fix(deps): update github.com/ggerganov/whisper.cpp/bindings/go digest to 54c978c

.env

@@ -66,24 +66,4 @@ MODELS_PATH=/models
 ### Python backends GRPC max workers
 ### Default number of workers for GRPC Python backends.
 ### This actually controls wether a backend can process multiple requests or not.
-# PYTHON_GRPC_MAX_WORKERS=1
-
-### Define the number of parallel LLAMA.cpp workers (Defaults to 1)
-# LLAMACPP_PARALLEL=1
-
-### Enable to run parallel requests
-# PARALLEL_REQUESTS=true
-
-### Watchdog settings
-###
-# Enables watchdog to kill backends that are inactive for too much time
-# WATCHDOG_IDLE=true
-#
-# Enables watchdog to kill backends that are busy for too much time
-# WATCHDOG_BUSY=true
-#
-# Time in duration format (e.g. 1h30m) after which a backend is considered idle
-# WATCHDOG_IDLE_TIMEOUT=5m
-#
-# Time in duration format (e.g. 1h30m) after which a backend is considered busy
-# WATCHDOG_BUSY_TIMEOUT=5m
+# PYTHON_GRPC_MAX_WORKERS=1

.github/workflows/bump_deps.yaml

@@ -12,9 +12,6 @@ jobs:
           - repository: "go-skynet/go-llama.cpp"
             variable: "GOLLAMA_VERSION"
             branch: "master"
-          - repository: "ggerganov/llama.cpp"
-            variable: "CPPLLAMA_VERSION"
-            branch: "master"
           - repository: "go-skynet/go-ggml-transformers.cpp"
             variable: "GOGGMLTRANSFORMERS_VERSION"
             branch: "master"
@@ -44,7 +41,7 @@ jobs:
             branch: "master"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Bump dependencies 🔧
         run: |
           bash .github/bump_deps.sh ${{ matrix.repository }} ${{ matrix.branch }} ${{ matrix.variable }}

.github/workflows/disabled/test-gpu.yml

@@ -1,63 +0,0 @@
----
-name: 'GPU tests'
-
-on:
-  pull_request:
-  push:
-    branches:
-      - master
-    tags:
-      - '*'
-
-concurrency:
-  group: ci-gpu-tests-${{ github.head_ref || github.ref }}-${{ github.repository }}
-  cancel-in-progress: true
-
-jobs:
-  ubuntu-latest:
-    runs-on: gpu
-    strategy:
-      matrix:
-        go-version: ['1.21.x']
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with: 
-          submodules: true
-      - name: Setup Go ${{ matrix.go-version }}
-        uses: actions/setup-go@v4
-        with:
-          go-version: ${{ matrix.go-version }}
-      # You can test your matrix by printing the current Go version
-      - name: Display Go version
-        run: go version
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo DEBIAN_FRONTEND=noninteractive apt-get install -y make wget
-      - name: Build
-        run: |
-          if [ ! -e /run/systemd/system ]; then
-            sudo mkdir /run/systemd/system
-          fi
-          sudo mkdir -p /host/tests/${{ github.head_ref || github.ref }}
-          sudo chmod -R 777 /host/tests/${{ github.head_ref || github.ref }}
-          make \
-            TEST_DIR="/host/tests/${{ github.head_ref || github.ref }}" \
-            BUILD_TYPE=cublas \
-            prepare-e2e run-e2e-image test-e2e
-      - name: Release space from worker ♻
-        if: always()
-        run: |
-          sudo rm -rf build || true
-          sudo rm -rf bin || true
-          sudo rm -rf dist || true
-          sudo docker logs $(sudo docker ps -q --filter ancestor=localai-tests) > logs.txt
-          sudo cat logs.txt || true
-          sudo rm -rf logs.txt
-          make clean || true
-          make \
-            TEST_DIR="/host/tests/${{ github.head_ref || github.ref }}" \
-            teardown-e2e || true
-          sudo rm -rf /host/tests/${{ github.head_ref || github.ref }} || true
-          docker system prune -f -a --volumes || true

.github/workflows/image.yml

@@ -14,144 +14,128 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  extras-image-build:
-    uses: ./.github/workflows/image_build.yml
-    with:
-      tag-latest: ${{ matrix.tag-latest }}
-      tag-suffix: ${{ matrix.tag-suffix }}
-      ffmpeg: ${{ matrix.ffmpeg }}
-      image-type: ${{ matrix.image-type }}
-      build-type: ${{ matrix.build-type }}
-      cuda-major-version: ${{ matrix.cuda-major-version }}
-      cuda-minor-version: ${{ matrix.cuda-minor-version }}
-      platforms: ${{ matrix.platforms }}
-      runs-on: ${{ matrix.runs-on }}
-    secrets:
-      dockerUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
-      dockerPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+  docker:
     strategy:
-      # Pushing with all jobs in parallel
-      # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
           - build-type: ''
-            #platforms: 'linux/amd64,linux/arm64'
-            platforms: 'linux/amd64'
+            platforms: 'linux/amd64,linux/arm64'
             tag-latest: 'auto'
             tag-suffix: ''
             ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-          - build-type: ''
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-ffmpeg'
-            ffmpeg: 'true'
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
           - build-type: 'cublas'
-            cuda-major-version: "11"
-            cuda-minor-version: "7"
+            cuda-major-version: 11
+            cuda-minor-version: 7
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11'
             ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
           - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "1"
+            cuda-major-version: 12
+            cuda-minor-version: 1
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12'
             ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
+          - build-type: ''
+            platforms: 'linux/amd64,linux/arm64'
+            tag-latest: 'false'
+            tag-suffix: '-ffmpeg'
+            ffmpeg: 'true'
           - build-type: 'cublas'
-            cuda-major-version: "11"
-            cuda-minor-version: "7"
+            cuda-major-version: 11
+            cuda-minor-version: 7
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11-ffmpeg'
             ffmpeg: 'true'
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
           - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "1"
+            cuda-major-version: 12
+            cuda-minor-version: 1
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg'
             ffmpeg: 'true'
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-          - build-type: ''
-            #platforms: 'linux/amd64,linux/arm64'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: ''
-            ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-  core-image-build:
-    uses: ./.github/workflows/image_build.yml
-    with:
-      tag-latest: ${{ matrix.tag-latest }}
-      tag-suffix: ${{ matrix.tag-suffix }}
-      ffmpeg: ${{ matrix.ffmpeg }}
-      image-type: ${{ matrix.image-type }}
-      build-type: ${{ matrix.build-type }}
-      cuda-major-version: ${{ matrix.cuda-major-version }}
-      cuda-minor-version: ${{ matrix.cuda-minor-version }}
-      platforms: ${{ matrix.platforms }}
-      runs-on: ${{ matrix.runs-on }}
-    secrets:
-      dockerUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
-      dockerPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
-    strategy:
-      matrix:
-        include:
-          - build-type: ''
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-          - build-type: 'cublas'
-            cuda-major-version: "11"
-            cuda-minor-version: "7"
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda11-core'
-            ffmpeg: ''
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "1"
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12-core'
-            ffmpeg: ''
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-          - build-type: 'cublas'
-            cuda-major-version: "11"
-            cuda-minor-version: "7"
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda11-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "1"
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
+
+    runs-on: ubuntu-latest
+    steps:
+      - name: Release space from worker
+        run: |
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          df -h
+          echo
+          sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
+          sudo apt-get remove --auto-remove android-sdk-platform-tools || true
+          sudo apt-get purge --auto-remove android-sdk-platform-tools || true
+          sudo rm -rf /usr/local/lib/android
+          sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
+          sudo rm -rf /usr/share/dotnet
+          sudo apt-get remove -y '^mono-.*' || true
+          sudo apt-get remove -y '^ghc-.*' || true
+          sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
+          sudo apt-get remove -y 'php.*' || true
+          sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
+          sudo apt-get remove -y '^google-.*' || true
+          sudo apt-get remove -y azure-cli || true
+          sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
+          sudo apt-get remove -y '^gfortran-.*' || true
+          sudo apt-get autoremove -y
+          sudo apt-get clean
+          echo
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          sudo rm -rfv build || true
+          df -h
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: quay.io/go-skynet/local-ai
+          tags: |
+            type=ref,event=branch
+            type=semver,pattern={{raw}}
+            type=sha
+          flavor: |
+            latest=${{ matrix.tag-latest }}
+            suffix=${{ matrix.tag-suffix }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@master
+        with:
+          platforms: all
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@master
+
+      - name: Login to DockerHub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          registry: quay.io
+          username: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+          password: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          builder: ${{ steps.buildx.outputs.name }}
+          build-args: |
+            BUILD_TYPE=${{ matrix.build-type }}
+            CUDA_MAJOR_VERSION=${{ matrix.cuda-major-version }}
+            CUDA_MINOR_VERSION=${{ matrix.cuda-minor-version }}
+            FFMPEG=${{ matrix.ffmpeg }}
+          context: .
+          file: ./Dockerfile
+          platforms: ${{ matrix.platforms }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/image_build.yml

@@ -1,147 +0,0 @@
----
-name: 'build container images (reusable)'
-
-on:
-  workflow_call:
-    inputs:
-      build-type:
-        description: 'Build type'
-        default: ''
-        type: string
-      cuda-major-version:
-        description: 'CUDA major version'
-        default: "11"
-        type: string
-      cuda-minor-version:
-        description: 'CUDA minor version'
-        default: "7"
-        type: string
-      platforms:
-        description: 'Platforms'
-        default: ''
-        type: string
-      tag-latest:
-        description: 'Tag latest'
-        default: ''
-        type: string
-      tag-suffix:
-        description: 'Tag suffix'
-        default: ''
-        type: string
-      ffmpeg:
-        description: 'FFMPEG'
-        default: ''
-        type: string
-      image-type:
-        description: 'Image type'
-        default: ''
-        type: string
-      runs-on:
-        description: 'Runs on'
-        required: true
-        default: ''
-        type: string
-    secrets:
-      dockerUsername:
-        required: true
-      dockerPassword:
-        required: true
-jobs:
-  reusable_image-build:
-    runs-on: ${{ inputs.runs-on }}
-    steps:
-      - name: Force Install GIT latest
-        run: |
-          sudo apt-get update \
-          && sudo apt-get install -y software-properties-common \
-          && sudo apt-get update \
-          && sudo add-apt-repository -y ppa:git-core/ppa \
-          && sudo apt-get update \
-          && sudo apt-get install -y git
-      - name: Checkout
-        uses: actions/checkout@v4
-      # - name: Release space from worker
-      #   run: |
-      #     echo "Listing top largest packages"
-      #     pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
-      #     head -n 30 <<< "${pkgs}"
-      #     echo
-      #     df -h
-      #     echo
-      #     sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
-      #     sudo apt-get remove --auto-remove android-sdk-platform-tools || true
-      #     sudo apt-get purge --auto-remove android-sdk-platform-tools || true
-      #     sudo rm -rf /usr/local/lib/android
-      #     sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
-      #     sudo rm -rf /usr/share/dotnet
-      #     sudo apt-get remove -y '^mono-.*' || true
-      #     sudo apt-get remove -y '^ghc-.*' || true
-      #     sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
-      #     sudo apt-get remove -y 'php.*' || true
-      #     sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
-      #     sudo apt-get remove -y '^google-.*' || true
-      #     sudo apt-get remove -y azure-cli || true
-      #     sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
-      #     sudo apt-get remove -y '^gfortran-.*' || true
-      #     sudo apt-get remove -y microsoft-edge-stable || true
-      #     sudo apt-get remove -y firefox || true
-      #     sudo apt-get remove -y powershell || true
-      #     sudo apt-get remove -y r-base-core || true
-      #     sudo apt-get autoremove -y
-      #     sudo apt-get clean
-      #     echo
-      #     echo "Listing top largest packages"
-      #     pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
-      #     head -n 30 <<< "${pkgs}"
-      #     echo
-      #     sudo rm -rfv build || true
-      #     df -h
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: quay.io/go-skynet/local-ai
-          tags: |
-            type=ref,event=branch
-            type=semver,pattern={{raw}}
-            type=sha
-          flavor: |
-            latest=${{ inputs.tag-latest }}
-            suffix=${{ inputs.tag-suffix }}
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@master
-        with:
-          platforms: all
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@master
-
-      - name: Login to DockerHub
-        if: github.event_name != 'pull_request'
-        uses: docker/login-action@v3
-        with:
-          registry: quay.io
-          username: ${{ secrets.dockerUsername }}
-          password: ${{ secrets.dockerPassword }}
-
-      - name: Build and push
-        uses: docker/build-push-action@v5
-        with:
-          builder: ${{ steps.buildx.outputs.name }}
-          build-args: |
-            BUILD_TYPE=${{ inputs.build-type }}
-            CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
-            CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
-            FFMPEG=${{ inputs.ffmpeg }}
-            IMAGE_TYPE=${{ inputs.image-type }}
-          context: .
-          file: ./Dockerfile
-          platforms: ${{ inputs.platforms }}
-          push: ${{ github.event_name != 'pull_request' }}
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-      - name: job summary
-        run: |
-          echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY

.github/workflows/release.yaml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           submodules: true
       - uses: actions/setup-go@v4
@@ -29,12 +29,6 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install build-essential ffmpeg
-
-          git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
-              cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-                -DgRPC_BUILD_TESTS=OFF \
-                ../.. && sudo make -j12 install
-
       - name: Build
         id: build
         env:
@@ -66,26 +60,18 @@ jobs:
     runs-on: macOS-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           submodules: true
       - uses: actions/setup-go@v4
         with:
           go-version: '>=1.21.0'
-      - name: Dependencies
-        run: |
-          git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
-              cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-                -DgRPC_BUILD_TESTS=OFF \
-                ../.. && make -j12 install && rm -rf grpc
       - name: Build
         id: build
         env:
           CMAKE_ARGS: "${{ matrix.defines }}"
           BUILD_ID: "${{ matrix.build }}"
         run: |
-          export C_INCLUDE_PATH=/usr/local/include
-          export CPLUS_INCLUDE_PATH=/usr/local/include
           make dist
       - uses: actions/upload-artifact@v3
         with:

.github/workflows/test.yml

@@ -14,7 +14,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  tests-linux:
+  ubuntu-latest:
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -53,7 +53,7 @@ jobs:
           sudo rm -rfv build || true
           df -h
       - name: Clone
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with: 
           submodules: true
       - name: Setup Go ${{ matrix.go-version }}
@@ -67,42 +67,38 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install build-essential ffmpeg
-          curl https://repo.anaconda.com/pkgs/misc/gpgkeys/anaconda.asc | gpg --dearmor > conda.gpg && \
-             sudo install -o root -g root -m 644 conda.gpg /usr/share/keyrings/conda-archive-keyring.gpg && \
-              gpg --keyring /usr/share/keyrings/conda-archive-keyring.gpg --no-default-keyring --fingerprint 34161F5BF5EB1D4BFBBB8F0A8AEB4F8B29D82806 && \
-             sudo /bin/bash -c 'echo "deb [arch=amd64 signed-by=/usr/share/keyrings/conda-archive-keyring.gpg] https://repo.anaconda.com/pkgs/misc/debrepo/conda stable main" > /etc/apt/sources.list.d/conda.list' && \
-             sudo /bin/bash -c 'echo "deb [arch=amd64 signed-by=/usr/share/keyrings/conda-archive-keyring.gpg] https://repo.anaconda.com/pkgs/misc/debrepo/conda stable main" | tee -a /etc/apt/sources.list.d/conda.list' && \
-             sudo apt-get update && \
-             sudo apt-get install -y conda
+          
           sudo apt-get install -y ca-certificates cmake curl patch
           sudo apt-get install -y libopencv-dev && sudo ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
-          
-          sudo rm -rfv /usr/bin/conda || true
-          PATH=$PATH:/opt/conda/bin make -C backend/python/sentencetransformers
+          sudo pip install -r extra/requirements.txt
 
-          # Pre-build piper before we start tests in order to have shared libraries in place
-          make sources/go-piper && \
-          GO_TAGS="tts" make -C sources/go-piper piper.o && \
-          sudo cp -rfv sources/go-piper/piper/build/pi/lib/. /usr/lib/ && \
-          # Pre-build stable diffusion before we install a newer version of abseil (not compatible with stablediffusion-ncn)
-          GO_TAGS="stablediffusion tts" GRPC_BACKENDS=backend-assets/grpc/stablediffusion make build
-
-          git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
-              cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-                -DgRPC_BUILD_TESTS=OFF \
-                ../.. && sudo make -j12 install
+          sudo mkdir /build && sudo chmod -R 777 /build && cd /build && \
+          curl -L "https://github.com/gabime/spdlog/archive/refs/tags/v1.11.0.tar.gz" | \
+          tar -xzvf - && \
+          mkdir -p "spdlog-1.11.0/build" && \
+          cd "spdlog-1.11.0/build" && \
+          cmake ..  && \
+          make -j8 && \
+          sudo cmake --install . --prefix /usr && mkdir -p "lib/Linux-$(uname -m)" && \
+          cd /build && \
+          mkdir -p "lib/Linux-$(uname -m)/piper_phonemize" && \
+          curl -L "https://github.com/rhasspy/piper-phonemize/releases/download/v1.0.0/libpiper_phonemize-amd64.tar.gz" | \
+          tar -C "lib/Linux-$(uname -m)/piper_phonemize" -xzvf - && ls -liah /build/lib/Linux-$(uname -m)/piper_phonemize/ && \
+          sudo cp -rfv /build/lib/Linux-$(uname -m)/piper_phonemize/lib/. /usr/lib/ && \
+          sudo ln -s /usr/lib/libpiper_phonemize.so /usr/lib/libpiper_phonemize.so.1 && \
+          sudo cp -rfv /build/lib/Linux-$(uname -m)/piper_phonemize/include/. /usr/include/
       - name: Test
         run: |
-          GO_TAGS="stablediffusion tts" make test
+          ESPEAK_DATA="/build/lib/Linux-$(uname -m)/piper_phonemize/lib/espeak-ng-data" GO_TAGS="tts stablediffusion" make test
 
-  tests-apple:
+  macOS-latest:
     runs-on: macOS-latest
     strategy:
       matrix:
         go-version: ['1.21.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with: 
           submodules: true
       - name: Setup Go ${{ matrix.go-version }}
@@ -112,14 +108,6 @@ jobs:
       # You can test your matrix by printing the current Go version
       - name: Display Go version
         run: go version
-      - name: Dependencies
-        run: |
-          git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
-              cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-                -DgRPC_BUILD_TESTS=OFF \
-                ../.. && make -j12 install && rm -rf grpc
       - name: Test
         run: |
-          export C_INCLUDE_PATH=/usr/local/include
-          export CPLUS_INCLUDE_PATH=/usr/local/include
           CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make test

.gitignore

@@ -1,10 +1,15 @@
 # go-llama build artifacts
-/sources/
+go-llama
+go-llama-stable
+/gpt4all
+go-stable-diffusion
+go-piper
+/go-bert
+go-ggllm
+/piper
 __pycache__/
 *.a
 get-sources
-/backend/cpp/llama/grpc-server
-/backend/cpp/llama/llama.cpp
 
 go-ggml-transformers
 go-gpt2

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "docs/themes/hugo-theme-relearn"]
-	path = docs/themes/hugo-theme-relearn
-	url = https://github.com/McShelby/hugo-theme-relearn.git

Dockerfile

@@ -1,27 +1,22 @@
 ARG GO_VERSION=1.21-bullseye
-ARG IMAGE_TYPE=extras
-# extras or core
 
-
-FROM golang:$GO_VERSION as requirements-core
+FROM golang:$GO_VERSION as requirements
 
 ARG BUILD_TYPE
 ARG CUDA_MAJOR_VERSION=11
 ARG CUDA_MINOR_VERSION=7
+ARG SPDLOG_VERSION="1.11.0"
+ARG PIPER_PHONEMIZE_VERSION='1.0.0'
 ARG TARGETARCH
 ARG TARGETVARIANT
 
 ENV BUILD_TYPE=${BUILD_TYPE}
-ENV EXTERNAL_GRPC_BACKENDS="huggingface-embeddings:/build/backend/python/sentencetransformers/run.sh,petals:/build/backend/python/petals/run.sh,transformers:/build/backend/python/transformers/run.sh,sentencetransformers:/build/backend/python/sentencetransformers/run.sh,autogptq:/build/backend/python/autogptq/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,exllama:/build/backend/python/exllama/run.sh,vall-e-x:/build/backend/python/vall-e-x/run.sh,vllm:/build/backend/python/vllm/run.sh"
+ENV EXTERNAL_GRPC_BACKENDS="huggingface-embeddings:/build/extra/grpc/huggingface/huggingface.py,autogptq:/build/extra/grpc/autogptq/autogptq.py,bark:/build/extra/grpc/bark/ttsbark.py,diffusers:/build/extra/grpc/diffusers/backend_diffusers.py,exllama:/build/extra/grpc/exllama/exllama.py,vall-e-x:/build/extra/grpc/vall-e-x/ttsvalle.py,vllm:/build/extra/grpc/vllm/backend_vllm.py"
 ENV GALLERIES='[{"name":"model-gallery", "url":"github:go-skynet/model-gallery/index.yaml"}, {"url": "github:go-skynet/model-gallery/huggingface.yaml","name":"huggingface"}]'
 ARG GO_TAGS="stablediffusion tts"
 
 RUN apt-get update && \
-    apt-get install -y ca-certificates curl patch pip cmake && apt-get clean
-
-
-COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
-RUN update-ca-certificates
+    apt-get install -y ca-certificates cmake curl patch pip
 
 # Use the variables in subsequent instructions
 RUN echo "Target Architecture: $TARGETARCH"
@@ -35,52 +30,66 @@ RUN if [ "${BUILD_TYPE}" = "cublas" ]; then \
     dpkg -i cuda-keyring_1.0-1_all.deb && \
     rm -f cuda-keyring_1.0-1_all.deb && \
     apt-get update && \
-    apt-get install -y cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcusparse-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}  && apt-get clean \
+    apt-get install -y cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcusparse-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
     ; fi
 ENV PATH /usr/local/cuda/bin:${PATH}
 
-# OpenBLAS requirements and stable diffusion
-RUN apt-get install -y \
-    libopenblas-dev \
-    libopencv-dev \ 
-    && apt-get clean
-
-# Set up OpenCV
-RUN ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
-
-WORKDIR /build
-
-RUN test -n "$TARGETARCH" \
-    || (echo 'warn: missing $TARGETARCH, either set this `ARG` manually, or run using `docker buildkit`')
-
 # Extras requirements
-FROM requirements-core as requirements-extras
-
-RUN curl https://repo.anaconda.com/pkgs/misc/gpgkeys/anaconda.asc | gpg --dearmor > conda.gpg && \
-    install -o root -g root -m 644 conda.gpg /usr/share/keyrings/conda-archive-keyring.gpg && \
-    gpg --keyring /usr/share/keyrings/conda-archive-keyring.gpg --no-default-keyring --fingerprint 34161F5BF5EB1D4BFBBB8F0A8AEB4F8B29D82806 && \
-    echo "deb [arch=amd64 signed-by=/usr/share/keyrings/conda-archive-keyring.gpg] https://repo.anaconda.com/pkgs/misc/debrepo/conda stable main" > /etc/apt/sources.list.d/conda.list && \
-    echo "deb [arch=amd64 signed-by=/usr/share/keyrings/conda-archive-keyring.gpg] https://repo.anaconda.com/pkgs/misc/debrepo/conda stable main" | tee -a /etc/apt/sources.list.d/conda.list && \
-    apt-get update && \
-    apt-get install -y conda
-
+COPY extra/requirements.txt /build/extra/requirements.txt
 ENV PATH="/root/.cargo/bin:${PATH}"
 RUN pip install --upgrade pip
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
+RUN if [ "${TARGETARCH}" = "amd64" ]; then \
+        pip install git+https://github.com/suno-ai/bark.git diffusers invisible_watermark transformers accelerate safetensors;\
+    fi
+RUN if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH}" = "amd64" ]; then \
+        pip install torch vllm && pip install auto-gptq https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu${CUDA_MAJOR_VERSION}${CUDA_MINOR_VERSION}-cp39-cp39-linux_x86_64.whl;\
+    fi
+RUN pip install -r /build/extra/requirements.txt && rm -rf /build/extra/requirements.txt
+
+# Vall-e-X
+RUN git clone https://github.com/Plachtaa/VALL-E-X.git /usr/lib/vall-e-x && cd /usr/lib/vall-e-x && pip install -r requirements.txt
+
+WORKDIR /build
+
+# OpenBLAS requirements
+RUN apt-get install -y libopenblas-dev
+
+# Stable Diffusion requirements
+RUN apt-get install -y libopencv-dev && \
+    ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
 
 
+# piper requirements
+# Use pre-compiled Piper phonemization library (includes onnxruntime)
+#RUN if echo "${GO_TAGS}" | grep -q "tts"; then \
+RUN test -n "$TARGETARCH" \
+    || (echo 'warn: missing $TARGETARCH, either set this `ARG` manually, or run using `docker buildkit`')
+
+RUN curl -L "https://github.com/gabime/spdlog/archive/refs/tags/v${SPDLOG_VERSION}.tar.gz" | \
+    tar -xzvf - && \
+    mkdir -p "spdlog-${SPDLOG_VERSION}/build" && \
+    cd "spdlog-${SPDLOG_VERSION}/build" && \
+    cmake ..  && \
+    make -j8 && \
+    cmake --install . --prefix /usr && mkdir -p "lib/Linux-$(uname -m)" && \
+    cd /build && \
+    mkdir -p "lib/Linux-$(uname -m)/piper_phonemize" && \
+    curl -L "https://github.com/rhasspy/piper-phonemize/releases/download/v${PIPER_PHONEMIZE_VERSION}/libpiper_phonemize-${TARGETARCH:-$(go env GOARCH)}${TARGETVARIANT}.tar.gz" | \
+    tar -C "lib/Linux-$(uname -m)/piper_phonemize" -xzvf - && ls -liah /build/lib/Linux-$(uname -m)/piper_phonemize/ && \
+    cp -rfv /build/lib/Linux-$(uname -m)/piper_phonemize/lib/. /usr/lib/ && \
+    ln -s /usr/lib/libpiper_phonemize.so /usr/lib/libpiper_phonemize.so.1 && \
+    cp -rfv /build/lib/Linux-$(uname -m)/piper_phonemize/include/. /usr/include/
 # \
 #    ; fi
 
 ###################################
 ###################################
 
-FROM requirements-${IMAGE_TYPE} as builder
+FROM requirements as builder
 
 ARG GO_TAGS="stablediffusion tts"
-ARG GRPC_BACKENDS
-ARG BUILD_GRPC=true
-ENV GRPC_BACKENDS=${GRPC_BACKENDS}
+
 ENV GO_TAGS=${GO_TAGS}
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
 ENV NVIDIA_REQUIRE_CUDA="cuda>=${CUDA_MAJOR_VERSION}.0"
@@ -88,47 +97,28 @@ ENV NVIDIA_VISIBLE_DEVICES=all
 
 WORKDIR /build
 
+COPY Makefile .
+RUN make get-sources
+COPY go.mod .
+RUN make prepare
 COPY . .
 COPY .git .
-RUN make prepare
 
-# stablediffusion does not tolerate a newer version of abseil, build it first
-RUN GRPC_BACKENDS=backend-assets/grpc/stablediffusion make build
-
-RUN if [ "${BUILD_GRPC}" = "true" ]; then \
-    git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
-    cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
-      -DgRPC_BUILD_TESTS=OFF \
-       ../.. && make -j12 install \
-    ; fi
-
-# Rebuild with defaults backends
-RUN make build
-
-RUN if [ ! -d "/build/sources/go-piper/piper/build/pi/lib/" ]; then \
-    mkdir -p /build/sources/go-piper/piper/build/pi/lib/ \
-    touch /build/sources/go-piper/piper/build/pi/lib/keep \
-    ; fi
+RUN ESPEAK_DATA=/build/lib/Linux-$(uname -m)/piper_phonemize/lib/espeak-ng-data make build
 
 ###################################
 ###################################
 
-FROM requirements-${IMAGE_TYPE}
+FROM requirements
 
 ARG FFMPEG
 ARG BUILD_TYPE
 ARG TARGETARCH
-ARG IMAGE_TYPE=extras
 
 ENV BUILD_TYPE=${BUILD_TYPE}
 ENV REBUILD=false
 ENV HEALTHCHECK_ENDPOINT=http://localhost:8080/readyz
 
-ARG CUDA_MAJOR_VERSION=11
-ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
-ENV NVIDIA_REQUIRE_CUDA="cuda>=${CUDA_MAJOR_VERSION}.0"
-ENV NVIDIA_VISIBLE_DEVICES=all
-
 # Add FFmpeg
 RUN if [ "${FFMPEG}" = "true" ]; then \
     apt-get install -y ffmpeg \
@@ -141,62 +131,16 @@ WORKDIR /build
 # see https://github.com/go-skynet/LocalAI/pull/658#discussion_r1241971626 and
 # https://github.com/go-skynet/LocalAI/pull/434
 COPY . .
-
-COPY --from=builder /build/sources ./sources/
-COPY --from=builder /build/grpc ./grpc/
-
-RUN make prepare-sources && cd /build/grpc/cmake/build && make install && rm -rf grpc
-
-# Copy the binary
+RUN make prepare-sources
 COPY --from=builder /build/local-ai ./
 
-# Copy shared libraries for piper
-COPY --from=builder /build/sources/go-piper/piper/build/pi/lib/* /usr/lib/
-
-# do not let stablediffusion rebuild (requires an older version of absl)
-COPY --from=builder /build/backend-assets/grpc/stablediffusion ./backend-assets/grpc/stablediffusion
-
-## Duplicated from Makefile to avoid having a big layer that's hard to push
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/autogptq \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/bark \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/diffusers \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/vllm \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/sentencetransformers \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/transformers \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/vall-e-x \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/exllama \
-    ; fi
-RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C backend/python/petals \
-    ; fi
-
 # Copy VALLE-X as it's not a real "lib"
-# TODO: this is wrong - we should copy the lib into the conda env path
-RUN if [ -d /usr/lib/vall-e-x ]; then \
-    cp -rfv /usr/lib/vall-e-x/* ./ ; \ 
-    fi
+RUN cp -rfv /usr/lib/vall-e-x/* ./
 
-# we also copy exllama libs over to resolve exllama import error
-# TODO: check if this is still needed
-RUN if [ -d /usr/local/lib/python3.9/dist-packages/exllama ]; then \
-        cp -rfv /usr/local/lib/python3.9/dist-packages/exllama backend/python/exllama/;\
+# To resolve exllama import error
+RUN if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH:-$(go env GOARCH)}" = "amd64" ]; then \
+        cp -rfv /usr/local/lib/python3.9/dist-packages/exllama extra/grpc/exllama/;\
     fi
-
 # Define the health check command
 HEALTHCHECK --interval=1m --timeout=10m --retries=10 \
   CMD curl -f $HEALTHCHECK_ENDPOINT || exit 1

Entitlements.plist

@@ -1,10 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-    <key>com.apple.security.network.client</key>
-    <true/>
-    <key>com.apple.security.network.server</key>
-    <true/>
-</dict>
-</plist>

Makefile

@@ -4,12 +4,10 @@ GOVET=$(GOCMD) vet
 BINARY_NAME=local-ai
 
 # llama.cpp versions
-GOLLAMA_VERSION?=aeba71ee842819da681ea537e78846dc75949ac0
+GOLLAMA_VERSION?=1676dcd7a139b6cdfbaea5fd67f46dc25d9d8bcf
 
 GOLLAMA_STABLE_VERSION?=50cee7712066d9e38306eccadcfbb44ea87df4b7
 
-CPPLLAMA_VERSION?=1f5cd83275fabb43f2ae92c30033b384a3eb37b4
-
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
 GPT4ALL_VERSION?=27a8b020c36b0df8f8b82a252d261cda47cf44b8
@@ -28,10 +26,16 @@ WHISPER_CPP_VERSION?=85ed71aaec8e0612a84c0b67804bde75aa75a273
 BERT_VERSION?=6abe312cded14042f6b7c3cd8edf082713334a4d
 
 # go-piper version
-PIPER_VERSION?=5a4c9e28c84bac09ab6baa9f88457d852cb46bb2
+PIPER_VERSION?=56b8a81b4760a6fbee1a82e62f007ae7e8f010a7
+
+# go-bloomz version
+BLOOMZ_VERSION?=1834e77b83faafe912ad4092ccf7f77937349e2f
 
 # stablediffusion version
-STABLEDIFFUSION_VERSION?=902db5f066fd137697e3b69d0fa10d4782bd2c2f
+STABLEDIFFUSION_VERSION?=d89260f598afb809279bc72aa0107b4292587632
+
+# Go-ggllm
+GOGGLLM_VERSION?=862477d16eefb0805261c19c9b0d053e3b2b684b
 
 export BUILD_TYPE?=
 export STABLE_BUILD_TYPE?=$(BUILD_TYPE)
@@ -41,10 +45,6 @@ CUDA_LIBPATH?=/usr/local/cuda/lib64/
 GO_TAGS?=
 BUILD_ID?=git
 
-TEST_DIR=/tmp/test
-
-RANDOM := $(shell bash -c 'echo $$RANDOM')
-
 VERSION?=$(shell git describe --always --tags || echo "dev" )
 # go tool nm ./local-ai | grep Commit
 LD_FLAGS?=
@@ -52,6 +52,7 @@ override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Version=$(VERSION
 override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Commit=$(shell git rev-parse HEAD)"
 
 OPTIONAL_TARGETS?=
+ESPEAK_DATA?=
 
 OS := $(shell uname -s)
 ARCH := $(shell uname -m)
@@ -61,26 +62,16 @@ WHITE  := $(shell tput -Txterm setaf 7)
 CYAN   := $(shell tput -Txterm setaf 6)
 RESET  := $(shell tput -Txterm sgr0)
 
-# Default Docker bridge IP
-E2E_BRIDGE_IP?=172.17.0.1
-
 ifndef UNAME_S
 UNAME_S := $(shell uname -s)
 endif
 
-ifeq ($(OS),Darwin)
+ifeq ($(UNAME_S),Darwin)
 	CGO_LDFLAGS += -lcblas -framework Accelerate
-	ifeq ($(OSX_SIGNING_IDENTITY),)
-		OSX_SIGNING_IDENTITY := $(shell security find-identity -v -p codesigning | grep '"' | head -n 1 | sed -E 's/.*"(.*)"/\1/')
-	endif
-
-	# on OSX, if BUILD_TYPE is blank, we should default to use Metal
-	ifeq ($(BUILD_TYPE),)
-		BUILD_TYPE=metal
-	# disable metal if on Darwin and any other value is explicitly passed.
-	else ifneq ($(BUILD_TYPE),metal)
-		CMAKE_ARGS+=-DLLAMA_METAL=OFF
-	endif
+ifneq ($(BUILD_TYPE),metal)
+    # explicit disable metal if on Darwin and metal is disabled
+	CMAKE_ARGS+=-DLLAMA_METAL=OFF
+endif
 endif
 
 ifeq ($(BUILD_TYPE),openblas)
@@ -96,7 +87,7 @@ ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_HOME ?= /opt/rocm
 	export CXX=$(ROCM_HOME)/llvm/bin/clang++
 	export CC=$(ROCM_HOME)/llvm/bin/clang
-	# llama-ggml has no hipblas support, so override it here.
+	# Llama-stable has no hipblas support, so override it here.
 	export STABLE_BUILD_TYPE=
 	GPU_TARGETS ?= gfx900,gfx90a,gfx1030,gfx1031,gfx1100
 	AMDGPU_TARGETS ?= "$(GPU_TARGETS)"
@@ -126,134 +117,146 @@ endif
 ifeq ($(findstring tts,$(GO_TAGS)),tts)
 #	OPTIONAL_TARGETS+=go-piper/libpiper_binding.a
 #	OPTIONAL_TARGETS+=backend-assets/espeak-ng-data
-	PIPER_CGO_CXXFLAGS+=-I$(shell pwd)/sources/go-piper/piper/src/cpp -I$(shell pwd)/sources/go-piper/piper/build/fi/include -I$(shell pwd)/sources/go-piper/piper/build/pi/include -I$(shell pwd)/sources/go-piper/piper/build/si/include
- 	PIPER_CGO_LDFLAGS+=-L$(shell pwd)/sources/go-piper/piper/build/fi/lib -L$(shell pwd)/sources/go-piper/piper/build/pi/lib -L$(shell pwd)/sources/go-piper/piper/build/si/lib -lfmt -lspdlog -lucd
 	OPTIONAL_GRPC+=backend-assets/grpc/piper
 endif
 
-ALL_GRPC_BACKENDS=backend-assets/grpc/langchain-huggingface backend-assets/grpc/falcon-ggml backend-assets/grpc/bert-embeddings backend-assets/grpc/llama backend-assets/grpc/llama-cpp backend-assets/grpc/llama-ggml backend-assets/grpc/gpt4all backend-assets/grpc/dolly backend-assets/grpc/gpt2 backend-assets/grpc/gptj backend-assets/grpc/gptneox backend-assets/grpc/mpt backend-assets/grpc/replit backend-assets/grpc/starcoder backend-assets/grpc/rwkv backend-assets/grpc/whisper $(OPTIONAL_GRPC)
-GRPC_BACKENDS?=$(ALL_GRPC_BACKENDS) $(OPTIONAL_GRPC)
-
-# If empty, then we build all
-ifeq ($(GRPC_BACKENDS),)
-	GRPC_BACKENDS=$(ALL_GRPC_BACKENDS)
-endif
+GRPC_BACKENDS?=backend-assets/grpc/langchain-huggingface backend-assets/grpc/falcon-ggml backend-assets/grpc/bert-embeddings backend-assets/grpc/falcon backend-assets/grpc/bloomz backend-assets/grpc/llama backend-assets/grpc/llama-stable backend-assets/grpc/gpt4all backend-assets/grpc/dolly backend-assets/grpc/gpt2 backend-assets/grpc/gptj backend-assets/grpc/gptneox backend-assets/grpc/mpt backend-assets/grpc/replit backend-assets/grpc/starcoder backend-assets/grpc/rwkv backend-assets/grpc/whisper $(OPTIONAL_GRPC)
 
 .PHONY: all test build vendor
 
 all: help
 
 ## GPT4ALL
-sources/gpt4all:
-	git clone --recurse-submodules $(GPT4ALL_REPO) sources/gpt4all
-	cd sources/gpt4all && git checkout -b build $(GPT4ALL_VERSION) && git submodule update --init --recursive --depth 1
+gpt4all:
+	git clone --recurse-submodules $(GPT4ALL_REPO) gpt4all
+	cd gpt4all && git checkout -b build $(GPT4ALL_VERSION) && git submodule update --init --recursive --depth 1
+
+## go-ggllm
+go-ggllm:
+	git clone --recurse-submodules https://github.com/mudler/go-ggllm.cpp go-ggllm
+	cd go-ggllm && git checkout -b build $(GOGGLLM_VERSION) && git submodule update --init --recursive --depth 1
+
+go-ggllm/libggllm.a: go-ggllm
+	$(MAKE) -C go-ggllm BUILD_TYPE=$(BUILD_TYPE) libggllm.a
 
 ## go-piper
-sources/go-piper:
-	git clone --recurse-submodules https://github.com/mudler/go-piper sources/go-piper
-	cd sources/go-piper && git checkout -b build $(PIPER_VERSION) && git submodule update --init --recursive --depth 1
+go-piper:
+	git clone --recurse-submodules https://github.com/mudler/go-piper go-piper
+	cd go-piper && git checkout -b build $(PIPER_VERSION) && git submodule update --init --recursive --depth 1
 
 ## BERT embeddings
-sources/go-bert:
-	git clone --recurse-submodules https://github.com/go-skynet/go-bert.cpp sources/go-bert
-	cd sources/go-bert && git checkout -b build $(BERT_VERSION) && git submodule update --init --recursive --depth 1
+go-bert:
+	git clone --recurse-submodules https://github.com/go-skynet/go-bert.cpp go-bert
+	cd go-bert && git checkout -b build $(BERT_VERSION) && git submodule update --init --recursive --depth 1
 
 ## stable diffusion
-sources/go-stable-diffusion:
-	git clone --recurse-submodules https://github.com/mudler/go-stable-diffusion sources/go-stable-diffusion
-	cd sources/go-stable-diffusion && git checkout -b build $(STABLEDIFFUSION_VERSION) && git submodule update --init --recursive --depth 1
+go-stable-diffusion:
+	git clone --recurse-submodules https://github.com/mudler/go-stable-diffusion go-stable-diffusion
+	cd go-stable-diffusion && git checkout -b build $(STABLEDIFFUSION_VERSION) && git submodule update --init --recursive --depth 1
 
-sources/go-stable-diffusion/libstablediffusion.a:
-	$(MAKE) -C sources/go-stable-diffusion libstablediffusion.a
+go-stable-diffusion/libstablediffusion.a:
+	$(MAKE) -C go-stable-diffusion libstablediffusion.a
 
 ## RWKV
-sources/go-rwkv:
-	git clone --recurse-submodules $(RWKV_REPO) sources/go-rwkv
-	cd sources/go-rwkv && git checkout -b build $(RWKV_VERSION) && git submodule update --init --recursive --depth 1
+go-rwkv:
+	git clone --recurse-submodules $(RWKV_REPO) go-rwkv
+	cd go-rwkv && git checkout -b build $(RWKV_VERSION) && git submodule update --init --recursive --depth 1
 
-sources/go-rwkv/librwkv.a: sources/go-rwkv
-	cd sources/go-rwkv && cd rwkv.cpp &&	cmake . -DRWKV_BUILD_SHARED_LIBRARY=OFF &&	cmake --build . && 	cp librwkv.a ..
+go-rwkv/librwkv.a: go-rwkv
+	cd go-rwkv && cd rwkv.cpp &&	cmake . -DRWKV_BUILD_SHARED_LIBRARY=OFF &&	cmake --build . && 	cp librwkv.a ..
 
-sources/go-bert/libgobert.a: sources/go-bert
-	$(MAKE) -C sources/go-bert libgobert.a
+## bloomz
+bloomz:
+	git clone --recurse-submodules https://github.com/go-skynet/bloomz.cpp bloomz
+	cd bloomz && git checkout -b build $(BLOOMZ_VERSION) && git submodule update --init --recursive --depth 1
 
-backend-assets/gpt4all: sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a
+bloomz/libbloomz.a: bloomz
+	cd bloomz && make libbloomz.a
+
+go-bert/libgobert.a: go-bert
+	$(MAKE) -C go-bert libgobert.a
+
+backend-assets/gpt4all: gpt4all/gpt4all-bindings/golang/libgpt4all.a
 	mkdir -p backend-assets/gpt4all
-	@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.so backend-assets/gpt4all/ || true
-	@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.dylib backend-assets/gpt4all/ || true
-	@cp sources/gpt4all/gpt4all-bindings/golang/buildllm/*.dll backend-assets/gpt4all/ || true
+	@cp gpt4all/gpt4all-bindings/golang/buildllm/*.so backend-assets/gpt4all/ || true
+	@cp gpt4all/gpt4all-bindings/golang/buildllm/*.dylib backend-assets/gpt4all/ || true
+	@cp gpt4all/gpt4all-bindings/golang/buildllm/*.dll backend-assets/gpt4all/ || true
 
-backend-assets/espeak-ng-data: sources/go-piper
+backend-assets/espeak-ng-data:
 	mkdir -p backend-assets/espeak-ng-data
-	$(MAKE) -C sources/go-piper piper.o
-	@cp -rf sources/go-piper/piper/build/pi/share/espeak-ng-data/. backend-assets/espeak-ng-data
+ifdef ESPEAK_DATA
+	@cp -rf $(ESPEAK_DATA)/. backend-assets/espeak-ng-data
+else
+	@echo "ESPEAK_DATA not set, skipping tts. Note that this will break the tts functionality."
+	@touch backend-assets/espeak-ng-data/keep
+endif
 
-sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a: sources/gpt4all
-	$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ libgpt4all.a
+gpt4all/gpt4all-bindings/golang/libgpt4all.a: gpt4all
+	$(MAKE) -C gpt4all/gpt4all-bindings/golang/ libgpt4all.a
 
 ## CEREBRAS GPT
-sources/go-ggml-transformers:
-	git clone --recurse-submodules https://github.com/go-skynet/go-ggml-transformers.cpp sources/go-ggml-transformers
-	cd sources/go-ggml-transformers && git checkout -b build $(GOGPT2_VERSION) && git submodule update --init --recursive --depth 1
+go-ggml-transformers:
+	git clone --recurse-submodules https://github.com/go-skynet/go-ggml-transformers.cpp go-ggml-transformers
+	cd go-ggml-transformers && git checkout -b build $(GOGPT2_VERSION) && git submodule update --init --recursive --depth 1
 
-sources/go-ggml-transformers/libtransformers.a: sources/go-ggml-transformers
-	$(MAKE) -C sources/go-ggml-transformers BUILD_TYPE=$(BUILD_TYPE) libtransformers.a
+go-ggml-transformers/libtransformers.a: go-ggml-transformers
+	$(MAKE) -C go-ggml-transformers BUILD_TYPE=$(BUILD_TYPE) libtransformers.a
 
-sources/whisper.cpp:
-	git clone https://github.com/ggerganov/whisper.cpp.git sources/whisper.cpp
-	cd sources/whisper.cpp && git checkout -b build $(WHISPER_CPP_VERSION) && git submodule update --init --recursive --depth 1
+whisper.cpp:
+	git clone https://github.com/ggerganov/whisper.cpp.git
+	cd whisper.cpp && git checkout -b build $(WHISPER_CPP_VERSION) && git submodule update --init --recursive --depth 1
 
-sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
-	cd sources/whisper.cpp && make libwhisper.a
+whisper.cpp/libwhisper.a: whisper.cpp
+	cd whisper.cpp && make libwhisper.a
 
-sources/go-llama:
-	git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp sources/go-llama
-	cd sources/go-llama && git checkout -b build $(GOLLAMA_VERSION) && git submodule update --init --recursive --depth 1
+go-llama:
+	git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp go-llama
+	cd go-llama && git checkout -b build $(GOLLAMA_VERSION) && git submodule update --init --recursive --depth 1
 
-sources/go-llama-ggml:
-	git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp sources/go-llama-ggml
-	cd sources/go-llama-ggml && git checkout -b build $(GOLLAMA_STABLE_VERSION) && git submodule update --init --recursive --depth 1
+go-llama-stable:
+	git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp go-llama-stable
+	cd go-llama-stable && git checkout -b build $(GOLLAMA_STABLE_VERSION) && git submodule update --init --recursive --depth 1
 
-sources/go-llama/libbinding.a: sources/go-llama
-	$(MAKE) -C sources/go-llama BUILD_TYPE=$(BUILD_TYPE) libbinding.a
+go-llama/libbinding.a: go-llama
+	$(MAKE) -C go-llama BUILD_TYPE=$(BUILD_TYPE) libbinding.a
 
-sources/go-llama-ggml/libbinding.a: sources/go-llama-ggml
-	$(MAKE) -C sources/go-llama-ggml BUILD_TYPE=$(STABLE_BUILD_TYPE) libbinding.a
+go-llama-stable/libbinding.a: go-llama-stable
+	$(MAKE) -C go-llama-stable BUILD_TYPE=$(STABLE_BUILD_TYPE) libbinding.a
 
-sources/go-piper/libpiper_binding.a: sources/go-piper
-	$(MAKE) -C sources/go-piper libpiper_binding.a example/main
+go-piper/libpiper_binding.a:
+	$(MAKE) -C go-piper libpiper_binding.a example/main
 
-backend/cpp/llama/llama.cpp:
-	$(MAKE) -C backend/cpp/llama llama.cpp	
-
-get-sources: backend/cpp/llama/llama.cpp sources/go-llama sources/go-llama-ggml sources/go-ggml-transformers sources/gpt4all sources/go-piper sources/go-rwkv sources/whisper.cpp sources/go-bert sources/go-stable-diffusion
+get-sources: go-llama go-llama-stable go-ggllm go-ggml-transformers gpt4all go-piper go-rwkv whisper.cpp go-bert bloomz go-stable-diffusion
 	touch $@
 
 replace:
-	$(GOCMD) mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=$(shell pwd)/sources/gpt4all/gpt4all-bindings/golang
-	$(GOCMD) mod edit -replace github.com/go-skynet/go-ggml-transformers.cpp=$(shell pwd)/sources/go-ggml-transformers
-	$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(shell pwd)/sources/go-rwkv
-	$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp=$(shell pwd)/sources/whisper.cpp
-	$(GOCMD) mod edit -replace github.com/go-skynet/go-bert.cpp=$(shell pwd)/sources/go-bert
-	$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(shell pwd)/sources/go-stable-diffusion
-	$(GOCMD) mod edit -replace github.com/mudler/go-piper=$(shell pwd)/sources/go-piper
+	$(GOCMD) mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=$(shell pwd)/gpt4all/gpt4all-bindings/golang
+	$(GOCMD) mod edit -replace github.com/go-skynet/go-ggml-transformers.cpp=$(shell pwd)/go-ggml-transformers
+	$(GOCMD) mod edit -replace github.com/donomii/go-rwkv.cpp=$(shell pwd)/go-rwkv
+	$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp=$(shell pwd)/whisper.cpp
+	$(GOCMD) mod edit -replace github.com/go-skynet/go-bert.cpp=$(shell pwd)/go-bert
+	$(GOCMD) mod edit -replace github.com/go-skynet/bloomz.cpp=$(shell pwd)/bloomz
+	$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(shell pwd)/go-stable-diffusion
+	$(GOCMD) mod edit -replace github.com/mudler/go-piper=$(shell pwd)/go-piper
+	$(GOCMD) mod edit -replace github.com/mudler/go-ggllm.cpp=$(shell pwd)/go-ggllm
 
 prepare-sources: get-sources replace
 	$(GOCMD) mod download
-	touch $@
 
 ## GENERIC
 rebuild: ## Rebuilds the project
 	$(GOCMD) clean -cache
-	$(MAKE) -C sources/go-llama clean
-	$(MAKE) -C sources/go-llama-ggml clean
-	$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ clean
-	$(MAKE) -C sources/go-ggml-transformers clean
-	$(MAKE) -C sources/go-rwkv clean
-	$(MAKE) -C sources/whisper.cpp clean
-	$(MAKE) -C sources/go-stable-diffusion clean
-	$(MAKE) -C sources/go-bert clean
-	$(MAKE) -C sources/go-piper clean
+	$(MAKE) -C go-llama clean
+	$(MAKE) -C go-llama-stable clean
+	$(MAKE) -C gpt4all/gpt4all-bindings/golang/ clean
+	$(MAKE) -C go-ggml-transformers clean
+	$(MAKE) -C go-rwkv clean
+	$(MAKE) -C whisper.cpp clean
+	$(MAKE) -C go-stable-diffusion clean
+	$(MAKE) -C go-bert clean
+	$(MAKE) -C bloomz clean
+	$(MAKE) -C go-piper clean
+	$(MAKE) -C go-ggllm clean
 	$(MAKE) build
 
 prepare: prepare-sources $(OPTIONAL_TARGETS)
@@ -262,13 +265,21 @@ prepare: prepare-sources $(OPTIONAL_TARGETS)
 clean: ## Remove build related file
 	$(GOCMD) clean -cache
 	rm -f prepare
-	rm -rf ./sources
+	rm -rf ./go-llama
+	rm -rf ./gpt4all
+	rm -rf ./go-llama-stable
+	rm -rf ./go-gpt2
+	rm -rf ./go-stable-diffusion
+	rm -rf ./go-ggml-transformers
+	rm -rf ./backend-assets
+	rm -rf ./go-rwkv
+	rm -rf ./go-bert
+	rm -rf ./bloomz
+	rm -rf ./whisper.cpp
+	rm -rf ./go-piper
+	rm -rf ./go-ggllm
 	rm -rf $(BINARY_NAME)
 	rm -rf release/
-	rm -rf ./backend/cpp/grpc/grpc_repo
-	rm -rf ./backend/cpp/grpc/build
-	rm -rf ./backend/cpp/grpc/installed_packages
-	$(MAKE) -C backend/cpp/llama clean
 
 ## Build:
 
@@ -284,9 +295,6 @@ dist: build
 	mkdir -p release
 	cp $(BINARY_NAME) release/$(BINARY_NAME)-$(BUILD_ID)-$(OS)-$(ARCH)
 
-osx-signed: build
-	codesign --deep --force --sign "$(OSX_SIGNING_IDENTITY)" --entitlements "./Entitlements.plist" "./$(BINARY_NAME)"
-
 ## Run
 run: prepare ## run local-ai
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) run ./
@@ -294,12 +302,12 @@ run: prepare ## run local-ai
 test-models/testmodel:
 	mkdir test-models
 	mkdir test-dir
-	wget -q https://huggingface.co/nnakasato/ggml-model-test/resolve/main/ggml-model-q4.bin -O test-models/testmodel
-	wget -q https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
-	wget -q https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin -O test-models/bert
-	wget -q https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
-	wget -q https://huggingface.co/mudler/rwkv-4-raven-1.5B-ggml/resolve/main/RWKV-4-Raven-1B5-v11-Eng99%2525-Other1%2525-20230425-ctx4096_Q4_0.bin -O test-models/rwkv
-	wget -q https://raw.githubusercontent.com/saharNooby/rwkv.cpp/5eb8f09c146ea8124633ab041d9ea0b1f1db4459/rwkv/20B_tokenizer.json -O test-models/rwkv.tokenizer.json
+	wget https://huggingface.co/nnakasato/ggml-model-test/resolve/main/ggml-model-q4.bin -O test-models/testmodel
+	wget https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
+	wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O test-models/bert
+	wget https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
+	wget https://huggingface.co/mudler/rwkv-4-raven-1.5B-ggml/resolve/main/RWKV-4-Raven-1B5-v11-Eng99%2525-Other1%2525-20230425-ctx4096_Q4_0.bin -O test-models/rwkv
+	wget https://raw.githubusercontent.com/saharNooby/rwkv.cpp/5eb8f09c146ea8124633ab041d9ea0b1f1db4459/rwkv/20B_tokenizer.json -O test-models/rwkv.tokenizer.json
 	cp tests/models_fixtures/* test-models
 
 prepare-test: grpcs
@@ -310,34 +318,14 @@ test: prepare test-models/testmodel grpcs
 	@echo 'Running tests'
 	export GO_TAGS="tts stablediffusion"
 	$(MAKE) prepare-test
-	HUGGINGFACE_GRPC=$(abspath ./)/backend/python/sentencetransformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!gpt4all && !llama && !llama-gguf"  --flake-attempts 5 --fail-fast -v -r ./api ./pkg
+	HUGGINGFACE_GRPC=$(abspath ./)/extra/grpc/huggingface/huggingface.py TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!gpt4all && !llama && !llama-gguf" --flake-attempts 5 -v -r ./api ./pkg
 	$(MAKE) test-gpt4all
 	$(MAKE) test-llama
 	$(MAKE) test-llama-gguf
 	$(MAKE) test-tts
 	$(MAKE) test-stablediffusion
 
-prepare-e2e:
-	mkdir -p $(TEST_DIR)
-	cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml
-	test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin
-	docker build --build-arg BUILD_GRPC=true --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=11 --build-arg CUDA_MINOR_VERSION=7 --build-arg FFMPEG=true -t localai-tests .
-
-run-e2e-image:
-	ls -liah $(abspath ./tests/e2e-fixtures)
-	docker run -p 5390:8080 -e MODELS_PATH=/models -e THREADS=1 -e DEBUG=true -d --rm -v $(TEST_DIR):/models --gpus all --name e2e-tests-$(RANDOM) localai-tests
-
-test-e2e:
-	@echo 'Running e2e tests'
-	BUILD_TYPE=$(BUILD_TYPE) \
-	LOCALAI_API=http://$(E2E_BRIDGE_IP):5390/v1 \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts 5 -v -r ./tests/e2e
-
-teardown-e2e:
-	rm -rf $(TEST_DIR) || true
-	docker stop $$(docker ps -q --filter ancestor=localai-tests)
-
 test-gpt4all: prepare-test
 	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="gpt4all" --flake-attempts 5 -v -r ./api ./pkg
@@ -378,141 +366,101 @@ protogen: protogen-go protogen-python
 
 protogen-go:
 	protoc --go_out=. --go_opt=paths=source_relative --go-grpc_out=. --go-grpc_opt=paths=source_relative \
-    backend/backend.proto
+    pkg/grpc/proto/backend.proto
 
 protogen-python:
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/sentencetransformers/ --grpc_python_out=backend/python/sentencetransformers/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/transformers/ --grpc_python_out=backend/python/transformers/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/autogptq/ --grpc_python_out=backend/python/autogptq/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/exllama/ --grpc_python_out=backend/python/exllama/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/bark/ --grpc_python_out=backend/python/bark/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/diffusers/ --grpc_python_out=backend/python/diffusers/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/vall-e-x/ --grpc_python_out=backend/python/vall-e-x/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/vllm/ --grpc_python_out=backend/python/vllm/ backend/backend.proto
-	python3 -m grpc_tools.protoc -Ibackend/ --python_out=backend/python/petals/ --grpc_python_out=backend/python/petals/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/huggingface/ --grpc_python_out=extra/grpc/huggingface/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/autogptq/ --grpc_python_out=extra/grpc/autogptq/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/exllama/ --grpc_python_out=extra/grpc/exllama/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/bark/ --grpc_python_out=extra/grpc/bark/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/diffusers/ --grpc_python_out=extra/grpc/diffusers/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/vall-e-x/ --grpc_python_out=extra/grpc/vall-e-x/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/vllm/ --grpc_python_out=extra/grpc/vllm/ pkg/grpc/proto/backend.proto
 
 ## GRPC
-# Note: it is duplicated in the Dockerfile
-prepare-extra-conda-environments:
-	$(MAKE) -C backend/python/autogptq
-	$(MAKE) -C backend/python/bark
-	$(MAKE) -C backend/python/diffusers
-	$(MAKE) -C backend/python/vllm
-	$(MAKE) -C backend/python/sentencetransformers
-	$(MAKE) -C backend/python/transformers
-	$(MAKE) -C backend/python/vall-e-x
-	$(MAKE) -C backend/python/exllama
-	$(MAKE) -C backend/python/petals
-
 
 backend-assets/grpc:
 	mkdir -p backend-assets/grpc
 
-backend-assets/grpc/llama: backend-assets/grpc sources/go-llama/libbinding.a
-	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/sources/go-llama
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-llama LIBRARY_PATH=$(shell pwd)/sources/go-llama \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama ./backend/go/llm/llama/
-# TODO: every binary should have its own folder instead, so can have different  implementations
-ifeq ($(BUILD_TYPE),metal)
-	cp backend/cpp/llama/llama.cpp/ggml-metal.metal backend-assets/grpc/
-endif
+backend-assets/grpc/falcon: backend-assets/grpc go-ggllm/libggllm.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggllm LIBRARY_PATH=$(shell pwd)/go-ggllm \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/falcon ./cmd/grpc/falcon/
 
-## BACKEND CPP LLAMA START
-# Sets the variables in case it has to build the gRPC locally.
-INSTALLED_PACKAGES=$(CURDIR)/backend/cpp/grpc/installed_packages
-INSTALLED_LIB_CMAKE=$(INSTALLED_PACKAGES)/lib/cmake
-ADDED_CMAKE_ARGS=-Dabsl_DIR=${INSTALLED_LIB_CMAKE}/absl \
-                 -DProtobuf_DIR=${INSTALLED_LIB_CMAKE}/protobuf \
-                 -Dutf8_range_DIR=${INSTALLED_LIB_CMAKE}/utf8_range \
-                 -DgRPC_DIR=${INSTALLED_LIB_CMAKE}/grpc \
-                 -DCMAKE_CXX_STANDARD_INCLUDE_DIRECTORIES=${INSTALLED_PACKAGES}/include
-
-backend/cpp/llama/grpc-server:
-ifdef BUILD_GRPC_FOR_BACKEND_LLAMA
-	backend/cpp/grpc/script/build_grpc.sh ${INSTALLED_PACKAGES}
-	export _PROTOBUF_PROTOC=${INSTALLED_PACKAGES}/bin/proto && \
-	export _GRPC_CPP_PLUGIN_EXECUTABLE=${INSTALLED_PACKAGES}/bin/grpc_cpp_plugin && \
-	export PATH=${PATH}:${INSTALLED_PACKAGES}/bin && \
-	CMAKE_ARGS="${CMAKE_ARGS} ${ADDED_CMAKE_ARGS}" LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
-else
-	echo "BUILD_GRPC_FOR_BACKEND_LLAMA is not defined."
-	LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server			
-endif
-## BACKEND CPP LLAMA END
-		
-##
-backend-assets/grpc/llama-cpp: backend-assets/grpc backend/cpp/llama/grpc-server
-	cp -rfv backend/cpp/llama/grpc-server backend-assets/grpc/llama-cpp
+backend-assets/grpc/llama: backend-assets/grpc go-llama/libbinding.a
+	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/go-llama
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-llama LIBRARY_PATH=$(shell pwd)/go-llama \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama ./cmd/grpc/llama/
 # TODO: every binary should have its own folder instead, so can have different metal implementations
 ifeq ($(BUILD_TYPE),metal)
-	cp backend/cpp/llama/llama.cpp/build/bin/ggml-metal.metal backend-assets/grpc/
+	cp go-llama/build/bin/ggml-metal.metal backend-assets/grpc/
 endif
 
-backend-assets/grpc/llama-ggml: backend-assets/grpc sources/go-llama-ggml/libbinding.a
-	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/sources/go-llama-ggml
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-llama-ggml LIBRARY_PATH=$(shell pwd)/sources/go-llama-ggml \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama-ggml ./backend/go/llm/llama-ggml/
+backend-assets/grpc/llama-stable: backend-assets/grpc go-llama-stable/libbinding.a
+	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(shell pwd)/go-llama-stable
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-llama-stable LIBRARY_PATH=$(shell pwd)/go-llama \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama-stable ./cmd/grpc/llama-stable/
 
-backend-assets/grpc/gpt4all: backend-assets/grpc backend-assets/gpt4all sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/gpt4all/gpt4all-bindings/golang/ LIBRARY_PATH=$(shell pwd)/sources/gpt4all/gpt4all-bindings/golang/ \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt4all ./backend/go/llm/gpt4all/
+backend-assets/grpc/gpt4all: backend-assets/grpc backend-assets/gpt4all gpt4all/gpt4all-bindings/golang/libgpt4all.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/gpt4all/gpt4all-bindings/golang/ LIBRARY_PATH=$(shell pwd)/gpt4all/gpt4all-bindings/golang/ \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt4all ./cmd/grpc/gpt4all/
 
-backend-assets/grpc/dolly: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/dolly ./backend/go/llm/dolly/
+backend-assets/grpc/dolly: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/dolly ./cmd/grpc/dolly/
 
-backend-assets/grpc/gpt2: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt2 ./backend/go/llm/gpt2/
+backend-assets/grpc/gpt2: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gpt2 ./cmd/grpc/gpt2/
 
-backend-assets/grpc/gptj: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gptj ./backend/go/llm/gptj/
+backend-assets/grpc/gptj: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gptj ./cmd/grpc/gptj/
 
-backend-assets/grpc/gptneox: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gptneox ./backend/go/llm/gptneox/
+backend-assets/grpc/gptneox: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/gptneox ./cmd/grpc/gptneox/
 
-backend-assets/grpc/mpt: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/mpt ./backend/go/llm/mpt/
+backend-assets/grpc/mpt: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/mpt ./cmd/grpc/mpt/
 
-backend-assets/grpc/replit: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/replit ./backend/go/llm/replit/
+backend-assets/grpc/replit: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/replit ./cmd/grpc/replit/
 
-backend-assets/grpc/falcon-ggml: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/falcon-ggml ./backend/go/llm/falcon-ggml/
+backend-assets/grpc/falcon-ggml: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/falcon-ggml ./cmd/grpc/falcon-ggml/
 
-backend-assets/grpc/starcoder: backend-assets/grpc sources/go-ggml-transformers/libtransformers.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/sources/go-ggml-transformers \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/starcoder ./backend/go/llm/starcoder/
+backend-assets/grpc/starcoder: backend-assets/grpc go-ggml-transformers/libtransformers.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-ggml-transformers LIBRARY_PATH=$(shell pwd)/go-ggml-transformers \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/starcoder ./cmd/grpc/starcoder/
 
-backend-assets/grpc/rwkv: backend-assets/grpc sources/go-rwkv/librwkv.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-rwkv LIBRARY_PATH=$(shell pwd)/sources/go-rwkv \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/rwkv ./backend/go/llm/rwkv
+backend-assets/grpc/rwkv: backend-assets/grpc go-rwkv/librwkv.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-rwkv LIBRARY_PATH=$(shell pwd)/go-rwkv \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/rwkv ./cmd/grpc/rwkv/
 
-backend-assets/grpc/bert-embeddings: backend-assets/grpc sources/go-bert/libgobert.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-bert LIBRARY_PATH=$(shell pwd)/sources/go-bert \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/bert-embeddings ./backend/go/llm/bert/
+backend-assets/grpc/bloomz: backend-assets/grpc bloomz/libbloomz.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/bloomz LIBRARY_PATH=$(shell pwd)/bloomz \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/bloomz ./cmd/grpc/bloomz/
+
+backend-assets/grpc/bert-embeddings: backend-assets/grpc go-bert/libgobert.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-bert LIBRARY_PATH=$(shell pwd)/go-bert \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/bert-embeddings ./cmd/grpc/bert-embeddings/
 
 backend-assets/grpc/langchain-huggingface: backend-assets/grpc
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/langchain-huggingface ./backend/go/llm/langchain/
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/langchain-huggingface ./cmd/grpc/langchain-huggingface/
 
-backend-assets/grpc/stablediffusion: backend-assets/grpc
-	if [ ! -f backend-assets/grpc/stablediffusion ]; then \
-		$(MAKE) sources/go-stable-diffusion/libstablediffusion.a; \
-		CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/go-stable-diffusion/ LIBRARY_PATH=$(shell pwd)/sources/go-stable-diffusion/ \
-		$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion ./backend/go/image/; \
-	fi
+backend-assets/grpc/stablediffusion: backend-assets/grpc go-stable-diffusion/libstablediffusion.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/go-stable-diffusion/ LIBRARY_PATH=$(shell pwd)/go-stable-diffusion/ \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion ./cmd/grpc/stablediffusion/
 
-backend-assets/grpc/piper: backend-assets/grpc backend-assets/espeak-ng-data sources/go-piper/libpiper_binding.a
-	CGO_CXXFLAGS="$(PIPER_CGO_CXXFLAGS)" CGO_LDFLAGS="$(PIPER_CGO_LDFLAGS)" LIBRARY_PATH=$(shell pwd)/sources/go-piper \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/piper ./backend/go/tts/
+backend-assets/grpc/piper: backend-assets/grpc backend-assets/espeak-ng-data go-piper/libpiper_binding.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" LIBRARY_PATH=$(shell pwd)/go-piper \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/piper ./cmd/grpc/piper/
 
-backend-assets/grpc/whisper: backend-assets/grpc sources/whisper.cpp/libwhisper.a
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/sources/whisper.cpp LIBRARY_PATH=$(shell pwd)/sources/whisper.cpp \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/whisper ./backend/go/transcribe/
+backend-assets/grpc/whisper: backend-assets/grpc whisper.cpp/libwhisper.a
+	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(shell pwd)/whisper.cpp LIBRARY_PATH=$(shell pwd)/whisper.cpp \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/whisper ./cmd/grpc/whisper/
 
 grpcs: prepare $(GRPC_BACKENDS)

README.md

@@ -22,13 +22,14 @@
 
 > :bulb: Get help - [❓FAQ](https://localai.io/faq/) [💭Discussions](https://github.com/go-skynet/LocalAI/discussions) [:speech_balloon: Discord](https://discord.gg/uJAeKSAGDy) [:book: Documentation website](https://localai.io/)
 > 
-> [💻 Quickstart](https://localai.io/basics/getting_started/) [📣 News](https://localai.io/basics/news/) [ 🛫 Examples ](https://github.com/go-skynet/LocalAI/tree/master/examples/) [ 🖼️ Models ](https://localai.io/models/) [ 🚀 Roadmap ](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
+> [💻 Quickstart](https://localai.io/basics/getting_started/) [📣 News](https://localai.io/basics/news/) [ 🛫 Examples ](https://github.com/go-skynet/LocalAI/tree/master/examples/) [ 🖼️ Models ](https://localai.io/models/)
+
 
 [![tests](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml)[![Build and Release](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml)[![build container images](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml)[![Bump dependencies](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml)[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/localai)](https://artifacthub.io/packages/search?repo=localai)
 
-**LocalAI** is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that’s compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families. Does not require GPU.
+**LocalAI** is a drop-in replacement REST API that's compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families that are compatible with the ggml format, pytorch and more. Does not require GPU.
 
-<p  align="center"><b>Follow LocalAI </b></p>
+<p align="center"><b>Follow LocalAI </b></p>
 
 <p align="center">
 <a href="https://twitter.com/LocalAI_API" target="blank">
@@ -38,7 +39,7 @@
 <img src="https://dcbadge.vercel.app/api/server/uJAeKSAGDy?style=flat-square&theme=default-inverted" alt="Join LocalAI Discord Community"/>
 </a>
 
-<p  align="center"><b>Connect with the Creator </b></p>
+<p align="center"><b>Connect with the Creator </b></p>
 
 <p align="center">
 <a href="https://twitter.com/mudler_it" target="blank">
@@ -49,7 +50,7 @@
 </a>
 </p>
 
-<p  align="center"><b>Share LocalAI Repository</b></p>
+<p align="center"><b>Share LocalAI Repository</b></p>
 
 <p align="center">
 
@@ -63,22 +64,6 @@
 
 </p>
 
-## 💻 [Getting started](https://localai.io/basics/getting_started/index.html)
-
-## 🔥🔥 Hot topics / Roadmap
-
-[Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
-
-🆕 New! [LLM finetuning guide](https://localai.io/advanced/fine-tuning/)
-
-Hot topics (looking for contributors):
-- Backends v2: https://github.com/mudler/LocalAI/issues/1126
-- Improving UX v2: https://github.com/mudler/LocalAI/issues/1373
-
-If you want to help and contribute, issues up for grabs: https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3A%22up+for+grabs%22
-
-
-
 <hr>
 
 In a nutshell:
@@ -94,6 +79,8 @@ LocalAI was created by [Ettore Di Giacinto](https://github.com/mudler/) and is a
 
 Note that this started just as a [fun weekend project](https://localai.io/#backstory) in order to try to create the necessary pieces for a full AI assistant like `ChatGPT`: the community is growing fast and we are working hard to make it better and more stable. If you want to help, please consider contributing (see below)!
 
+## 🔥🔥 [Hot topics / Roadmap](https://localai.io/#-hot-topics--roadmap)
+
 ## 🚀 [Features](https://localai.io/features/)
 
 - 📖 [Text generation with GPTs](https://localai.io/features/text-generation/) (`llama.cpp`, `gpt4all.cpp`, ... [:book: and more](https://localai.io/model-compatibility/index.html#model-compatibility-table))
@@ -104,32 +91,8 @@ Note that this started just as a [fun weekend project](https://localai.io/#backs
 - 🧠 [Embeddings generation for vector databases](https://localai.io/features/embeddings/)
 - ✍️ [Constrained grammars](https://localai.io/features/constrained_grammars/)
 - 🖼️ [Download Models directly from Huggingface ](https://localai.io/models/)
-- 🆕 [Vision API](https://localai.io/features/gpt-vision/)
 
-## 💻 Usage
 
-Check out the [Getting started](https://localai.io/basics/getting_started/index.html) section in our documentation.
-
-### 🔗 Community and integrations
-
-WebUIs:
-- https://github.com/Jirubizu/localai-admin
-- https://github.com/go-skynet/LocalAI-frontend
-
-Model galleries
-- https://github.com/go-skynet/model-gallery
-
-Other:
-- Helm chart https://github.com/go-skynet/helm-charts
-
-### 🔗 Resources
-
-- 🆕 New! [LLM finetuning guide](https://localai.io/advanced/fine-tuning/)
-- [How to build locally](https://localai.io/basics/build/index.html)
-- [How to install in Kubernetes](https://localai.io/basics/getting_started/index.html#run-localai-in-kubernetes)
-- [Projects integrating LocalAI](https://localai.io/integrations/)
-- [How tos section](https://localai.io/howtos/) (curated by our community)
-  
 ## :book: 🎥 [Media, Blogs, Social](https://localai.io/basics/news/#media-blogs-social)
 
 - [Create a slackbot for teams and OSS projects that answer to documentation](https://mudler.pm/posts/smart-slackbot-for-teams/)
@@ -137,6 +100,21 @@ Other:
 - [Question Answering on Documents locally with LangChain, LocalAI, Chroma, and GPT4All](https://mudler.pm/posts/localai-question-answering/)
 - [Tutorial to use k8sgpt with LocalAI](https://medium.com/@tyler_97636/k8sgpt-localai-unlock-kubernetes-superpowers-for-free-584790de9b65)
 
+## 💻 Usage
+
+Check out the [Getting started](https://localai.io/basics/getting_started/index.html) section in our documentation.
+
+### 💡 Example: Use Luna-AI Llama model
+
+See the [documentation](https://localai.io/basics/getting_started)
+
+### 🔗 Resources
+
+- [How to build locally](https://localai.io/basics/build/index.html)
+- [How to install in Kubernetes](https://localai.io/basics/getting_started/index.html#run-localai-in-kubernetes)
+- [Projects integrating LocalAI](https://localai.io/integrations/)
+- [How tos section](https://localai.io/howtos/) (curated by our community)
+  
 ## Citation
 
 If you utilize this repository, data in a downstream project, please consider citing it with:

api/api.go

@@ -11,9 +11,7 @@ import (
 	"github.com/go-skynet/LocalAI/api/options"
 	"github.com/go-skynet/LocalAI/api/schema"
 	"github.com/go-skynet/LocalAI/internal"
-	"github.com/go-skynet/LocalAI/metrics"
 	"github.com/go-skynet/LocalAI/pkg/assets"
-	"github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/fiber/v2/middleware/cors"
@@ -80,22 +78,6 @@ func Startup(opts ...options.AppOption) (*options.Option, *config.ConfigLoader,
 		options.Loader.StopAllGRPC()
 	}()
 
-	if options.WatchDog {
-		wd := model.NewWatchDog(
-			options.Loader,
-			options.WatchDogBusyTimeout,
-			options.WatchDogIdleTimeout,
-			options.WatchDogBusy,
-			options.WatchDogIdle)
-		options.Loader.SetWatchDog(wd)
-		go wd.Run()
-		go func() {
-			<-options.Context.Done()
-			log.Debug().Msgf("Context canceled, shutting down")
-			wd.Shutdown()
-		}()
-	}
-
 	return options, cl, nil
 }
 
@@ -138,9 +120,6 @@ func App(opts ...options.AppOption) (*fiber.App, error) {
 
 	// Default middleware config
 	app.Use(recover.New())
-	if options.Metrics != nil {
-		app.Use(metrics.APIMiddleware(options.Metrics))
-	}
 
 	// Auth middleware checking if API key is valid. If no API key is set, no auth is required.
 	auth := func(c *fiber.Ctx) error {
@@ -250,7 +229,5 @@ func App(opts ...options.AppOption) (*fiber.App, error) {
 	app.Get("/v1/models", auth, openai.ListModelsEndpoint(options.Loader, cl))
 	app.Get("/models", auth, openai.ListModelsEndpoint(options.Loader, cl))
 
-	app.Get("/metrics", metrics.MetricsHandler())
-
 	return app, nil
 }

api/api_test.go

@@ -15,7 +15,6 @@ import (
 
 	. "github.com/go-skynet/LocalAI/api"
 	"github.com/go-skynet/LocalAI/api/options"
-	"github.com/go-skynet/LocalAI/metrics"
 	"github.com/go-skynet/LocalAI/pkg/gallery"
 	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/go-skynet/LocalAI/pkg/utils"
@@ -163,12 +162,8 @@ var _ = Describe("API test", func() {
 				},
 			}
 
-			metricsService, err := metrics.SetupMetrics()
-			Expect(err).ToNot(HaveOccurred())
-
 			app, err = App(
 				append(commonOpts,
-					options.WithMetrics(metricsService),
 					options.WithContext(c),
 					options.WithGalleries(galleries),
 					options.WithModelLoader(modelLoader), options.WithBackendAssets(backendAssets), options.WithBackendAssetsOutput(tmpdir))...)
@@ -301,7 +296,7 @@ var _ = Describe("API test", func() {
 				response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
 					URL:       "github:go-skynet/model-gallery/openllama_3b.yaml",
 					Name:      "openllama_3b",
-					Overrides: map[string]interface{}{"backend": "llama-ggml", "mmap": true, "f16": true, "context_size": 128},
+					Overrides: map[string]interface{}{"backend": "llama-stable", "mmap": true, "f16": true, "context_size": 128},
 				})
 
 				Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
@@ -457,7 +452,7 @@ var _ = Describe("API test", func() {
 				Eventually(func() bool {
 					response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
 					return response["processed"].(bool)
-				}, "960s", "10s").Should(Equal(true))
+				}, "360s", "10s").Should(Equal(true))
 
 				resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "gpt4all-j", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: "How are you?"}}})
 				Expect(err).ToNot(HaveOccurred())
@@ -484,13 +479,9 @@ var _ = Describe("API test", func() {
 				},
 			}
 
-			metricsService, err := metrics.SetupMetrics()
-			Expect(err).ToNot(HaveOccurred())
-
 			app, err = App(
 				append(commonOpts,
 					options.WithContext(c),
-					options.WithMetrics(metricsService),
 					options.WithAudioDir(tmpdir),
 					options.WithImageDir(tmpdir),
 					options.WithGalleries(galleries),
@@ -592,15 +583,12 @@ var _ = Describe("API test", func() {
 			modelLoader = model.NewModelLoader(os.Getenv("MODELS_PATH"))
 			c, cancel = context.WithCancel(context.Background())
 
-			metricsService, err := metrics.SetupMetrics()
-			Expect(err).ToNot(HaveOccurred())
-
+			var err error
 			app, err = App(
 				append(commonOpts,
 					options.WithExternalBackend("huggingface", os.Getenv("HUGGINGFACE_GRPC")),
 					options.WithContext(c),
 					options.WithModelLoader(modelLoader),
-					options.WithMetrics(metricsService),
 				)...)
 			Expect(err).ToNot(HaveOccurred())
 			go app.Listen("127.0.0.1:9090")
@@ -687,7 +675,7 @@ var _ = Describe("API test", func() {
 					Input: []string{"sun", "cat"},
 				},
 			)
-			Expect(err).ToNot(HaveOccurred(), err)
+			Expect(err).ToNot(HaveOccurred())
 			Expect(len(resp.Data[0].Embedding)).To(BeNumerically("==", 384))
 			Expect(len(resp.Data[1].Embedding)).To(BeNumerically("==", 384))
 
@@ -704,7 +692,7 @@ var _ = Describe("API test", func() {
 		})
 
 		Context("External gRPC calls", func() {
-			It("calculate embeddings with sentencetransformers", func() {
+			It("calculate embeddings with huggingface", func() {
 				if runtime.GOOS != "linux" {
 					Skip("test supported only on linux")
 				}
@@ -804,13 +792,10 @@ var _ = Describe("API test", func() {
 			modelLoader = model.NewModelLoader(os.Getenv("MODELS_PATH"))
 			c, cancel = context.WithCancel(context.Background())
 
-			metricsService, err := metrics.SetupMetrics()
-			Expect(err).ToNot(HaveOccurred())
-
+			var err error
 			app, err = App(
 				append(commonOpts,
 					options.WithContext(c),
-					options.WithMetrics(metricsService),
 					options.WithModelLoader(modelLoader),
 					options.WithConfigFile(os.Getenv("CONFIG_FILE")))...,
 			)

api/backend/image.go

@@ -21,7 +21,6 @@ func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negat
 			PipelineType:  c.Diffusers.PipelineType,
 			CFGScale:      c.Diffusers.CFGScale,
 			LoraAdapter:   c.LoraAdapter,
-			LoraScale:     c.LoraScale,
 			LoraBase:      c.LoraBase,
 			IMG2IMG:       c.Diffusers.IMG2IMG,
 			CLIPModel:     c.Diffusers.ClipModel,

api/backend/llm.go

@@ -26,7 +26,7 @@ type TokenUsage struct {
 	Completion int
 }
 
-func ModelInference(ctx context.Context, s string, images []string, loader *model.ModelLoader, c config.Config, o *options.Option, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
+func ModelInference(ctx context.Context, s string, loader *model.ModelLoader, c config.Config, o *options.Option, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
 	modelFile := c.Model
 
 	grpcOpts := gRPCModelOpts(c)
@@ -72,7 +72,6 @@ func ModelInference(ctx context.Context, s string, images []string, loader *mode
 	fn := func() (LLMResponse, error) {
 		opts := gRPCPredictOpts(c, loader.ModelPath)
 		opts.Prompt = s
-		opts.Images = images
 
 		tokenUsage := TokenUsage{}
 

api/backend/options.go

@@ -16,10 +16,6 @@ func modelOpts(c config.Config, o *options.Option, opts []model.Option) []model.
 		opts = append(opts, model.WithSingleActiveBackend())
 	}
 
-	if o.ParallelBackendRequests {
-		opts = append(opts, model.EnableParallelRequests)
-	}
-
 	if c.GRPC.Attempts != 0 {
 		opts = append(opts, model.WithGRPCAttempts(c.GRPC.Attempts))
 	}
@@ -42,35 +38,29 @@ func gRPCModelOpts(c config.Config) *pb.ModelOptions {
 	}
 
 	return &pb.ModelOptions{
-		ContextSize:    int32(c.ContextSize),
-		Seed:           int32(c.Seed),
-		NBatch:         int32(b),
-		NoMulMatQ:      c.NoMulMatQ,
-		DraftModel:     c.DraftModel,
-		AudioPath:      c.VallE.AudioPath,
-		Quantization:   c.Quantization,
-		MMProj:         c.MMProj,
-		YarnExtFactor:  c.YarnExtFactor,
-		YarnAttnFactor: c.YarnAttnFactor,
-		YarnBetaFast:   c.YarnBetaFast,
-		YarnBetaSlow:   c.YarnBetaSlow,
-		LoraAdapter:    c.LoraAdapter,
-		LoraBase:       c.LoraBase,
-		LoraScale:      c.LoraScale,
-		NGQA:           c.NGQA,
-		RMSNormEps:     c.RMSNormEps,
-		F16Memory:      c.F16,
-		MLock:          c.MMlock,
-		RopeFreqBase:   c.RopeFreqBase,
-		RopeFreqScale:  c.RopeFreqScale,
-		NUMA:           c.NUMA,
-		Embeddings:     c.Embeddings,
-		LowVRAM:        c.LowVRAM,
-		NGPULayers:     int32(c.NGPULayers),
-		MMap:           c.MMap,
-		MainGPU:        c.MainGPU,
-		Threads:        int32(c.Threads),
-		TensorSplit:    c.TensorSplit,
+		ContextSize:   int32(c.ContextSize),
+		Seed:          int32(c.Seed),
+		NBatch:        int32(b),
+		NoMulMatQ:     c.NoMulMatQ,
+		DraftModel:    c.DraftModel,
+		AudioPath:     c.VallE.AudioPath,
+		Quantization:  c.Quantization,
+		LoraAdapter:   c.LoraAdapter,
+		LoraBase:      c.LoraBase,
+		NGQA:          c.NGQA,
+		RMSNormEps:    c.RMSNormEps,
+		F16Memory:     c.F16,
+		MLock:         c.MMlock,
+		RopeFreqBase:  c.RopeFreqBase,
+		RopeFreqScale: c.RopeFreqScale,
+		NUMA:          c.NUMA,
+		Embeddings:    c.Embeddings,
+		LowVRAM:       c.LowVRAM,
+		NGPULayers:    int32(c.NGPULayers),
+		MMap:          c.MMap,
+		MainGPU:       c.MainGPU,
+		Threads:       int32(c.Threads),
+		TensorSplit:   c.TensorSplit,
 		// AutoGPTQ
 		ModelBaseName:    c.AutoGPTQ.ModelBaseName,
 		Device:           c.AutoGPTQ.Device,

api/config/config.go

@@ -100,18 +100,10 @@ type LLMConfig struct {
 	NUMA            bool     `yaml:"numa"`
 	LoraAdapter     string   `yaml:"lora_adapter"`
 	LoraBase        string   `yaml:"lora_base"`
-	LoraScale       float32  `yaml:"lora_scale"`
 	NoMulMatQ       bool     `yaml:"no_mulmatq"`
 	DraftModel      string   `yaml:"draft_model"`
 	NDraft          int32    `yaml:"n_draft"`
 	Quantization    string   `yaml:"quantization"`
-	MMProj          string   `yaml:"mmproj"`
-
-	RopeScaling    string  `yaml:"rope_scaling"`
-	YarnExtFactor  float32 `yaml:"yarn_ext_factor"`
-	YarnAttnFactor float32 `yaml:"yarn_attn_factor"`
-	YarnBetaFast   float32 `yaml:"yarn_beta_fast"`
-	YarnBetaSlow   float32 `yaml:"yarn_beta_slow"`
 }
 
 type AutoGPTQ struct {
@@ -277,7 +269,7 @@ func (cm *ConfigLoader) LoadConfigs(path string) error {
 	}
 	for _, file := range files {
 		// Skip templates, YAML and .keep files
-		if !strings.Contains(file.Name(), ".yaml") && !strings.Contains(file.Name(), ".yml") {
+		if !strings.Contains(file.Name(), ".yaml") {
 			continue
 		}
 		c, err := ReadConfig(filepath.Join(path, file.Name()))

api/localai/backend_monitor.go

@@ -123,12 +123,13 @@ func BackendMonitorEndpoint(bm BackendMonitor) func(c *fiber.Ctx) error {
 			return err
 		}
 
-		model := bm.options.Loader.CheckIsLoaded(backendId)
-		if model == "" {
+		client := bm.options.Loader.CheckIsLoaded(backendId)
+
+		if client == nil {
 			return fmt.Errorf("backend %s is not currently loaded", backendId)
 		}
 
-		status, rpcErr := model.GRPC(false, nil).Status(context.TODO())
+		status, rpcErr := client.Status(context.TODO())
 		if rpcErr != nil {
 			log.Warn().Msgf("backend %s experienced an error retrieving status info: %s", backendId, rpcErr.Error())
 			val, slbErr := bm.SampleLocalBackendProcess(backendId)

api/openai/chat.go

@@ -81,10 +81,6 @@ func ChatEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fiber.Ctx)
 			noActionDescription = config.FunctionsConfig.NoActionDescriptionName
 		}
 
-		if input.ResponseFormat.Type == "json_object" {
-			input.Grammar = grammar.JSONBNF
-		}
-
 		// process functions if we have any defined or if we have a function call string
 		if len(input.Functions) > 0 && config.ShouldUseFunctions() {
 			log.Debug().Msgf("Response needs to process functions")
@@ -144,14 +140,14 @@ func ChatEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fiber.Ctx)
 				}
 			}
 			r := config.Roles[role]
-			contentExists := i.Content != nil && i.StringContent != ""
+			contentExists := i.Content != nil && *i.Content != ""
 			// First attempt to populate content via a chat message specific template
 			if config.TemplateConfig.ChatMessage != "" {
 				chatMessageData := model.ChatMessageTemplateData{
 					SystemPrompt: config.SystemPrompt,
 					Role:         r,
 					RoleName:     role,
-					Content:      i.StringContent,
+					Content:      *i.Content,
 					MessageIndex: messageIndex,
 				}
 				templatedChatMessage, err := o.Loader.EvaluateTemplateForChatMessage(config.TemplateConfig.ChatMessage, chatMessageData)
@@ -170,7 +166,7 @@ func ChatEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fiber.Ctx)
 			if content == "" {
 				if r != "" {
 					if contentExists {
-						content = fmt.Sprint(r, i.StringContent)
+						content = fmt.Sprint(r, " ", *i.Content)
 					}
 					if i.FunctionCall != nil {
 						j, err := json.Marshal(i.FunctionCall)
@@ -184,7 +180,7 @@ func ChatEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fiber.Ctx)
 					}
 				} else {
 					if contentExists {
-						content = fmt.Sprint(i.StringContent)
+						content = fmt.Sprint(*i.Content)
 					}
 					if i.FunctionCall != nil {
 						j, err := json.Marshal(i.FunctionCall)
@@ -338,11 +334,7 @@ func ChatEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fiber.Ctx)
 					// Otherwise ask the LLM to understand the JSON output and the context, and return a message
 					// Note: This costs (in term of CPU) another computation
 					config.Grammar = ""
-					images := []string{}
-					for _, m := range input.Messages {
-						images = append(images, m.StringImages...)
-					}
-					predFunc, err := backend.ModelInference(input.Context, predInput, images, o.Loader, *config, o, nil)
+					predFunc, err := backend.ModelInference(input.Context, predInput, o.Loader, *config, o, nil)
 					if err != nil {
 						log.Error().Msgf("inference error: %s", err.Error())
 						return

api/openai/completion.go

@@ -12,7 +12,6 @@ import (
 	config "github.com/go-skynet/LocalAI/api/config"
 	"github.com/go-skynet/LocalAI/api/options"
 	"github.com/go-skynet/LocalAI/api/schema"
-	"github.com/go-skynet/LocalAI/pkg/grammar"
 	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
@@ -65,10 +64,6 @@ func CompletionEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fibe
 			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
 
-		if input.ResponseFormat.Type == "json_object" {
-			input.Grammar = grammar.JSONBNF
-		}
-
 		log.Debug().Msgf("Parameter Config: %+v", config)
 
 		if input.Stream {

api/openai/image.go

@@ -100,7 +100,7 @@ func ImageEndpoint(cm *config.ConfigLoader, o *options.Option) func(c *fiber.Ctx
 		}
 
 		b64JSON := false
-		if input.ResponseFormat.Type == "b64_json" {
+		if input.ResponseFormat == "b64_json" {
 			b64JSON = true
 		}
 		// src and clip_skip

api/openai/inference.go

@@ -23,13 +23,8 @@ func ComputeChoices(
 		n = 1
 	}
 
-	images := []string{}
-	for _, m := range req.Messages {
-		images = append(images, m.StringImages...)
-	}
-
 	// get the model function to call for the result
-	predFunc, err := backend.ModelInference(req.Context, predInput, images, loader, *config, o, tokenCallback)
+	predFunc, err := backend.ModelInference(req.Context, predInput, loader, *config, o, tokenCallback)
 	if err != nil {
 		return result, backend.TokenUsage{}, err
 	}

api/openai/request.go

@@ -2,11 +2,8 @@ package openai
 
 import (
 	"context"
-	"encoding/base64"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
-	"net/http"
 	"os"
 	"path/filepath"
 	"strings"
@@ -27,7 +24,7 @@ func readInput(c *fiber.Ctx, o *options.Option, randomModel bool) (string, *sche
 	input.Cancel = cancel
 	// Get input data from the request body
 	if err := c.BodyParser(input); err != nil {
-		return "", nil, fmt.Errorf("failed parsing request body: %w", err)
+		return "", nil, err
 	}
 
 	modelFile := input.Model
@@ -64,37 +61,6 @@ func readInput(c *fiber.Ctx, o *options.Option, randomModel bool) (string, *sche
 	return modelFile, input, nil
 }
 
-// this function check if the string is an URL, if it's an URL downloads the image in memory
-// encodes it in base64 and returns the base64 string
-func getBase64Image(s string) (string, error) {
-	if strings.HasPrefix(s, "http") {
-		// download the image
-		resp, err := http.Get(s)
-		if err != nil {
-			return "", err
-		}
-		defer resp.Body.Close()
-
-		// read the image data into memory
-		data, err := ioutil.ReadAll(resp.Body)
-		if err != nil {
-			return "", err
-		}
-
-		// encode the image data in base64
-		encoded := base64.StdEncoding.EncodeToString(data)
-
-		// return the base64 string
-		return encoded, nil
-	}
-
-	// if the string instead is prefixed with "data:image/jpeg;base64,", drop it
-	if strings.HasPrefix(s, "data:image/jpeg;base64,") {
-		return strings.ReplaceAll(s, "data:image/jpeg;base64,", ""), nil
-	}
-	return "", fmt.Errorf("not valid string")
-}
-
 func updateConfig(config *config.Config, input *schema.OpenAIRequest) {
 	if input.Echo {
 		config.Echo = input.Echo
@@ -163,35 +129,6 @@ func updateConfig(config *config.Config, input *schema.OpenAIRequest) {
 		}
 	}
 
-	// Decode each request's message content
-	index := 0
-	for i, m := range input.Messages {
-		switch content := m.Content.(type) {
-		case string:
-			input.Messages[i].StringContent = content
-		case []interface{}:
-			dat, _ := json.Marshal(content)
-			c := []schema.Content{}
-			json.Unmarshal(dat, &c)
-			for _, pp := range c {
-				if pp.Type == "text" {
-					input.Messages[i].StringContent = pp.Text
-				} else if pp.Type == "image_url" {
-					// Detect if pp.ImageURL is an URL, if it is download the image and encode it in base64:
-					base64, err := getBase64Image(pp.ImageURL.URL)
-					if err == nil {
-						input.Messages[i].StringImages = append(input.Messages[i].StringImages, base64) // TODO: make sure that we only return base64 stuff
-						// set a placeholder for each image
-						input.Messages[i].StringContent = fmt.Sprintf("[img-%d]", index) + input.Messages[i].StringContent
-						index++
-					} else {
-						fmt.Print("Failed encoding image", err)
-					}
-				}
-			}
-		}
-	}
-
 	if input.RepeatPenalty != 0 {
 		config.RepeatPenalty = input.RepeatPenalty
 	}

api/options/options.go

@@ -4,9 +4,7 @@ import (
 	"context"
 	"embed"
 	"encoding/json"
-	"time"
 
-	"github.com/go-skynet/LocalAI/metrics"
 	"github.com/go-skynet/LocalAI/pkg/gallery"
 	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
@@ -26,7 +24,6 @@ type Option struct {
 	PreloadModelsFromPath               string
 	CORSAllowOrigins                    string
 	ApiKeys                             []string
-	Metrics                             *metrics.Metrics
 
 	Galleries []gallery.Gallery
 
@@ -37,13 +34,7 @@ type Option struct {
 
 	AutoloadGalleries bool
 
-	SingleBackend           bool
-	ParallelBackendRequests bool
-
-	WatchDogIdle                             bool
-	WatchDogBusy                             bool
-	WatchDog                                 bool
-	WatchDogBusyTimeout, WatchDogIdleTimeout time.Duration
+	SingleBackend bool
 }
 
 type AppOption func(*Option)
@@ -69,40 +60,10 @@ func WithCors(b bool) AppOption {
 	}
 }
 
-var EnableWatchDog = func(o *Option) {
-	o.WatchDog = true
-}
-
-var EnableWatchDogIdleCheck = func(o *Option) {
-	o.WatchDog = true
-	o.WatchDogIdle = true
-}
-
-var EnableWatchDogBusyCheck = func(o *Option) {
-	o.WatchDog = true
-	o.WatchDogBusy = true
-}
-
-func SetWatchDogBusyTimeout(t time.Duration) AppOption {
-	return func(o *Option) {
-		o.WatchDogBusyTimeout = t
-	}
-}
-
-func SetWatchDogIdleTimeout(t time.Duration) AppOption {
-	return func(o *Option) {
-		o.WatchDogIdleTimeout = t
-	}
-}
-
 var EnableSingleBackend = func(o *Option) {
 	o.SingleBackend = true
 }
 
-var EnableParallelBackendRequests = func(o *Option) {
-	o.ParallelBackendRequests = true
-}
-
 var EnableGalleriesAutoload = func(o *Option) {
 	o.AutoloadGalleries = true
 }
@@ -237,9 +198,3 @@ func WithApiKeys(apiKeys []string) AppOption {
 		o.ApiKeys = apiKeys
 	}
 }
-
-func WithMetrics(meter *metrics.Metrics) AppOption {
-	return func(o *Option) {
-		o.Metrics = meter
-	}
-}

api/schema/openai.go

@@ -55,25 +55,11 @@ type Choice struct {
 	Text         string   `json:"text,omitempty"`
 }
 
-type Content struct {
-	Type     string     `json:"type" yaml:"type"`
-	Text     string     `json:"text" yaml:"text"`
-	ImageURL ContentURL `json:"image_url" yaml:"image_url"`
-}
-
-type ContentURL struct {
-	URL string `json:"url" yaml:"url"`
-}
-
 type Message struct {
 	// The message role
 	Role string `json:"role,omitempty" yaml:"role"`
 	// The message content
-	Content interface{} `json:"content" yaml:"content"`
-
-	StringContent string   `json:"string_content,omitempty" yaml:"string_content,omitempty"`
-	StringImages  []string `json:"string_images,omitempty" yaml:"string_images,omitempty"`
-
+	Content *string `json:"content" yaml:"content"`
 	// A result of a function call
 	FunctionCall interface{} `json:"function_call,omitempty" yaml:"function_call,omitempty"`
 }
@@ -83,12 +69,6 @@ type OpenAIModel struct {
 	Object string `json:"object"`
 }
 
-type ChatCompletionResponseFormatType string
-
-type ChatCompletionResponseFormat struct {
-	Type ChatCompletionResponseFormatType `json:"type,omitempty"`
-}
-
 type OpenAIRequest struct {
 	config.PredictionOptions
 
@@ -98,7 +78,7 @@ type OpenAIRequest struct {
 	// whisper
 	File string `json:"file" validate:"required"`
 	//whisper/image
-	ResponseFormat ChatCompletionResponseFormat `json:"response_format"`
+	ResponseFormat string `json:"response_format"`
 	// image
 	Size string `json:"size"`
 	// Prompt is read only by completion/image API calls

backend/cpp/grpc/.gitignore

@@ -1,3 +0,0 @@
-installed_packages/
-grpc_build/
-grpc_repo/

backend/cpp/grpc/script/build_grpc.sh

@@ -1,81 +0,0 @@
-#!/bin/bash
-
-# Builds locally from sources the packages needed by the llama cpp backend.
-
-# Makes sure a few base packages exist.
-# sudo apt-get --no-upgrade -y install g++ gcc binutils cmake git build-essential autoconf libtool pkg-config 
-
-SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )"
-echo "Script directory: $SCRIPT_DIR"
-
-CPP_INSTALLED_PACKAGES_DIR=$1
-if [ -z ${CPP_INSTALLED_PACKAGES_DIR} ]; then 
-    echo "CPP_INSTALLED_PACKAGES_DIR env variable not set. Don't know where to install: failed."; 
-    echo
-    exit -1
-fi
-
-if [ -d "${CPP_INSTALLED_PACKAGES_DIR}" ]; then
-  echo "gRPC installation directory already exists. Nothing to do."
-  exit 0
-fi
-
-# The depth when cloning a git repo. 1 speeds up the clone when the repo history is not needed.
-GIT_CLONE_DEPTH=1
-
-NUM_BUILD_THREADS=$(nproc --ignore=1)
-
-# Google gRPC --------------------------------------------------------------------------------------
-TAG_LIB_GRPC="v1.59.0"
-GIT_REPO_LIB_GRPC="https://github.com/grpc/grpc.git"
-GRPC_REPO_DIR="${SCRIPT_DIR}/../grpc_repo"
-GRPC_BUILD_DIR="${SCRIPT_DIR}/../grpc_build"
-SRC_DIR_LIB_GRPC="${GRPC_REPO_DIR}/grpc"
-
-echo "SRC_DIR_LIB_GRPC: ${SRC_DIR_LIB_GRPC}"
-echo "GRPC_REPO_DIR: ${GRPC_REPO_DIR}"
-echo "GRPC_BUILD_DIR: ${GRPC_BUILD_DIR}"
-
-mkdir -pv ${GRPC_REPO_DIR}
-
-rm   -rf ${GRPC_BUILD_DIR}
-mkdir -pv ${GRPC_BUILD_DIR}
-
-mkdir -pv ${CPP_INSTALLED_PACKAGES_DIR}
-	
-if [ -d "${SRC_DIR_LIB_GRPC}" ]; then
-  echo "gRPC source already exists locally. Not cloned again."
-else  
-  ( cd ${GRPC_REPO_DIR} && \
-    git clone --depth ${GIT_CLONE_DEPTH} -b ${TAG_LIB_GRPC} ${GIT_REPO_LIB_GRPC} && \
-    cd ${SRC_DIR_LIB_GRPC} && \
-    git submodule update --init --recursive --depth ${GIT_CLONE_DEPTH} 
-  )    
-fi
-
-( cd ${GRPC_BUILD_DIR} && \
-  cmake -G "Unix Makefiles" \
-     -DCMAKE_BUILD_TYPE=Release \
-     -DgRPC_INSTALL=ON \
-     -DEXECUTABLE_OUTPUT_PATH=${CPP_INSTALLED_PACKAGES_DIR}/grpc/bin \
-     -DLIBRARY_OUTPUT_PATH=${CPP_INSTALLED_PACKAGES_DIR}/grpc/lib \
-     -DgRPC_BUILD_TESTS=OFF \
-     -DgRPC_BUILD_CSHARP_EXT=OFF \
-     -DgRPC_BUILD_GRPC_CPP_PLUGIN=ON \
-     -DgRPC_BUILD_GRPC_CSHARP_PLUGIN=OFF \
-     -DgRPC_BUILD_GRPC_NODE_PLUGIN=OFF \
-     -DgRPC_BUILD_GRPC_OBJECTIVE_C_PLUGIN=OFF \
-     -DgRPC_BUILD_GRPC_PHP_PLUGIN=OFF \
-     -DgRPC_BUILD_GRPC_PYTHON_PLUGIN=ON \
-     -DgRPC_BUILD_GRPC_RUBY_PLUGIN=OFF \
-     -Dprotobuf_WITH_ZLIB=ON \
-     -DRE2_BUILD_TESTING=OFF \
-     -DCMAKE_INSTALL_PREFIX=${CPP_INSTALLED_PACKAGES_DIR}/ \
-     ${SRC_DIR_LIB_GRPC}  && \
-  cmake --build .  -- -j ${NUM_BUILD_THREADS} && \
-  cmake --build .  --target install -- -j ${NUM_BUILD_THREADS} 
-)
-
-rm -rf ${GRPC_BUILD_DIR}
-rm -rf ${GRPC_REPO_DIR}
-

backend/cpp/llama/CMakeLists.txt

@@ -1,74 +0,0 @@
-
-## XXX: In some versions of CMake clip wasn't being built before llama.
-## This is an hack for now, but it should be fixed in the future.
-set(TARGET myclip)
-add_library(${TARGET} clip.cpp clip.h)
-install(TARGETS ${TARGET} LIBRARY)
-target_link_libraries(${TARGET} PRIVATE common ggml ${CMAKE_THREAD_LIBS_INIT})
-target_compile_features(${TARGET} PRIVATE cxx_std_11)
-if (NOT MSVC)
-    target_compile_options(${TARGET} PRIVATE -Wno-cast-qual) # stb_image.h
-endif()
-
-set(TARGET grpc-server)
-# END CLIP hack
-set(CMAKE_CXX_STANDARD 17)
-cmake_minimum_required(VERSION 3.15)
-set(TARGET grpc-server)
-set(_PROTOBUF_LIBPROTOBUF libprotobuf)
-set(_REFLECTION grpc++_reflection)
-if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
-    link_directories("/opt/homebrew/lib")
-    include_directories("/opt/homebrew/include")
-endif()
-
-find_package(absl CONFIG REQUIRED)
-find_package(Protobuf CONFIG REQUIRED)
-find_package(gRPC CONFIG REQUIRED)
-
-find_program(_PROTOBUF_PROTOC protoc)
-set(_GRPC_GRPCPP grpc++)
-find_program(_GRPC_CPP_PLUGIN_EXECUTABLE grpc_cpp_plugin)
-
-include_directories(${CMAKE_CURRENT_BINARY_DIR})
-include_directories(${Protobuf_INCLUDE_DIRS})
-
-message(STATUS "Using protobuf version ${Protobuf_VERSION} | Protobuf_INCLUDE_DIRS: ${Protobuf_INCLUDE_DIRS} | CMAKE_CURRENT_BINARY_DIR: ${CMAKE_CURRENT_BINARY_DIR}")
-
-# Proto file
-get_filename_component(hw_proto "../../../../../../backend/backend.proto" ABSOLUTE)
-get_filename_component(hw_proto_path "${hw_proto}" PATH)
-
-# Generated sources
-set(hw_proto_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.cc")
-set(hw_proto_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.h")
-set(hw_grpc_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.cc")
-set(hw_grpc_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.h")
-
-add_custom_command(
-      OUTPUT "${hw_proto_srcs}" "${hw_proto_hdrs}" "${hw_grpc_srcs}" "${hw_grpc_hdrs}"
-      COMMAND ${_PROTOBUF_PROTOC}
-      ARGS --grpc_out "${CMAKE_CURRENT_BINARY_DIR}"
-        --cpp_out "${CMAKE_CURRENT_BINARY_DIR}"
-        -I "${hw_proto_path}"
-        --plugin=protoc-gen-grpc="${_GRPC_CPP_PLUGIN_EXECUTABLE}"
-        "${hw_proto}"
-      DEPENDS "${hw_proto}")
-
-# hw_grpc_proto
-add_library(hw_grpc_proto
-  ${hw_grpc_srcs}
-  ${hw_grpc_hdrs}
-  ${hw_proto_srcs}
-  ${hw_proto_hdrs} )
-
-add_executable(${TARGET} grpc-server.cpp json.hpp )
-target_link_libraries(${TARGET} PRIVATE common llama myclip ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto
-  absl::flags_parse
-  gRPC::${_REFLECTION}
-  gRPC::${_GRPC_GRPCPP}
-  protobuf::${_PROTOBUF_LIBPROTOBUF})
-target_compile_features(${TARGET} PRIVATE cxx_std_11)
-if(TARGET BUILD_INFO)
-  add_dependencies(${TARGET} BUILD_INFO)
-endif()

backend/cpp/llama/Makefile

@@ -1,50 +0,0 @@
-
-LLAMA_VERSION?=d9b33fe95bd257b36c84ee5769cc048230067d6f
-
-CMAKE_ARGS?=
-BUILD_TYPE?=
-
-# If build type is cublas, then we set -DLLAMA_CUBLAS=ON to CMAKE_ARGS automatically
-ifeq ($(BUILD_TYPE),cublas)
-	CMAKE_ARGS+=-DLLAMA_CUBLAS=ON
-# If build type is openblas then we set -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
-# to CMAKE_ARGS automatically
-else ifeq ($(BUILD_TYPE),openblas)
-	CMAKE_ARGS+=-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
-# If build type is clblast (openCL) we set -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
-else ifeq ($(BUILD_TYPE),clblast)
-	CMAKE_ARGS+=-DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
-# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ 
-else ifeq ($(BUILD_TYPE),hipblas)
-	CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON
-endif
-
-llama.cpp:
-	git clone --recurse-submodules https://github.com/ggerganov/llama.cpp llama.cpp
-	cd llama.cpp && git checkout -b build $(LLAMA_VERSION) && git submodule update --init --recursive --depth 1
-
-llama.cpp/examples/grpc-server:
-	mkdir -p llama.cpp/examples/grpc-server
-	cp -r $(abspath ./)/CMakeLists.txt llama.cpp/examples/grpc-server/
-	cp -r $(abspath ./)/grpc-server.cpp llama.cpp/examples/grpc-server/
-	cp -rfv $(abspath ./)/json.hpp llama.cpp/examples/grpc-server/
-	echo "add_subdirectory(grpc-server)" >> llama.cpp/examples/CMakeLists.txt
-## XXX: In some versions of CMake clip wasn't being built before llama.
-## This is an hack for now, but it should be fixed in the future.
-	cp -rfv llama.cpp/examples/llava/clip.h llama.cpp/examples/grpc-server/clip.h
-	cp -rfv llama.cpp/examples/llava/clip.cpp llama.cpp/examples/grpc-server/clip.cpp
-
-rebuild:
-	cp -rfv $(abspath ./)/CMakeLists.txt llama.cpp/examples/grpc-server/
-	cp -rfv $(abspath ./)/grpc-server.cpp llama.cpp/examples/grpc-server/
-	cp -rfv $(abspath ./)/json.hpp llama.cpp/examples/grpc-server/
-	rm -rf grpc-server
-	$(MAKE) grpc-server
-
-clean:
-	rm -rf llama.cpp
-	rm -rf grpc-server
-
-grpc-server: llama.cpp llama.cpp/examples/grpc-server
-	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release
-	cp llama.cpp/build/bin/grpc-server .

backend/go/llm/rwkv/main.go

@@ -1,21 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &LLM{}); err != nil {
-		panic(err)
-	}
-}

backend/go/transcribe/main.go

@@ -1,21 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &Whisper{}); err != nil {
-		panic(err)
-	}
-}

backend/go/tts/main.go

@@ -1,21 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &Piper{}); err != nil {
-		panic(err)
-	}
-}

backend/python/README.md

@@ -1,38 +0,0 @@
-# Common commands about conda environment
-
-## Create a new empty conda environment
-
-```
-conda create --name <env-name> python=<your version> -y
-
-conda create --name autogptq python=3.11 -y
-```
-
-## To activate the environment
-
-As of conda 4.4
-```
-conda activate autogptq
-```
-
-The conda version older than 4.4
-
-```
-source activate autogptq
-```
-
-## Install the packages to your environment
-
-Sometimes you need to install the packages from the conda-forge channel
-
-By using `conda`
-```
-conda install <your-package-name>
-
-conda install -c conda-forge <your package-name>
-```
-
-Or by using `pip`
-```
-pip install <your-package-name>
-```

backend/python/autogptq/Makefile

@@ -1,5 +0,0 @@
-.PHONY: autogptq
-autogptq:
-	@echo "Creating virtual environment..."
-	@conda env create --name autogptq --file autogptq.yml
-	@echo "Virtual environment created."

backend/python/autogptq/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the autogptq project
-
-```
-make autogptq
-```

backend/python/autogptq/autogptq.yml

@@ -1,86 +0,0 @@
-name: autogptq
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - accelerate==0.23.0
-      - aiohttp==3.8.5
-      - aiosignal==1.3.1
-      - async-timeout==4.0.3
-      - attrs==23.1.0
-      - auto-gptq==0.4.2
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - datasets==2.14.5
-      - dill==0.3.7
-      - filelock==3.12.4
-      - frozenlist==1.4.0
-      - fsspec==2023.6.0
-      - grpcio==1.59.0
-      - huggingface-hub==0.16.4
-      - idna==3.4
-      - jinja2==3.1.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - multidict==6.0.4
-      - multiprocess==0.70.15
-      - networkx==3.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - packaging==23.2
-      - pandas==2.1.1
-      - peft==0.5.0
-      - protobuf==4.24.4
-      - psutil==5.9.5
-      - pyarrow==13.0.0
-      - python-dateutil==2.8.2
-      - pytz==2023.3.post1
-      - pyyaml==6.0.1
-      - regex==2023.10.3
-      - requests==2.31.0
-      - rouge==1.0.1
-      - safetensors==0.3.3
-      - six==1.16.0
-      - sympy==1.12
-      - tokenizers==0.14.0
-      - torch==2.1.0
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.1.0
-      - typing-extensions==4.8.0
-      - tzdata==2023.3
-      - urllib3==2.0.6
-      - xxhash==3.4.1
-      - yarl==1.9.2

backend/python/autogptq/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the autogptq server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate autogptq
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/autogptq.py $@

backend/python/bark/Makefile

@@ -1,5 +0,0 @@
-.PHONY: ttsbark
-ttsbark:
-	@echo "Creating virtual environment..."
-	@conda env create --name ttsbark --file ttsbark.yml
-	@echo "Virtual environment created."

backend/python/bark/README.md

@@ -1,16 +0,0 @@
-# Creating a separate environment for ttsbark project
-
-```
-make ttsbark
-```
-
-# Testing the gRPC server
-
-```
-<The path of your python interpreter> -m unittest test_ttsbark.py
-```
-
-For example
-```
-/opt/conda/envs/bark/bin/python -m unittest extra/grpc/bark/test_ttsbark.py
-``````

backend/python/bark/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the ttsbark server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate ttsbark
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/ttsbark.py $@

backend/python/bark/test_ttsbark.py

@@ -1,32 +0,0 @@
-import unittest
-import subprocess
-import time
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-class TestBackendServicer(unittest.TestCase):
-    """
-    TestBackendServicer is the class that tests the gRPC service
-    """
-    def setUp(self):
-        self.service = subprocess.Popen(["python3", "ttsbark.py", "--addr", "localhost:50051"])
-
-    def tearDown(self) -> None:
-        self.service.terminate()
-        self.service.wait()
-
-    def test_server_startup(self):
-        time.sleep(2)
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.Health(backend_pb2.HealthMessage())
-                self.assertEqual(response.message, b'OK')
-        except Exception as err:
-            print(err)
-            self.fail("Server failed to start")
-        finally:
-            self.tearDown()

backend/python/bark/ttsbark.yml

@@ -1,96 +0,0 @@
-name: bark
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - accelerate==0.23.0
-      - aiohttp==3.8.5
-      - aiosignal==1.3.1
-      - async-timeout==4.0.3
-      - attrs==23.1.0
-      - bark==0.1.5
-      - boto3==1.28.61
-      - botocore==1.31.61
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - datasets==2.14.5
-      - dill==0.3.7
-      - einops==0.7.0
-      - encodec==0.1.1
-      - filelock==3.12.4
-      - frozenlist==1.4.0
-      - fsspec==2023.6.0
-      - funcy==2.0
-      - grpcio==1.59.0
-      - huggingface-hub==0.16.4
-      - idna==3.4
-      - jinja2==3.1.2
-      - jmespath==1.0.1
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - multidict==6.0.4
-      - multiprocess==0.70.15
-      - networkx==3.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - packaging==23.2
-      - pandas==2.1.1
-      - peft==0.5.0
-      - protobuf==4.24.4
-      - psutil==5.9.5
-      - pyarrow==13.0.0
-      - python-dateutil==2.8.2
-      - pytz==2023.3.post1
-      - pyyaml==6.0.1
-      - regex==2023.10.3
-      - requests==2.31.0
-      - rouge==1.0.1
-      - s3transfer==0.7.0
-      - safetensors==0.3.3
-      - scipy==1.11.3
-      - six==1.16.0
-      - sympy==1.12
-      - tokenizers==0.14.0
-      - torch==2.1.0
-      - torchaudio==2.1.0
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.1.0
-      - typing-extensions==4.8.0
-      - tzdata==2023.3
-      - urllib3==1.26.17
-      - xxhash==3.4.1
-      - yarl==1.9.2
-prefix: /opt/conda/envs/bark

backend/python/diffusers/Makefile

@@ -1,11 +0,0 @@
-.PHONY: diffusers
-diffusers:
-	@echo "Creating virtual environment..."
-	@conda env create --name diffusers --file diffusers.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running diffusers..."
-	bash run.sh
-	@echo "Diffusers run."

backend/python/diffusers/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the diffusers project
-
-```
-make diffusers
-```

backend/python/diffusers/diffusers.yml

@@ -1,74 +0,0 @@
-name: diffusers
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - tzdata=2023c=h04d1e81_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - accelerate==0.23.0
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - compel==2.0.2
-      - diffusers==0.21.4
-      - filelock==3.12.4
-      - fsspec==2023.9.2
-      - grpcio==1.59.0
-      - huggingface-hub==0.17.3
-      - idna==3.4
-      - importlib-metadata==6.8.0
-      - jinja2==3.1.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - networkx==3.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - packaging==23.2
-      - pillow==10.0.1
-      - protobuf==4.24.4
-      - psutil==5.9.5
-      - pyparsing==3.1.1
-      - pyyaml==6.0.1
-      - regex==2023.10.3
-      - requests==2.31.0
-      - safetensors==0.4.0
-      - sympy==1.12
-      - tokenizers==0.14.1
-      - torch==2.1.0
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.1.0
-      - typing-extensions==4.8.0
-      - urllib3==2.0.6
-      - zipp==3.17.0
-prefix: /opt/conda/envs/diffusers

backend/python/diffusers/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the diffusers server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate diffusers
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/backend_diffusers.py $@

backend/python/exllama/Makefile

@@ -1,11 +0,0 @@
-.PHONY: exllama
-exllama:
-	@echo "Creating virtual environment..."
-	@conda env create --name exllama --file exllama.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running exllama..."
-	bash run.sh
-	@echo "exllama run."

backend/python/exllama/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the exllama project
-
-```
-make exllama
-```

backend/python/exllama/exllama.yml

@@ -1,55 +0,0 @@
-name: exllama
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - tzdata=2023c=h04d1e81_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - filelock==3.12.4
-      - fsspec==2023.9.2
-      - grpcio==1.59.0
-      - jinja2==3.1.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - networkx==3.1
-      - ninja==1.11.1
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - protobuf==4.24.4
-      - safetensors==0.3.2
-      - sentencepiece==0.1.99
-      - sympy==1.12
-      - torch==2.1.0
-      - triton==2.1.0
-      - typing-extensions==4.8.0
-prefix: /opt/conda/envs/exllama

backend/python/exllama/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the exllama server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate exllama
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/exllama.py $@

backend/python/petals/Makefile

@@ -1,11 +0,0 @@
-.PHONY: petals
-petals:
-	@echo "Creating virtual environment..."
-	@conda env create --name petals --file petals.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running petals..."
-	bash run.sh
-	@echo "petals run."

backend/python/petals/backend_petals.py

@@ -1,140 +0,0 @@
-#!/usr/bin/env python3
-from concurrent import futures
-import time
-import argparse
-import signal
-import sys
-import os
-
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-import torch
-from transformers import AutoTokenizer
-from petals import AutoDistributedModelForCausalLM
-
-_ONE_DAY_IN_SECONDS = 60 * 60 * 24
-
-# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
-MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
-
-# Implement the BackendServicer class with the service methods
-class BackendServicer(backend_pb2_grpc.BackendServicer):
-    """
-    A gRPC servicer that implements the Backend service defined in backend.proto.
-    """
-    def Health(self, request, context):
-        """
-        Returns a health check message.
-
-        Args:
-            request: The health check request.
-            context: The gRPC context.
-
-        Returns:
-            backend_pb2.Reply: The health check reply.
-        """
-        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
-
-    def LoadModel(self, request, context):
-        """
-        Loads a language model.
-
-        Args:
-            request: The load model request.
-            context: The gRPC context.
-
-        Returns:
-            backend_pb2.Result: The load model result.
-        """
-        try:
-            self.tokenizer = AutoTokenizer.from_pretrained(request.Model, use_fast=False, add_bos_token=False)
-            self.model = AutoDistributedModelForCausalLM.from_pretrained(request.Model)
-            self.cuda = False
-            if request.CUDA:
-                self.model = self.model.cuda()
-                self.cuda = True
-
-        except Exception as err:
-            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-        return backend_pb2.Result(message="Model loaded successfully", success=True)
-
-    def Predict(self, request, context):
-        """
-        Generates text based on the given prompt and sampling parameters.
-
-        Args:
-            request: The predict request.
-            context: The gRPC context.
-
-        Returns:
-            backend_pb2.Result: The predict result.
-        """
-
-        inputs = self.tokenizer(request.Prompt, return_tensors="pt")["input_ids"]
-        if self.cuda:
-            inputs = inputs.cuda()
- 
-        if request.Tokens == 0:
-            # Max to max value if tokens are not specified
-            request.Tokens = 8192
-
-        # TODO: kwargs and map all parameters
-        outputs = self.model.generate(inputs, max_new_tokens=request.Tokens)
-
-        generated_text = self.tokenizer.decode(outputs[0])
-        # Remove prompt from response if present
-        if request.Prompt in generated_text:
-            generated_text = generated_text.replace(request.Prompt, "")
-
-        return backend_pb2.Result(message=bytes(generated_text, encoding='utf-8'))
-
-    def PredictStream(self, request, context):
-        """
-        Generates text based on the given prompt and sampling parameters, and streams the results.
-
-        Args:
-            request: The predict stream request.
-            context: The gRPC context.
-
-        Returns:
-            backend_pb2.Result: The predict stream result.
-        """
-        # Implement PredictStream RPC
-        #for reply in some_data_generator():
-        #    yield reply
-        # Not implemented yet
-        return self.Predict(request, context)
-
-def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
-    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
-    server.add_insecure_port(address)
-    server.start()
-    print("Server started. Listening on: " + address, file=sys.stderr)
-
-    # Define the signal handler function
-    def signal_handler(sig, frame):
-        print("Received termination signal. Shutting down...")
-        server.stop(0)
-        sys.exit(0)
-
-    # Set the signal handlers for SIGINT and SIGTERM
-    signal.signal(signal.SIGINT, signal_handler)
-    signal.signal(signal.SIGTERM, signal_handler)
-
-    try:
-        while True:
-            time.sleep(_ONE_DAY_IN_SECONDS)
-    except KeyboardInterrupt:
-        server.stop(0)
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run the gRPC server.")
-    parser.add_argument(
-        "--addr", default="localhost:50051", help="The address to bind the server to."
-    )
-    args = parser.parse_args()
-
-    serve(args.addr)

backend/python/petals/petals.yml

@@ -1,29 +0,0 @@
-name: petals
-channels:
-  - defaults
-dependencies:
-  # - _libgcc_mutex=0.1=main
-  # - _openmp_mutex=5.1=1_gnu
-  # - bzip2=1.0.8=h7b6447c_0
-  # - ca-certificates=2023.08.22=h06a4308_0
-  # - ld_impl_linux-64=2.38=h1181459_1
-  # - libffi=3.4.4=h6a678d5_0
-  # - libgcc-ng=11.2.0=h1234567_1
-  # - libgomp=11.2.0=h1234567_1
-  # - libstdcxx-ng=11.2.0=h1234567_1
-  # - libuuid=1.41.5=h5eee18b_0
-  # - ncurses=6.4=h6a678d5_0
-  # - openssl=3.0.11=h7f8727e_2
-  # - pip=23.2.1=py311h06a4308_0
-  # - python=3.11.5=h955ad1f_0
-  # - readline=8.2=h5eee18b_0
-  # - setuptools=68.0.0=py311h06a4308_0
-  # - sqlite=3.41.2=h5eee18b_0
-  # - tk=8.6.12=h1ccaba5_0
-  # - tzdata=2023c=h04d1e81_0
-  # - wheel=0.41.2=py311h06a4308_0
-  # - xz=5.4.2=h5eee18b_0
-  # - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - git+https://github.com/bigscience-workshop/petals
-prefix: /opt/conda/envs/petals

backend/python/petals/run.sh

@@ -1,21 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the exllama server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-# if source is available use it, or use conda
-#
-if [ -f /opt/conda/bin/activate ]; then
-    source activate petals
-else
-    eval "$(conda shell.bash hook)"
-    conda activate petals
-fi
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/backend_petals.py $@

backend/python/sentencetransformers/Makefile

@@ -1,18 +0,0 @@
-.PHONY: sentencetransformers
-sentencetransformers:
-	@echo "Creating virtual environment..."
-	@conda env create --name sentencetransformers --file sentencetransformers.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running sentencetransformers..."
-	bash run.sh
-	@echo "sentencetransformers run."
-
-# It is not working well by using command line. It only6 works with IDE like VSCode.
-.PHONY: test
-test:
-	@echo "Testing sentencetransformers..."
-	bash test.sh
-	@echo "sentencetransformers tested."

backend/python/sentencetransformers/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the sentencetransformers project
-
-```
-make sentencetransformers
-```

backend/python/sentencetransformers/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the sentencetransformers server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate sentencetransformers
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/sentencetransformers.py $@

backend/python/sentencetransformers/sentencetransformers.yml

@@ -1,77 +0,0 @@
-name: sentencetransformers
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - tzdata=2023c=h04d1e81_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - click==8.1.7
-      - filelock==3.12.4
-      - fsspec==2023.9.2
-      - grpcio==1.59.0
-      - huggingface-hub==0.17.3
-      - idna==3.4
-      - install==1.3.5
-      - jinja2==3.1.2
-      - joblib==1.3.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - networkx==3.1
-      - nltk==3.8.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - packaging==23.2
-      - pillow==10.0.1
-      - protobuf==4.24.4
-      - pyyaml==6.0.1
-      - regex==2023.10.3
-      - requests==2.31.0
-      - safetensors==0.4.0
-      - scikit-learn==1.3.1
-      - scipy==1.11.3
-      - sentence-transformers==2.2.2
-      - sentencepiece==0.1.99
-      - sympy==1.12
-      - threadpoolctl==3.2.0
-      - tokenizers==0.14.1
-      - torch==2.1.0
-      - torchvision==0.16.0
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.1.0
-      - typing-extensions==4.8.0
-      - urllib3==2.0.6
-prefix: /opt/conda/envs/sentencetransformers

backend/python/sentencetransformers/test.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-##
-## A bash script wrapper that runs the sentencetransformers server with conda
-
-# Activate conda environment
-source activate sentencetransformers
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python -m unittest $DIR/test_sentencetransformers.py

backend/python/sentencetransformers/test_sentencetransformers.py

@@ -1,81 +0,0 @@
-"""
-A test script to test the gRPC service
-"""
-import unittest
-import subprocess
-import time
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-
-class TestBackendServicer(unittest.TestCase):
-    """
-    TestBackendServicer is the class that tests the gRPC service
-    """
-    def setUp(self):
-        """
-        This method sets up the gRPC service by starting the server
-        """
-        self.service = subprocess.Popen(["python3", "sentencetransformers.py", "--addr", "localhost:50051"])
-
-    def tearDown(self) -> None:
-        """
-        This method tears down the gRPC service by terminating the server
-        """
-        self.service.terminate()
-        self.service.wait()
-
-    def test_server_startup(self):
-        """
-        This method tests if the server starts up successfully
-        """
-        time.sleep(2)
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.Health(backend_pb2.HealthMessage())
-                self.assertEqual(response.message, b'OK')
-        except Exception as err:
-            print(err)
-            self.fail("Server failed to start")
-        finally:
-            self.tearDown()
-
-    def test_load_model(self):
-        """
-        This method tests if the model is loaded successfully
-        """
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-nli-mean-tokens"))
-                self.assertTrue(response.success)
-                self.assertEqual(response.message, "Model loaded successfully")
-        except Exception as err:
-            print(err)
-            self.fail("LoadModel service failed")
-        finally:
-            self.tearDown()
-
-    def test_embedding(self):
-        """
-        This method tests if the embeddings are generated successfully
-        """
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-nli-mean-tokens"))
-                self.assertTrue(response.success)
-                embedding_request = backend_pb2.PredictOptions(Embeddings="This is a test sentence.")
-                embedding_response = stub.Embedding(embedding_request)
-                self.assertIsNotNone(embedding_response.embeddings)
-        except Exception as err:
-            print(err)
-            self.fail("Embedding service failed")
-        finally:
-            self.tearDown()

backend/python/transformers/Makefile

@@ -1,18 +0,0 @@
-.PHONY: transformers
-transformers:
-	@echo "Creating virtual environment..."
-	@conda env create --name transformers --file transformers.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running transformers..."
-	bash run.sh
-	@echo "transformers run."
-
-# It is not working well by using command line. It only6 works with IDE like VSCode.
-.PHONY: test
-test:
-	@echo "Testing transformers..."
-	bash test.sh
-	@echo "transformers tested."

backend/python/transformers/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the transformers project
-
-```
-make transformers
-```

backend/python/transformers/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the transformers server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate transformers
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/transformers_server.py $@

backend/python/transformers/test.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-##
-## A bash script wrapper that runs the transformers server with conda
-
-# Activate conda environment
-source activate transformers
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python -m unittest $DIR/test_transformers_server.py

backend/python/transformers/test_transformers.py

@@ -1,81 +0,0 @@
-"""
-A test script to test the gRPC service
-"""
-import unittest
-import subprocess
-import time
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-
-class TestBackendServicer(unittest.TestCase):
-    """
-    TestBackendServicer is the class that tests the gRPC service
-    """
-    def setUp(self):
-        """
-        This method sets up the gRPC service by starting the server
-        """
-        self.service = subprocess.Popen(["python3", "transformers_server.py", "--addr", "localhost:50051"])
-
-    def tearDown(self) -> None:
-        """
-        This method tears down the gRPC service by terminating the server
-        """
-        self.service.terminate()
-        self.service.wait()
-
-    def test_server_startup(self):
-        """
-        This method tests if the server starts up successfully
-        """
-        time.sleep(2)
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.Health(backend_pb2.HealthMessage())
-                self.assertEqual(response.message, b'OK')
-        except Exception as err:
-            print(err)
-            self.fail("Server failed to start")
-        finally:
-            self.tearDown()
-
-    def test_load_model(self):
-        """
-        This method tests if the model is loaded successfully
-        """
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-nli-mean-tokens"))
-                self.assertTrue(response.success)
-                self.assertEqual(response.message, "Model loaded successfully")
-        except Exception as err:
-            print(err)
-            self.fail("LoadModel service failed")
-        finally:
-            self.tearDown()
-
-    def test_embedding(self):
-        """
-        This method tests if the embeddings are generated successfully
-        """
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.LoadModel(backend_pb2.ModelOptions(Model="bert-base-nli-mean-tokens"))
-                self.assertTrue(response.success)
-                embedding_request = backend_pb2.PredictOptions(Embeddings="This is a test sentence.")
-                embedding_response = stub.Embedding(embedding_request)
-                self.assertIsNotNone(embedding_response.embeddings)
-        except Exception as err:
-            print(err)
-            self.fail("Embedding service failed")
-        finally:
-            self.tearDown()

backend/python/transformers/transformers.yml

@@ -1,77 +0,0 @@
-name: transformers
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - tzdata=2023c=h04d1e81_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - click==8.1.7
-      - filelock==3.12.4
-      - fsspec==2023.9.2
-      - grpcio==1.59.0
-      - huggingface-hub==0.17.3
-      - idna==3.4
-      - install==1.3.5
-      - jinja2==3.1.2
-      - joblib==1.3.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - networkx==3.1
-      - nltk==3.8.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - packaging==23.2
-      - pillow==10.0.1
-      - protobuf==4.24.4
-      - pyyaml==6.0.1
-      - regex==2023.10.3
-      - requests==2.31.0
-      - safetensors==0.4.0
-      - scikit-learn==1.3.1
-      - scipy==1.11.3
-      - sentence-transformers==2.2.2
-      - sentencepiece==0.1.99
-      - sympy==1.12
-      - threadpoolctl==3.2.0
-      - tokenizers==0.14.1
-      - torch==2.1.0
-      - torchvision==0.16.0
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.1.0
-      - typing-extensions==4.8.0
-      - urllib3==2.0.6
-prefix: /opt/conda/envs/transformers

backend/python/transformers/transformers_server.py

@@ -1,114 +0,0 @@
-#!/usr/bin/env python3
-"""
-Extra gRPC server for HuggingFace AutoModel models.
-"""
-from concurrent import futures
-
-import argparse
-import signal
-import sys
-import os
-
-import time
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-from transformers import AutoModel
-
-_ONE_DAY_IN_SECONDS = 60 * 60 * 24
-
-# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
-MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
-
-# Implement the BackendServicer class with the service methods
-class BackendServicer(backend_pb2_grpc.BackendServicer):
-    """
-    A gRPC servicer for the backend service.
-
-    This class implements the gRPC methods for the backend service, including Health, LoadModel, and Embedding.
-    """
-    def Health(self, request, context):
-        """
-        A gRPC method that returns the health status of the backend service.
-
-        Args:
-            request: A HealthRequest object that contains the request parameters.
-            context: A grpc.ServicerContext object that provides information about the RPC.
-
-        Returns:
-            A Reply object that contains the health status of the backend service.
-        """
-        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
-
-    def LoadModel(self, request, context):
-        """
-        A gRPC method that loads a model into memory.
-
-        Args:
-            request: A LoadModelRequest object that contains the request parameters.
-            context: A grpc.ServicerContext object that provides information about the RPC.
-
-        Returns:
-            A Result object that contains the result of the LoadModel operation.
-        """
-        model_name = request.Model
-        try:
-            self.model = AutoModel.from_pretrained(model_name, trust_remote_code=True) # trust_remote_code is needed to use the encode method with embeddings models like jinai-v2
-        except Exception as err:
-            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-
-        # Implement your logic here for the LoadModel service
-        # Replace this with your desired response
-        return backend_pb2.Result(message="Model loaded successfully", success=True)
-
-    def Embedding(self, request, context):
-        """
-        A gRPC method that calculates embeddings for a given sentence.
-
-        Args:
-            request: An EmbeddingRequest object that contains the request parameters.
-            context: A grpc.ServicerContext object that provides information about the RPC.
-
-        Returns:
-            An EmbeddingResult object that contains the calculated embeddings.
-        """
-        # Implement your logic here for the Embedding service
-        # Replace this with your desired response
-        print("Calculated embeddings for: " + request.Embeddings, file=sys.stderr)
-        sentence_embeddings = self.model.encode(request.Embeddings)
-        return backend_pb2.EmbeddingResult(embeddings=sentence_embeddings)
-
-
-def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
-    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
-    server.add_insecure_port(address)
-    server.start()
-    print("Server started. Listening on: " + address, file=sys.stderr)
-
-    # Define the signal handler function
-    def signal_handler(sig, frame):
-        print("Received termination signal. Shutting down...")
-        server.stop(0)
-        sys.exit(0)
-
-    # Set the signal handlers for SIGINT and SIGTERM
-    signal.signal(signal.SIGINT, signal_handler)
-    signal.signal(signal.SIGTERM, signal_handler)
-
-    try:
-        while True:
-            time.sleep(_ONE_DAY_IN_SECONDS)
-    except KeyboardInterrupt:
-        server.stop(0)
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run the gRPC server.")
-    parser.add_argument(
-        "--addr", default="localhost:50051", help="The address to bind the server to."
-    )
-    args = parser.parse_args()
-
-    serve(args.addr)

backend/python/vall-e-x/Makefile

@@ -1,11 +0,0 @@
-.PHONY: ttsvalle
-ttsvalle:
-	@echo "Creating virtual environment..."
-	@conda env create --name ttsvalle --file ttsvalle.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running ttsvalle..."
-	bash run.sh
-	@echo "ttsvalle run."

backend/python/vall-e-x/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the ttsvalle project
-
-```
-make ttsvalle
-```

backend/python/vall-e-x/backend_pb2_grpc.py

@@ -1,363 +0,0 @@
-# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
-"""Client and server classes corresponding to protobuf-defined services."""
-import grpc
-
-import backend_pb2 as backend__pb2
-
-
-class BackendStub(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def __init__(self, channel):
-        """Constructor.
-
-        Args:
-            channel: A grpc.Channel.
-        """
-        self.Health = channel.unary_unary(
-                '/backend.Backend/Health',
-                request_serializer=backend__pb2.HealthMessage.SerializeToString,
-                response_deserializer=backend__pb2.Reply.FromString,
-                )
-        self.Predict = channel.unary_unary(
-                '/backend.Backend/Predict',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.Reply.FromString,
-                )
-        self.LoadModel = channel.unary_unary(
-                '/backend.Backend/LoadModel',
-                request_serializer=backend__pb2.ModelOptions.SerializeToString,
-                response_deserializer=backend__pb2.Result.FromString,
-                )
-        self.PredictStream = channel.unary_stream(
-                '/backend.Backend/PredictStream',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.Reply.FromString,
-                )
-        self.Embedding = channel.unary_unary(
-                '/backend.Backend/Embedding',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.EmbeddingResult.FromString,
-                )
-        self.GenerateImage = channel.unary_unary(
-                '/backend.Backend/GenerateImage',
-                request_serializer=backend__pb2.GenerateImageRequest.SerializeToString,
-                response_deserializer=backend__pb2.Result.FromString,
-                )
-        self.AudioTranscription = channel.unary_unary(
-                '/backend.Backend/AudioTranscription',
-                request_serializer=backend__pb2.TranscriptRequest.SerializeToString,
-                response_deserializer=backend__pb2.TranscriptResult.FromString,
-                )
-        self.TTS = channel.unary_unary(
-                '/backend.Backend/TTS',
-                request_serializer=backend__pb2.TTSRequest.SerializeToString,
-                response_deserializer=backend__pb2.Result.FromString,
-                )
-        self.TokenizeString = channel.unary_unary(
-                '/backend.Backend/TokenizeString',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.TokenizationResponse.FromString,
-                )
-        self.Status = channel.unary_unary(
-                '/backend.Backend/Status',
-                request_serializer=backend__pb2.HealthMessage.SerializeToString,
-                response_deserializer=backend__pb2.StatusResponse.FromString,
-                )
-
-
-class BackendServicer(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def Health(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Predict(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def LoadModel(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def PredictStream(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Embedding(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def GenerateImage(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def AudioTranscription(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def TTS(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def TokenizeString(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Status(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-
-def add_BackendServicer_to_server(servicer, server):
-    rpc_method_handlers = {
-            'Health': grpc.unary_unary_rpc_method_handler(
-                    servicer.Health,
-                    request_deserializer=backend__pb2.HealthMessage.FromString,
-                    response_serializer=backend__pb2.Reply.SerializeToString,
-            ),
-            'Predict': grpc.unary_unary_rpc_method_handler(
-                    servicer.Predict,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.Reply.SerializeToString,
-            ),
-            'LoadModel': grpc.unary_unary_rpc_method_handler(
-                    servicer.LoadModel,
-                    request_deserializer=backend__pb2.ModelOptions.FromString,
-                    response_serializer=backend__pb2.Result.SerializeToString,
-            ),
-            'PredictStream': grpc.unary_stream_rpc_method_handler(
-                    servicer.PredictStream,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.Reply.SerializeToString,
-            ),
-            'Embedding': grpc.unary_unary_rpc_method_handler(
-                    servicer.Embedding,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.EmbeddingResult.SerializeToString,
-            ),
-            'GenerateImage': grpc.unary_unary_rpc_method_handler(
-                    servicer.GenerateImage,
-                    request_deserializer=backend__pb2.GenerateImageRequest.FromString,
-                    response_serializer=backend__pb2.Result.SerializeToString,
-            ),
-            'AudioTranscription': grpc.unary_unary_rpc_method_handler(
-                    servicer.AudioTranscription,
-                    request_deserializer=backend__pb2.TranscriptRequest.FromString,
-                    response_serializer=backend__pb2.TranscriptResult.SerializeToString,
-            ),
-            'TTS': grpc.unary_unary_rpc_method_handler(
-                    servicer.TTS,
-                    request_deserializer=backend__pb2.TTSRequest.FromString,
-                    response_serializer=backend__pb2.Result.SerializeToString,
-            ),
-            'TokenizeString': grpc.unary_unary_rpc_method_handler(
-                    servicer.TokenizeString,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.TokenizationResponse.SerializeToString,
-            ),
-            'Status': grpc.unary_unary_rpc_method_handler(
-                    servicer.Status,
-                    request_deserializer=backend__pb2.HealthMessage.FromString,
-                    response_serializer=backend__pb2.StatusResponse.SerializeToString,
-            ),
-    }
-    generic_handler = grpc.method_handlers_generic_handler(
-            'backend.Backend', rpc_method_handlers)
-    server.add_generic_rpc_handlers((generic_handler,))
-
-
- # This class is part of an EXPERIMENTAL API.
-class Backend(object):
-    """Missing associated documentation comment in .proto file."""
-
-    @staticmethod
-    def Health(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Health',
-            backend__pb2.HealthMessage.SerializeToString,
-            backend__pb2.Reply.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Predict(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Predict',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.Reply.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def LoadModel(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/LoadModel',
-            backend__pb2.ModelOptions.SerializeToString,
-            backend__pb2.Result.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def PredictStream(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_stream(request, target, '/backend.Backend/PredictStream',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.Reply.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Embedding(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Embedding',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.EmbeddingResult.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def GenerateImage(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/GenerateImage',
-            backend__pb2.GenerateImageRequest.SerializeToString,
-            backend__pb2.Result.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def AudioTranscription(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/AudioTranscription',
-            backend__pb2.TranscriptRequest.SerializeToString,
-            backend__pb2.TranscriptResult.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def TTS(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/TTS',
-            backend__pb2.TTSRequest.SerializeToString,
-            backend__pb2.Result.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def TokenizeString(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/TokenizeString',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.TokenizationResponse.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Status(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Status',
-            backend__pb2.HealthMessage.SerializeToString,
-            backend__pb2.StatusResponse.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)

backend/python/vall-e-x/run.sh

@@ -1,13 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the ttsvalle server with conda
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate ttsvalle
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/ttvalle.py $@

backend/python/vall-e-x/ttsvalle.yml

@@ -1,101 +0,0 @@
-name: ttsvalle
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py310h06a4308_0
-  - python=3.10.13=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py310h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - tzdata=2023c=h04d1e81_0
-  - wheel=0.41.2=py310h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - aiofiles==23.2.1
-      - altair==5.1.2
-      - annotated-types==0.6.0
-      - anyio==3.7.1
-      - click==8.1.7
-      - cn2an==0.5.22
-      - cython==3.0.3
-      - einops==0.7.0
-      - encodec==0.1.1
-      - eng-to-ipa==0.0.2
-      - fastapi==0.103.2
-      - ffmpeg-python==0.2.0
-      - ffmpy==0.3.1
-      - fsspec==2023.9.2
-      - future==0.18.3
-      - gradio==3.47.1
-      - gradio-client==0.6.0
-      - grpcio==1.59.0
-      - h11==0.14.0
-      - httpcore==0.18.0
-      - httpx==0.25.0
-      - huggingface-hub==0.17.3
-      - importlib-resources==6.1.0
-      - inflect==7.0.0
-      - jieba==0.42.1
-      - langid==1.1.6
-      - llvmlite==0.41.0
-      - more-itertools==10.1.0
-      - nltk==3.8.1
-      - numba==0.58.0
-      - numpy==1.25.2
-      - nvidia-cublas-cu12==12.1.3.1
-      - nvidia-cuda-cupti-cu12==12.1.105
-      - nvidia-cuda-nvrtc-cu12==12.1.105
-      - nvidia-cuda-runtime-cu12==12.1.105
-      - nvidia-cudnn-cu12==8.9.2.26
-      - nvidia-cufft-cu12==11.0.2.54
-      - nvidia-curand-cu12==10.3.2.106
-      - nvidia-cusolver-cu12==11.4.5.107
-      - nvidia-cusparse-cu12==12.1.0.106
-      - nvidia-nccl-cu12==2.18.1
-      - nvidia-nvjitlink-cu12==12.2.140
-      - nvidia-nvtx-cu12==12.1.105
-      - openai-whisper==20230306
-      - orjson==3.9.7
-      - proces==0.1.7
-      - protobuf==4.24.4
-      - pydantic==2.4.2
-      - pydantic-core==2.10.1
-      - pydub==0.25.1
-      - pyopenjtalk-prebuilt==0.3.0
-      - pypinyin==0.49.0
-      - python-multipart==0.0.6
-      - regex==2023.10.3
-      - safetensors==0.4.0
-      - semantic-version==2.10.0
-      - soundfile==0.12.1
-      - starlette==0.27.0
-      - sudachidict-core==20230927
-      - sudachipy==0.6.7
-      - tokenizers==0.14.1
-      - toolz==0.12.0
-      - torch==2.1.0
-      - torchaudio==2.1.0
-      - torchvision==0.16.0
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.1.0
-      - unidecode==1.3.7
-      - uvicorn==0.23.2
-      - vocos==0.0.3
-      - websockets==11.0.3
-      - wget==3.2
-prefix: /opt/conda/envs/ttsvalle

backend/python/vllm/Makefile

@@ -1,11 +0,0 @@
-.PHONY: vllm
-vllm:
-	@echo "Creating virtual environment..."
-	@conda env create --name vllm --file vllm.yml
-	@echo "Virtual environment created."
-
-.PHONY: run
-run:
-	@echo "Running vllm..."
-	bash run.sh
-	@echo "vllm run."

backend/python/vllm/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the vllm project
-
-```
-make vllm
-```

backend/python/vllm/backend_pb2_grpc.py

@@ -1,363 +0,0 @@
-# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
-"""Client and server classes corresponding to protobuf-defined services."""
-import grpc
-
-import backend_pb2 as backend__pb2
-
-
-class BackendStub(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def __init__(self, channel):
-        """Constructor.
-
-        Args:
-            channel: A grpc.Channel.
-        """
-        self.Health = channel.unary_unary(
-                '/backend.Backend/Health',
-                request_serializer=backend__pb2.HealthMessage.SerializeToString,
-                response_deserializer=backend__pb2.Reply.FromString,
-                )
-        self.Predict = channel.unary_unary(
-                '/backend.Backend/Predict',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.Reply.FromString,
-                )
-        self.LoadModel = channel.unary_unary(
-                '/backend.Backend/LoadModel',
-                request_serializer=backend__pb2.ModelOptions.SerializeToString,
-                response_deserializer=backend__pb2.Result.FromString,
-                )
-        self.PredictStream = channel.unary_stream(
-                '/backend.Backend/PredictStream',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.Reply.FromString,
-                )
-        self.Embedding = channel.unary_unary(
-                '/backend.Backend/Embedding',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.EmbeddingResult.FromString,
-                )
-        self.GenerateImage = channel.unary_unary(
-                '/backend.Backend/GenerateImage',
-                request_serializer=backend__pb2.GenerateImageRequest.SerializeToString,
-                response_deserializer=backend__pb2.Result.FromString,
-                )
-        self.AudioTranscription = channel.unary_unary(
-                '/backend.Backend/AudioTranscription',
-                request_serializer=backend__pb2.TranscriptRequest.SerializeToString,
-                response_deserializer=backend__pb2.TranscriptResult.FromString,
-                )
-        self.TTS = channel.unary_unary(
-                '/backend.Backend/TTS',
-                request_serializer=backend__pb2.TTSRequest.SerializeToString,
-                response_deserializer=backend__pb2.Result.FromString,
-                )
-        self.TokenizeString = channel.unary_unary(
-                '/backend.Backend/TokenizeString',
-                request_serializer=backend__pb2.PredictOptions.SerializeToString,
-                response_deserializer=backend__pb2.TokenizationResponse.FromString,
-                )
-        self.Status = channel.unary_unary(
-                '/backend.Backend/Status',
-                request_serializer=backend__pb2.HealthMessage.SerializeToString,
-                response_deserializer=backend__pb2.StatusResponse.FromString,
-                )
-
-
-class BackendServicer(object):
-    """Missing associated documentation comment in .proto file."""
-
-    def Health(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Predict(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def LoadModel(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def PredictStream(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Embedding(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def GenerateImage(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def AudioTranscription(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def TTS(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def TokenizeString(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-    def Status(self, request, context):
-        """Missing associated documentation comment in .proto file."""
-        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
-        context.set_details('Method not implemented!')
-        raise NotImplementedError('Method not implemented!')
-
-
-def add_BackendServicer_to_server(servicer, server):
-    rpc_method_handlers = {
-            'Health': grpc.unary_unary_rpc_method_handler(
-                    servicer.Health,
-                    request_deserializer=backend__pb2.HealthMessage.FromString,
-                    response_serializer=backend__pb2.Reply.SerializeToString,
-            ),
-            'Predict': grpc.unary_unary_rpc_method_handler(
-                    servicer.Predict,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.Reply.SerializeToString,
-            ),
-            'LoadModel': grpc.unary_unary_rpc_method_handler(
-                    servicer.LoadModel,
-                    request_deserializer=backend__pb2.ModelOptions.FromString,
-                    response_serializer=backend__pb2.Result.SerializeToString,
-            ),
-            'PredictStream': grpc.unary_stream_rpc_method_handler(
-                    servicer.PredictStream,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.Reply.SerializeToString,
-            ),
-            'Embedding': grpc.unary_unary_rpc_method_handler(
-                    servicer.Embedding,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.EmbeddingResult.SerializeToString,
-            ),
-            'GenerateImage': grpc.unary_unary_rpc_method_handler(
-                    servicer.GenerateImage,
-                    request_deserializer=backend__pb2.GenerateImageRequest.FromString,
-                    response_serializer=backend__pb2.Result.SerializeToString,
-            ),
-            'AudioTranscription': grpc.unary_unary_rpc_method_handler(
-                    servicer.AudioTranscription,
-                    request_deserializer=backend__pb2.TranscriptRequest.FromString,
-                    response_serializer=backend__pb2.TranscriptResult.SerializeToString,
-            ),
-            'TTS': grpc.unary_unary_rpc_method_handler(
-                    servicer.TTS,
-                    request_deserializer=backend__pb2.TTSRequest.FromString,
-                    response_serializer=backend__pb2.Result.SerializeToString,
-            ),
-            'TokenizeString': grpc.unary_unary_rpc_method_handler(
-                    servicer.TokenizeString,
-                    request_deserializer=backend__pb2.PredictOptions.FromString,
-                    response_serializer=backend__pb2.TokenizationResponse.SerializeToString,
-            ),
-            'Status': grpc.unary_unary_rpc_method_handler(
-                    servicer.Status,
-                    request_deserializer=backend__pb2.HealthMessage.FromString,
-                    response_serializer=backend__pb2.StatusResponse.SerializeToString,
-            ),
-    }
-    generic_handler = grpc.method_handlers_generic_handler(
-            'backend.Backend', rpc_method_handlers)
-    server.add_generic_rpc_handlers((generic_handler,))
-
-
- # This class is part of an EXPERIMENTAL API.
-class Backend(object):
-    """Missing associated documentation comment in .proto file."""
-
-    @staticmethod
-    def Health(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Health',
-            backend__pb2.HealthMessage.SerializeToString,
-            backend__pb2.Reply.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Predict(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Predict',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.Reply.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def LoadModel(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/LoadModel',
-            backend__pb2.ModelOptions.SerializeToString,
-            backend__pb2.Result.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def PredictStream(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_stream(request, target, '/backend.Backend/PredictStream',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.Reply.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Embedding(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Embedding',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.EmbeddingResult.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def GenerateImage(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/GenerateImage',
-            backend__pb2.GenerateImageRequest.SerializeToString,
-            backend__pb2.Result.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def AudioTranscription(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/AudioTranscription',
-            backend__pb2.TranscriptRequest.SerializeToString,
-            backend__pb2.TranscriptResult.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def TTS(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/TTS',
-            backend__pb2.TTSRequest.SerializeToString,
-            backend__pb2.Result.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def TokenizeString(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/TokenizeString',
-            backend__pb2.PredictOptions.SerializeToString,
-            backend__pb2.TokenizationResponse.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
-
-    @staticmethod
-    def Status(request,
-            target,
-            options=(),
-            channel_credentials=None,
-            call_credentials=None,
-            insecure=False,
-            compression=None,
-            wait_for_ready=None,
-            timeout=None,
-            metadata=None):
-        return grpc.experimental.unary_unary(request, target, '/backend.Backend/Status',
-            backend__pb2.HealthMessage.SerializeToString,
-            backend__pb2.StatusResponse.FromString,
-            options, channel_credentials,
-            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)

backend/python/vllm/run.sh

@@ -1,14 +0,0 @@
-#!/bin/bash
-
-##
-## A bash script wrapper that runs the diffusers server with conda
-
-export PATH=$PATH:/opt/conda/bin
-
-# Activate conda environment
-source activate vllm
-
-# get the directory where the bash script is located
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-
-python $DIR/backend_vllm.py $@

backend/python/vllm/test_backend_vllm.py

@@ -1,41 +0,0 @@
-import unittest
-import subprocess
-import time
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-import unittest
-import subprocess
-import time
-import grpc
-import backend_pb2_grpc
-import backend_pb2
-
-class TestBackendServicer(unittest.TestCase):
-    """
-    TestBackendServicer is the class that tests the gRPC service.
-
-    This class contains methods to test the startup and shutdown of the gRPC service.
-    """
-    def setUp(self):
-        self.service = subprocess.Popen(["python", "backend_vllm.py", "--addr", "localhost:50051"])
-
-    def tearDown(self) -> None:
-        self.service.terminate()
-        self.service.wait()
-
-    def test_server_startup(self):
-        time.sleep(2)
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.Health(backend_pb2.HealthMessage())
-                self.assertEqual(response.message, b'OK')
-        except Exception as err:
-            print(err)
-            self.fail("Server failed to start")
-        finally:
-            self.tearDown()

backend/python/vllm/vllm.yml

@@ -1,99 +0,0 @@
-name: vllm
-channels:
-  - defaults
-dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - bzip2=1.0.8=h7b6447c_0
-  - ca-certificates=2023.08.22=h06a4308_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libffi=3.4.4=h6a678d5_0
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libuuid=1.41.5=h5eee18b_0
-  - ncurses=6.4=h6a678d5_0
-  - openssl=3.0.11=h7f8727e_2
-  - pip=23.2.1=py311h06a4308_0
-  - python=3.11.5=h955ad1f_0
-  - readline=8.2=h5eee18b_0
-  - setuptools=68.0.0=py311h06a4308_0
-  - sqlite=3.41.2=h5eee18b_0
-  - tk=8.6.12=h1ccaba5_0
-  - wheel=0.41.2=py311h06a4308_0
-  - xz=5.4.2=h5eee18b_0
-  - zlib=1.2.13=h5eee18b_0
-  - pip:
-      - aiosignal==1.3.1
-      - anyio==3.7.1
-      - attrs==23.1.0
-      - certifi==2023.7.22
-      - charset-normalizer==3.3.0
-      - click==8.1.7
-      - cmake==3.27.6
-      - fastapi==0.103.2
-      - filelock==3.12.4
-      - frozenlist==1.4.0
-      - fsspec==2023.9.2
-      - grpcio==1.59.0
-      - h11==0.14.0
-      - httptools==0.6.0
-      - huggingface-hub==0.17.3
-      - idna==3.4
-      - jinja2==3.1.2
-      - jsonschema==4.19.1
-      - jsonschema-specifications==2023.7.1
-      - lit==17.0.2
-      - markupsafe==2.1.3
-      - mpmath==1.3.0
-      - msgpack==1.0.7
-      - networkx==3.1
-      - ninja==1.11.1
-      - numpy==1.26.0
-      - nvidia-cublas-cu11==11.10.3.66
-      - nvidia-cuda-cupti-cu11==11.7.101
-      - nvidia-cuda-nvrtc-cu11==11.7.99
-      - nvidia-cuda-runtime-cu11==11.7.99
-      - nvidia-cudnn-cu11==8.5.0.96
-      - nvidia-cufft-cu11==10.9.0.58
-      - nvidia-curand-cu11==10.2.10.91
-      - nvidia-cusolver-cu11==11.4.0.1
-      - nvidia-cusparse-cu11==11.7.4.91
-      - nvidia-nccl-cu11==2.14.3
-      - nvidia-nvtx-cu11==11.7.91
-      - packaging==23.2
-      - pandas==2.1.1
-      - protobuf==4.24.4
-      - psutil==5.9.5
-      - pyarrow==13.0.0
-      - pydantic==1.10.13
-      - python-dateutil==2.8.2
-      - python-dotenv==1.0.0
-      - pytz==2023.3.post1
-      - pyyaml==6.0.1
-      - ray==2.7.0
-      - referencing==0.30.2
-      - regex==2023.10.3
-      - requests==2.31.0
-      - rpds-py==0.10.4
-      - safetensors==0.4.0
-      - sentencepiece==0.1.99
-      - six==1.16.0
-      - sniffio==1.3.0
-      - starlette==0.27.0
-      - sympy==1.12
-      - tokenizers==0.14.1
-      - torch==2.0.1
-      - tqdm==4.66.1
-      - transformers==4.34.0
-      - triton==2.0.0
-      - typing-extensions==4.8.0
-      - tzdata==2023.3
-      - urllib3==2.0.6
-      - uvicorn==0.23.2
-      - uvloop==0.17.0
-      - vllm==0.2.0
-      - watchfiles==0.20.0
-      - websockets==11.0.3
-      - xformers==0.0.22
-prefix: /opt/conda/envs/vllm

cmd/grpc/bert-embeddings/main.go

@@ -5,6 +5,7 @@ package main
 import (
 	"flag"
 
+	bert "github.com/go-skynet/LocalAI/pkg/backend/llm/bert"
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
@@ -15,7 +16,7 @@ var (
 func main() {
 	flag.Parse()
 
-	if err := grpc.StartServer(*addr, &StableDiffusion{}); err != nil {
+	if err := grpc.StartServer(*addr, &bert.Embeddings{}); err != nil {
 		panic(err)
 	}
 }

cmd/grpc/bloomz/main.go

@@ -5,6 +5,8 @@ package main
 import (
 	"flag"
 
+	bloomz "github.com/go-skynet/LocalAI/pkg/backend/llm/bloomz"
+
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
@@ -15,7 +17,7 @@ var (
 func main() {
 	flag.Parse()
 
-	if err := grpc.StartServer(*addr, &LLM{}); err != nil {
+	if err := grpc.StartServer(*addr, &bloomz.LLM{}); err != nil {
 		panic(err)
 	}
 }

cmd/grpc/dolly/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	transformers "github.com/go-skynet/LocalAI/backend/go/llm/transformers"
+	transformers "github.com/go-skynet/LocalAI/pkg/backend/llm/transformers"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

cmd/grpc/falcon-ggml/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	transformers "github.com/go-skynet/LocalAI/backend/go/llm/transformers"
+	transformers "github.com/go-skynet/LocalAI/pkg/backend/llm/transformers"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

cmd/grpc/falcon/main.go

@@ -0,0 +1,25 @@
+package main
+
+// GRPC Falcon server
+
+// Note: this is started internally by LocalAI and a server is allocated for each model
+
+import (
+	"flag"
+
+	falcon "github.com/go-skynet/LocalAI/pkg/backend/llm/falcon"
+
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+func main() {
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &falcon.LLM{}); err != nil {
+		panic(err)
+	}
+}

cmd/grpc/gpt2/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	transformers "github.com/go-skynet/LocalAI/backend/go/llm/transformers"
+	transformers "github.com/go-skynet/LocalAI/pkg/backend/llm/transformers"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

cmd/grpc/gpt4all/main.go

@@ -5,6 +5,8 @@ package main
 import (
 	"flag"
 
+	gpt4all "github.com/go-skynet/LocalAI/pkg/backend/llm/gpt4all"
+
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
@@ -15,7 +17,7 @@ var (
 func main() {
 	flag.Parse()
 
-	if err := grpc.StartServer(*addr, &LLM{}); err != nil {
+	if err := grpc.StartServer(*addr, &gpt4all.LLM{}); err != nil {
 		panic(err)
 	}
 }

cmd/grpc/gptj/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	transformers "github.com/go-skynet/LocalAI/backend/go/llm/transformers"
+	transformers "github.com/go-skynet/LocalAI/pkg/backend/llm/transformers"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

cmd/grpc/gptneox/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	transformers "github.com/go-skynet/LocalAI/backend/go/llm/transformers"
+	transformers "github.com/go-skynet/LocalAI/pkg/backend/llm/transformers"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )