+
+## Controlling which GPUs to use
+
+By default, on Linux and Windows, Ollama will attempt to use Nvidia GPUs, or
+Radeon GPUs, and will use all the GPUs it can find. You can limit which GPUs
+will be utilized by setting the environment variable `CUDA_VISIBLE_DEVICES` for
+NVIDIA cards, or `HIP_VISIBLE_DEVICES` for Radeon GPUs to a comma delimited list
+of GPU IDs.  You can see the list of devices with GPU tools such as `nvidia-smi` or
+`rocminfo`. You can set to an invalid GPU ID (e.g., "-1") to bypass the GPU and
+fallback to CPU.

docs/import.md

@@ -15,7 +15,7 @@ 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
+FROM ./mistral-7b-v0.1.Q4_0.gguf
 TEMPLATE "[INST] {{ .Prompt }} [/INST]"
 ```
 
@@ -37,56 +37,69 @@ ollama run example "What is your favourite condiment?"
 
 ## Importing (PyTorch & Safetensors)
 
-### Supported models
+> Importing from PyTorch and Safetensors is a longer process than importing from GGUF. Improvements that make it easier are a work in progress.
 
-Ollama supports a set of model architectures, with support for more coming soon:
+### Setup
 
-- Llama & Mistral
-- Falcon & RW
-- GPT-NeoX
-- BigCode
+First, clone the `ollama/ollama` repo:
 
-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`).
+```
+git clone git@github.com:ollama/ollama.git ollama
+cd ollama
+```
 
-### Step 1: Clone the HuggingFace repository (optional)
+and then fetch its `llama.cpp` submodule:
+
+```shell
+git submodule init
+git submodule update llm/llama.cpp
+```
+
+Next, install the Python dependencies:
+
+```
+python3 -m venv llm/llama.cpp/.venv
+source llm/llama.cpp/.venv/bin/activate
+pip install -r llm/llama.cpp/requirements.txt
+```
+
+Then build the `quantize` tool:
+
+```
+make -C llm/llama.cpp quantize
+```
+
+### Clone the HuggingFace repository (optional)
 
 If the model is currently hosted in a HuggingFace repository, first clone that repository to download the raw model.
 
+Install [Git LFS](https://docs.github.com/en/repositories/working-with-files/managing-large-files/installing-git-large-file-storage), verify it's installed, and then clone the model's repository:
+
 ```
 git lfs install
-git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
-cd Mistral-7B-Instruct-v0.1
+git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 model
 ```
 
-### Step 2: Convert and quantize to a `.bin` file (optional, for PyTorch and Safetensors)
+### Convert the model
 
-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:
+> Note: some model architectures require using specific convert scripts. For example, Qwen models require running `convert-hf-to-gguf.py` instead of `convert.py`
 
 ```
-docker run --rm -v .:/model ollama/quantize -q q4_0 /model
+python llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin
 ```
 
-This will output two files into the directory:
+### Quantize the model
 
-- `f16.bin`: the model converted to GGUF
-- `q4_0.bin` the model quantized to a 4-bit quantization (we will use this file to create the Ollama model)
+```
+llm/llama.cpp/quantize converted.bin quantized.bin q4_0
+```
 
 ### 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
+FROM quantized.bin
 TEMPLATE "[INST] {{ .Prompt }} [/INST]"
 ```
 
@@ -110,9 +123,12 @@ ollama run example "What is your favourite condiment?"
 
 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)
+1. Create [an account](https://ollama.com/signup)
+2. Copy your Ollama public key:
+  - macOS: `cat ~/.ollama/id_ed25519.pub`
+  - Windows: `type %USERPROFILE%\.ollama\id_ed25519.pub`
+  - Linux: `cat /usr/share/ollama/.ollama/id_ed25519.pub`
+3. Add your public key to your [Ollama account](https://ollama.com/settings/keys)
 
 Next, copy your model to your username's namespace:
 
@@ -126,7 +142,7 @@ Then push the model:
 ollama push <your username>/example
 ```
 
-After publishing, your model will be available at `https://ollama.ai/<your username>/example`.
+After publishing, your model will be available at `https://ollama.com/<your username>/example`.
 
 ## Quantization reference
 
@@ -149,50 +165,4 @@ The quantization options are as follow (from highest highest to lowest levels of
 - `q5_K_M`
 - `q6_K`
 - `q8_0`
-
-## 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>
-
-# GPTNeoXForCausalLM
-python convert-gptneox-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
-```
+- `f16`

docs/linux.md

@@ -3,11 +3,21 @@
 ## Install
 
 Install Ollama running this one-liner:
+
 >
+
 ```bash
-curl https://ollama.ai/install.sh | sh
+curl -fsSL https://ollama.com/install.sh | sh
 ```
 
+## AMD Radeon GPU support
+
+While AMD has contributed the `amdgpu` driver upstream to the official linux
+kernel source, the version is older and may not support all ROCm features. We
+recommend you install the latest driver from
+https://www.amd.com/en/support/linux-drivers for best support of your Radeon
+GPU.
+
 ## Manual install
 
 ### Download the `ollama` binary
@@ -15,7 +25,7 @@ curl https://ollama.ai/install.sh | sh
 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 curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama
 sudo chmod +x /usr/bin/ollama
 ```
 
@@ -62,6 +72,11 @@ Verify that the drivers are installed by running the following command, which sh
 nvidia-smi
 ```
 
+### Install ROCm (optional - for Radeon GPUs)
+[Download and Install](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html)
+
+Make sure to install ROCm v6
+
 ### Start Ollama
 
 Start Ollama using `systemd`:
@@ -75,13 +90,13 @@ sudo systemctl start ollama
 Update ollama by running the install script again:
 
 ```bash
-curl https://ollama.ai/install.sh | sh
+curl -fsSL https://ollama.com/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 curl -L https://ollama.com/download/ollama-linux-amd64 -o /usr/bin/ollama
 sudo chmod +x /usr/bin/ollama
 ```
 
@@ -109,8 +124,10 @@ Remove the ollama binary from your bin directory (either `/usr/local/bin`, `/usr
 sudo rm $(which ollama)
 ```
 
-Remove the downloaded models and Ollama service user:
+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: this `Modelfile` syntax is in development
+> Note: `Modelfile` syntax is in development
 
 A model file is the blueprint to create and share models with Ollama.
 
@@ -19,6 +19,7 @@ A model file is the blueprint to create and share models with Ollama.
   - [SYSTEM](#system)
   - [ADAPTER](#adapter)
   - [LICENSE](#license)
+  - [MESSAGE](#message)
 - [Notes](#notes)
 
 ## Format
@@ -30,14 +31,15 @@ The format of the `Modelfile`:
 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 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.                                  |
+| 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.                                   |
+| [`MESSAGE`](#message)               | Specify message history.                                       |
 
 ## Examples
 
@@ -52,7 +54,7 @@ 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 prompt to specify the behavior of the chat assistant
+# sets a custom system message to specify the behavior of the chat assistant
 SYSTEM You are Mario from super mario bros, acting as an assistant.
 ```
 
@@ -65,17 +67,17 @@ To use this:
 
 More examples are available in the [examples directory](../examples).
 
-### `Modelfile`s in [ollama.ai/library][1]
+### `Modelfile`s in [ollama.com/library][1]
 
-There are two ways to view `Modelfile`s underlying the models in [ollama.ai/library][1]:
+There are two ways to view `Modelfile`s underlying the models in [ollama.com/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"
+  1.  Go to a particular model's tags (e.g. https://ollama.com/library/llama2/tags)
+  2.  Click on a tag (e.g. https://ollama.com/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` like so:
+- Option 2: use `ollama show` to print the `Modelfile` for any local models like so:
 
   ```bash
   > ollama show --modelfile llama2:13b
@@ -84,7 +86,7 @@ There are two ways to view `Modelfile`s underlying the models in [ollama.ai/libr
   # FROM llama2:13b
 
   FROM /root/.ollama/models/blobs/sha256:123abc
-  TEMPLATE """[INST] {{ if and .First .System }}<<SYS>>{{ .System }}<</SYS>>
+  TEMPLATE """[INST] {{ if .System }}<<SYS>>{{ .System }}<</SYS>>
 
   {{ end }}{{ .Prompt }} [/INST] """
   SYSTEM """"""
@@ -129,7 +131,7 @@ The `PARAMETER` instruction defines a parameter that can be set when the model i
 PARAMETER <parameter> <parametervalue>
 ```
 
-### Valid Parameters and Values
+#### Valid Parameters and Values
 
 | Parameter      | Description                                                                                                                                                                                                                                             | Value Type | Example Usage        |
 | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------------- |
@@ -152,35 +154,28 @@ PARAMETER <parameter> <parametervalue>
 
 ### TEMPLATE
 
-`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. 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 message, a user's message and the response from the model. Note: syntax may be model specific. Templates use Go [template syntax](https://pkg.go.dev/text/template).
 
 #### Template Variables
 
-| 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.          |
+| Variable          | Description                                                                                   |
+| ----------------- | --------------------------------------------------------------------------------------------- |
+| `{{ .System }}`   | The system message used to specify custom behavior.                                           |
+| `{{ .Prompt }}`   | The user prompt message.                                                                      |
+| `{{ .Response }}` | The response from the model. When generating a response, text after this variable is omitted. |
 
-```modelfile
-TEMPLATE """
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
-
-### User:
-{{ .Prompt }}
-
-### Response:
+```
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
 """
-
-SYSTEM """<system message>"""
 ```
 
 ### SYSTEM
 
-The `SYSTEM` instruction specifies the system prompt to be used in the template, if applicable.
+The `SYSTEM` instruction specifies the system message to be used in the template, if applicable.
 
 ```modelfile
 SYSTEM """<system message>"""
@@ -204,9 +199,38 @@ LICENSE """
 """
 ```
 
+### MESSAGE
+
+The `MESSAGE` instruction allows you to specify a message history for the model to use when responding. Use multiple iterations of the MESSAGE command to build up a conversation which will guide the model to answer in a similar way.
+
+```modelfile
+MESSAGE <role> <message>
+```
+
+#### Valid roles
+
+| Role      | Description                                                  |
+| --------- | ------------------------------------------------------------ |
+| system    | Alternate way of providing the SYSTEM message for the model. |
+| user      | An example message of what the user could have asked.        |
+| assistant | An example message of how the model should respond.          |
+
+
+#### Example conversation
+
+```modelfile
+MESSAGE user Is Toronto in Canada?
+MESSAGE assistant yes
+MESSAGE user Is Sacramento in Canada?
+MESSAGE assistant no
+MESSAGE user Is Ontario in Canada?
+MESSAGE assistant yes
+```
+
+
 ## Notes
 
-- 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.
+- 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
+[1]: https://ollama.com/library

docs/openai.md

@@ -0,0 +1,141 @@
+# OpenAI compatibility
+
+> **Note:** OpenAI compatibility is experimental and is subject to major adjustments including breaking changes. For fully-featured access to the Ollama API, see the Ollama [Python library](https://github.com/ollama/ollama-python), [JavaScript library](https://github.com/ollama/ollama-js) and [REST API](https://github.com/jmorganca/ollama/blob/main/docs/api.md).
+
+Ollama provides experimental compatibility with parts of the [OpenAI API](https://platform.openai.com/docs/api-reference) to help connect existing applications to Ollama.
+
+## Usage
+
+### OpenAI Python library
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url='http://localhost:11434/v1/',
+
+    # required but ignored
+    api_key='ollama',
+)
+
+chat_completion = client.chat.completions.create(
+    messages=[
+        {
+            'role': 'user',
+            'content': 'Say this is a test',
+        }
+    ],
+    model='llama2',
+)
+```
+
+### OpenAI JavaScript library
+
+```javascript
+import OpenAI from 'openai'
+
+const openai = new OpenAI({
+  baseURL: 'http://localhost:11434/v1/',
+
+  // required but ignored
+  apiKey: 'ollama',
+})
+
+const chatCompletion = await openai.chat.completions.create({
+  messages: [{ role: 'user', content: 'Say this is a test' }],
+  model: 'llama2',
+})
+```
+
+### `curl`
+
+```
+curl http://localhost:11434/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "llama2",
+        "messages": [
+            {
+                "role": "system",
+                "content": "You are a helpful assistant."
+            },
+            {
+                "role": "user",
+                "content": "Hello!"
+            }
+        ]
+    }'
+```
+
+## Endpoints
+
+### `/v1/chat/completions`
+
+#### Supported features
+
+- [x] Chat completions
+- [x] Streaming
+- [x] JSON mode
+- [x] Reproducible outputs
+- [ ] Vision
+- [ ] Function calling
+- [ ] Logprobs
+
+#### Supported request fields
+
+- [x] `model`
+- [x] `messages`
+  - [x] Text `content`
+  - [ ] Array of `content` parts
+- [x] `frequency_penalty`
+- [x] `presence_penalty`
+- [x] `response_format`
+- [x] `seed`
+- [x] `stop`
+- [x] `stream`
+- [x] `temperature`
+- [x] `top_p`
+- [x] `max_tokens`
+- [ ] `logit_bias`
+- [ ] `tools`
+- [ ] `tool_choice`
+- [ ] `user`
+- [ ] `n`
+
+#### Notes
+
+- Setting `seed` will always set `temperature` to `0`
+- `finish_reason` will always be `stop`
+- `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached
+
+## Models
+
+Before using a model, pull it locally `ollama pull`:
+
+```shell
+ollama pull llama2
+```
+
+### Default model names
+
+For tooling that relies on default OpenAI model names such as `gpt-3.5-turbo`, use `ollama cp` to copy an existing model name to a temporary name:
+
+```
+ollama cp llama2 gpt-3.5-turbo
+```
+
+Afterwards, this new model name can be specified the `model` field:
+
+```shell
+curl http://localhost:11434/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "gpt-3.5-turbo",
+        "messages": [
+            {
+                "role": "user",
+                "content": "Hello!"
+            }
+        ]
+    }'
+```

docs/troubleshooting.md

@@ -0,0 +1,111 @@
+# 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
+```
+
+When you run Ollama in a **container**, the logs go to stdout/stderr in the container:
+
+```shell
+docker logs <container-name>
+```
+(Use `docker ps` to find the container name)
+
+If manually running `ollama serve` in a terminal, the logs will be on that terminal.
+
+When you run Ollama on **Windows**, there are a few different locations.  You can view them in the explorer window by hitting `<cmd>+R` and type in:
+- `explorer %LOCALAPPDATA%\Ollama` to view logs
+- `explorer %LOCALAPPDATA%\Programs\Ollama` to browse the binaries (The installer adds this to your user PATH)
+- `explorer %HOMEPATH%\.ollama` to browse where models and configuration is stored
+- `explorer %TEMP%` where temporary executable files are stored in one or more `ollama*` directories
+
+To enable additional debug logging to help troubleshoot problems, first **Quit the running app from the tray menu** then in a powershell terminal
+```powershell
+$env:OLLAMA_DEBUG="1"
+& "ollama app.exe"
+```
+
+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
+```
+
+## AMD Radeon GPU Support
+
+Ollama leverages the AMD ROCm library, which does not support all AMD GPUs. In
+some cases you can force the system to try to use a similar LLVM target that is
+close.  For example The Radeon RX 5400 is `gfx1034` (also known as 10.3.4)
+however, ROCm does not currently support this target. The closest support is
+`gfx1030`.  You can use the environment variable `HSA_OVERRIDE_GFX_VERSION` with
+`x.y.z` syntax.  So for example, to force the system to run on the RX 5400, you
+would set `HSA_OVERRIDE_GFX_VERSION="10.3.0"` as an environment variable for the
+server.  If you have an unsupported AMD GPU you can experiment using the list of
+supported types below.
+
+At this time, the known supported GPU types are the following LLVM Targets.
+This table shows some example GPUs that map to these LLVM targets:
+| **LLVM Target** | **An Example GPU** |
+|-----------------|---------------------|
+| gfx900 | Radeon RX Vega 56 |
+| gfx906 | Radeon Instinct MI50 |
+| gfx908 | Radeon Instinct MI100 |
+| gfx90a | Radeon Instinct MI210 |
+| gfx940 | Radeon Instinct MI300 |
+| gfx941 | |
+| gfx942 | |
+| gfx1030 | Radeon PRO V620 |
+| gfx1100 | Radeon PRO W7900 |
+| gfx1101 | Radeon PRO W7700 |
+| gfx1102 | Radeon RX 7600 |
+
+AMD is working on enhancing ROCm v6 to broaden support for families of GPUs in a
+future release which should increase support for more GPUs.
+
+Reach out on [Discord](https://discord.gg/ollama) or file an
+[issue](https://github.com/ollama/ollama/issues) for additional help.
+
+## Installing older versions on Linux
+
+If you run into problems on Linux and want to install an older version you can tell the install script
+which version to install.
+
+```sh
+curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION="0.1.27" sh
+```

docs/tutorials/fly-gpu.md

@@ -0,0 +1,83 @@
+# 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/langchainpy.md

@@ -42,12 +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. We can use Ollama directly to instantiate an embedding model. We will use ChromaDB in this example for a vector database. `pip install chromadb`
 
 ```python
 from langchain.embeddings import OllamaEmbeddings
 from langchain.vectorstores import Chroma
-oembed = OllamaEmbeddings(base_url="http://localhost:11434", model="llama2")
+oembed = OllamaEmbeddings(base_url="http://localhost:11434", model="nomic-embed-text")
 vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed)
 ```
 
@@ -66,7 +66,7 @@ The next thing is to send the question and the relevant parts of the docs to the
 ```python
 from langchain.chains import RetrievalQA
 qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever())
-qachain({"query": question})
+qachain.invoke({"query": question})
 ```
 
 The answer received from this chain was:

docs/tutorials/nvidia-jetson.md

@@ -17,7 +17,7 @@ Prerequisites:
 
 Here are the steps:
 
-- Install Ollama via standard Linux command (ignore the 404 error): `curl https://ollama.ai/install.sh | sh`
+- Install Ollama via standard Linux command (ignore the 404 error): `curl https://ollama.com/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'`

docs/windows.md

@@ -0,0 +1,47 @@
+# Ollama Windows Preview
+
+Welcome to the Ollama Windows preview.
+
+No more WSL required!
+
+Ollama now runs as a native Windows application, including NVIDIA and AMD Radeon GPU support.
+After installing Ollama Windows Preview, Ollama will run in the background and
+the `ollama` command line is available in `cmd`, `powershell` or your favorite
+terminal application. As usual the Ollama [api](./api.md) will be served on
+`http://localhost:11434`.
+
+As this is a preview release, you should expect a few bugs here and there.  If
+you run into a problem you can reach out on
+[Discord](https://discord.gg/ollama), or file an 
+[issue](https://github.com/ollama/ollama/issues).
+Logs will often be helpful in dianosing the problem (see
+[Troubleshooting](#troubleshooting) below)
+
+## System Requirements
+
+* Windows 10 or newer, Home or Pro
+* NVIDIA 452.39 or newer Drivers if you have an NVIDIA card
+* AMD Radeon Driver https://www.amd.com/en/support if you have a Radeon card
+
+## API Access
+
+Here's a quick example showing API access from `powershell`
+```powershell
+(Invoke-WebRequest -method POST -Body '{"model":"llama2", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
+```
+
+## Troubleshooting
+
+While we're in preview, `OLLAMA_DEBUG` is always enabled, which adds
+a "view logs" menu item to the app, and increses logging for the GUI app and
+server.
+
+Ollama on Windows stores files in a few different locations.  You can view them in
+the explorer window by hitting `<cmd>+R` and type in:
+- `explorer %LOCALAPPDATA%\Ollama` contains logs, and downloaded updates
+    - *app.log* contains logs from the GUI application
+    - *server.log* contains the server logs
+    - *upgrade.log* contains log output for upgrades
+- `explorer %LOCALAPPDATA%\Programs\Ollama` contains the binaries (The installer adds this to your user PATH)
+- `explorer %HOMEPATH%\.ollama` contains models and configuration
+- `explorer %TEMP%` contains temporary executable files in one or more `ollama*` directories

examples/.gitignore

@@ -1,7 +1,10 @@
 node_modules
+bun.lockb
+.vscode
 # OSX
 .DS_STORE
 
+
 # Models
 models/
 

examples/golang-simplegenerate/main.go

@@ -18,6 +18,8 @@ func main() {
 		os.Exit(1)
 	}
 
+	defer resp.Body.Close()
+	
 	responseData, err := io.ReadAll(resp.Body)
 	if err != nil {
 		log.Fatal(err)

examples/jupyter-notebook/ollama.ipynb

@@ -8,7 +8,7 @@
    "outputs": [],
    "source": [
     "# Download and run the Ollama Linux install script\n",
-    "!curl https://ollama.ai/install.sh | sh\n",
+    "!curl -fsSL https://ollama.com/install.sh | sh\n",
     "!command -v systemctl >/dev/null && sudo systemctl stop ollama"
    ]
   },

examples/kubernetes/README.md

@@ -2,28 +2,28 @@
 
 ## Prerequisites
 
-- Ollama: https://ollama.ai/download
+- Ollama: https://ollama.com/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
-    ```
+   ```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
-    ```
+   ```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
-    ```
+   ```bash
+   ollama run orca-mini:3b
+   ```
 
 ## (Optional) Hardware Acceleration
 

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

@@ -1,15 +1,23 @@
 # LangChain Web Summarization
 
-This example summarizes a website
+This example summarizes the website, [https://ollama.com/blog/run-llama2-uncensored-locally](https://ollama.com/blog/run-llama2-uncensored-locally)
 
-## Setup
+## Running the Example
 
-```
-pip install -r requirements.txt
-```
+1. Ensure you have the `llama2` model installed:
 
-## Run
+   ```bash
+   ollama pull llama2
+   ```
 
-```
-python main.py
-```
+2. Install the Python Requirements.
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. Run the example:
+
+   ```bash
+   python main.py
+   ```

examples/langchain-python-rag-websummary/main.py

@@ -2,7 +2,7 @@ from langchain.llms import Ollama
 from langchain.document_loaders import WebBaseLoader
 from langchain.chains.summarize import load_summarize_chain
 
-loader = WebBaseLoader("https://ollama.ai/blog/run-llama2-uncensored-locally")
+loader = WebBaseLoader("https://ollama.com/blog/run-llama2-uncensored-locally")
 docs = loader.load()
 
 llm = Ollama(model="llama2")

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

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

examples/langchain-python-simple/README.md

@@ -2,20 +2,23 @@
 
 This example is a basic "hello world" of using LangChain with Ollama.
 
-## Setup
+## Running the Example
 
-```
-pip install -r requirements.txt
-```
+1. Ensure you have the `llama2` model installed:
 
-## Run
+   ```bash
+   ollama pull llama2
+   ```
 
-```
-python main.py
-```
+2. Install the Python Requirements.
 
-Running this example will print the response for "hello":
+   ```bash
+   pip install -r requirements.txt
+   ```
 
-```
-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?
-```
+3. Run the example:
+
+   ```bash
+   python main.py
+   ```
+  

examples/langchain-python-simple/main.py

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

examples/langchain-typescript-simple/README.md

@@ -2,20 +2,22 @@
 
 This example is a basic "hello world" of using LangChain with Ollama using Node.js and Typescript.
 
-## Setup
+## Running the Example
 
-```shell
-npm install
-```
+1. Install the prerequisites:
 
-## Run
+   ```bash
+   npm install
+   ```
 
-```shell
-ts-node main.ts
-```
+2. Ensure the `mistral` model is available:
 
-Running this example will print the response for "hello":
+   ```bash
+   ollama pull mistral
+   ```
 
-```plaintext
-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?
-```
+3. Run the example:
+
+   ```bash
+   npm start
+   ```

examples/langchain-typescript-simple/main.ts

@@ -1,15 +1,25 @@
-import { Ollama} from 'langchain/llms/ollama';
+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 stream = await ollama.stream("Hello");
+  });
 
-  for await (const chunk of stream) {
-    process.stdout.write(chunk);
-  }
+  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

@@ -1,5 +1,5 @@
 {
-  "name": "with-langchain-typescript-simplegenerate",
+  "name": "langchain-typescript-simple",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {

examples/langchain-typescript-simple/package.json

@@ -1,8 +1,13 @@
 {
+  "scripts": {
+    "start": "tsx main.ts"
+  },
   "devDependencies": {
-    "typescript": "^5.2.2"
+    "tsx": "^4.6.2",
+    "typescript": "^5.3.3"
   },
   "dependencies": {
-    "langchain": "^0.0.165"
+    "langchain": "^0.0.165",
+    "readline": "^1.3.0"
   }
 }

examples/modelfile-10tweets/Modelfile

@@ -1,7 +0,0 @@
-# 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/modelfile-10tweets/README.md

@@ -1,23 +0,0 @@
-# Ten Tweets Modelfile
-
-This is a simple modelfile that generates ten tweets based off any topic.
-
-```bash
-ollama create tentweets
-
-ollama run tentweets
->>> underwater basketweaving
- Great! Here are ten creative tweets about underwater basketweaving:
-
-1. "Just discovered the ultimate stress-reliever: Underwater basketweaving! 🌊🧵 #UnderwaterBasketweaving #StressRelief"
-2. "Who needs meditation when you can do underwater basketweaving? 😴👀 #PeacefulDistraction #UnderwaterBasketweaving"
-3. "Just spent an hour in the pool and still managed to knot my basket. Goal: untangle it before next session. 💪🏽 #ChallengeAccepted #UnderwaterBasketweaving"
-4. "When life gives you lemons, make underwater basketweaving! 🍋🧵 #LemonadeLife #UnderwaterBasketweaving"
-5. "Just realized my underwater basketweaving skills could come in handy during a zombie apocalypse. 😂🧡 #SurvivalTips #UnderwaterBasketweaving"
-6. "I'm not lazy, I'm just conserving energy for my next underwater basketweaving session. 😴💤 #LazyDay #UnderwaterBasketweaving"
-7. "Just found my inner peace while doing underwater basketweaving. It's like meditation, but with knots! 🙏🧵 #Mindfulness #UnderwaterBasketweaving"
-8. "Why study for exams when you can do underwater basketweaving and forget all your worries? 😜🧵 #ProcrastinationStation #UnderwaterBasketweaving"
-9. "Just had to cut my underwater basketweaving session short due to a sudden urge to breathe. 🤯🌊 #AquaticAdventures #UnderwaterBasketweaving"
-10. "I'm not sure what's more impressive: my underwater basketweaving skills or the fact that I didn't drown trying to make this tweet. 😅🧵 #Accomplishment 
-#UnderwaterBasketweaving"
-```

examples/modelfile-devopsengineer/Modelfile

@@ -1,8 +0,0 @@
-# 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 mistral
-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/modelfile-devopsengineer/README.md

@@ -1,40 +0,0 @@
-# DevOps Engineer Modelfile
-
-This is a simple modelfile that takes will respond to any questions that a senior DevOps engineer should know how to solve.
-
-````text
-ollama create devopsengineer
-
-ollama run devopsengineer
->>> how can i proxy all connections from inside the office through a single server that caches large files. Provide a config file for nginx to achieve this?
-
-Here is an example configuration file for Nginx that can be used to proxy all connections from inside the office network to a centralized cache server:
-```perl
-http {
-    upstream cache_server {
-        server <cache_server_ip>;
-        server <cache_server_ip>;
-        server <cache_server_ip>;
-    }
-    
-    server {
-        listen 80;
-        server_name localhost;
-        
-        location / {
-            proxy_pass http://cache_server;
-            proxy_set_header Host $host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        }
-    }
-}
-```
-In this configuration, we define an `upstream` block that lists the IP addresses of the cache servers. We then define a server block that listens on port 80 and routes all 
-traffic to the `/` location to the cache servers using the `proxy_pass` directive. The `proxy_set_header` directives are used to preserve the source IP address of the client
-request when forwarding it to the cache server.
-
-To use this configuration, you would need to replace the placeholder `<cache_server_ip>` with the actual IP addresses of your cache servers. You would also need to make sure
-that the cache servers are configured to accept incoming connections from the Nginx server and handle requests for files.
-
-````

examples/modelfile-midjourney/Modelfile

@@ -1,11 +0,0 @@
-# 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 zephyr
-PARAMETER temperature 0.8
-PARAMETER top_k 500
-PARAMETER top_p 0.9
-SYSTEM """
-Embrace your role as a creative illustrator. Based on a concept provided, you must produce a single paragraph with a multifaceted description of an image, ensuring significant details of the concept and more is represented in your instructions. You do not need to write complete sentences but rather short concepts with the following information: the level of detail that should be represented, an artistic style and maybe a specific name of a painter or illustrator, the ideal color pallete, lighting, mood, perspective, the setting, time of day, weather, the season, the time period, location, materials, the textures, patterns, lines, brushstrokes, techniques, the medium, the genre, the rendering style. Don't include everything and keep the description length under 250 words. 
-"""

examples/modelfile-midjourney/README.md

@@ -1,11 +0,0 @@
-# Midjourney Prompt Generator Modelfile
-
-This simple modelfile will help create a prompt to feed to Midjourney.
-
-```text
-ollama create midjourney
-
-ollama run midjourney
->>> a sports car in the mountains. 
-A sleek, high-performance automobile cuts through a serpentine mountain landscape. The concept is a classic illustration of speed and power, depicted in the style of pop art by Andy Warhol. The color palette is dominated by bold, primary hues of red, blue, and yellow, with striking accent colors of white, black, and metallic shades. The lighting is bright and focused, casting sharp shadows on the rugged terrain. A sense of excitement and anticipation permeates throughout the scene, as the car navigates a treacherous course through the winding road. The perspective is low, allowing for a full view of the vehicle's sleek lines and intricate details. The setting takes place in the afternoon during a sunny day in autumn, as evidenced by the vibrant foliage on the mountainside. The time period is modern, with nods to classic car design. The materials are primarily digital, allowing for smooth curves and sharp contrasts. The textures are sleek and polished, with meticulously detailed lines and brushstrokes that accentuate the car's aerodynamic design. The patterns consist of geometric shapes and bold stripes, adding to the car's dynamic appeal. The genre is modern realism, with a focus on precision and detail. The rendering style is highly technical, capturing the nuances and subtleties of the vehicle and its surroundings in breathtaking detail.
-```

examples/modelfile-recipemaker/Modelfile

@@ -1,6 +0,0 @@
-# Modelfile for creating a recipe from a list of ingredients
-# Run `ollama create recipemaker -f ./Modelfile` and then `ollama run recipemaker` and feed it lists of ingredients to create recipes around.
-FROM nous-hermes
-SYSTEM """
-The instruction will be a list of ingredients. You should generate a recipe that can be made in less than an hour. You can also include ingredients that most people will find in their pantry every day. The recipe should be 4 people and you should include a description of what the meal will taste like
-"""

examples/modelfile-recipemaker/README.md

@@ -1,20 +0,0 @@
-# Recipe Maker Modelfile 
-
-Simple modelfile to generate a recipe from a short list of ingredients.
-
-```
-ollama create recipemaker
-
-ollama run recipemaker
->>> chilli pepper, white chocolate, kale
- Ingredients:
-- 1 small chili pepper
-- 4 squares of white chocolate
-- handful of kale leaves
-
-Instructions:
-1. In a blender or food processor, puree the chilies and white chocolate until smooth.
-2. Add the chopped kale leaves to the blender and pulse until well combined.
-3. Serve immediately as a dip for crackers or use it as an ingredient in your favorite recipe. The mixture of spicy chili pepper with sweet white chocolate and nutritious 
-kale will make your taste buds dance with delight!
-```

examples/modelfile-sentiments/Modelfile

@@ -1,28 +0,0 @@
-# Modelfile for creating a sentiment analyzer. 
-# Run `ollama create sentiments -f pathtofile` and then `ollama run sentiments` and enter a topic
-
-FROM orca
-TEMPLATE """
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
-### User: 
-I hate it when my phone dies
-### Response: 
-NEGATIVE
-### User: 
-He is awesome
-### Response: 
-POSITIVE
-### User: 
-This is the link to the article
-### Response: 
-NEUTRAL
-### User:
-{{ .Prompt }}
-
-### Response:
-"""
-
-SYSTEM """You are a sentiment analyzer. You will receive text and output only one word, either POSITIVE or NEGATIVE or NEUTRAL, depending on the sentiment of the text."""

examples/modelfile-sentiments/Readme.md

@@ -1,25 +0,0 @@
-# Sentiments Modelfile
-
-This is a simple sentiments analyzer using the Orca model. When you pull Orca from the registry, it has a Template already defined that looks like this:
-
-```Modelfile
-{{- if .First }}
-### System:
-{{ .System }}
-{{- end }}
-
-### User:
-{{ .Prompt }}
-
-### Response:
-```
-
-If we just wanted to have the text:
-
-```Plaintext
-You are a sentiment analyzer. You will receive text and output only one word, either POSITIVE or NEGATIVE or NEUTRAL, depending on the sentiment of the text.
-```
-
-then we could have put this in a SYSTEM block. But we want to provide examples which require updating the full Template. Any Modelfile you create will inherit all the settings from the source model. But in this example, we are overriding the Template.
-
-When providing examples for the input and output, you should include the way the model usually provides information. Since the Orca model expects a user prompt to appear after ### User: and the response is after ### Response, we should format our examples like that as well. If we were using the Llama 2 model, the format would be a bit different.

examples/modelfile-tweetwriter/Modelfile

@@ -1,7 +0,0 @@
-# Modelfile for creating a tweet from a topic
-# Run `ollama create tweetwriter -f ./Modelfile` and then `ollama run tweetwriter` and enter a topic
-
-FROM nous-hermes
-SYSTEM """
-You are a content marketer who needs to come up with a short but succinct tweet. Make sure to include the appropriate hashtags and links. Sometimes when appropriate, describe a meme that can be included as well. All answers should be in the form of a tweet which has a max size of 280 characters. Every instruction will be the topic to create a tweet about.
-"""

examples/python-dockerit/README.md

@@ -1,15 +1,31 @@
 # 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. 
+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 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
-```
+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/readme.md

@@ -4,6 +4,32 @@
 
 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.