debug

.github/ci/modelslist.go

@@ -75,7 +75,7 @@ var modelPageTemplate string = `
     <div class="container mx-auto px-4 py-4">
         <div class="flex items-center justify-between">
             <div class="flex items-center">
-                <a href="/" class="text-white text-xl font-bold"><img src="https://github.com/mudler/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd" alt="LocalAI Logo" class="h-10 mr-3 border-2 border-gray-300 shadow rounded"></a>
+                <a href="/" class="text-white text-xl font-bold"><img src="https://github.com/go-skynet/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd" alt="LocalAI Logo" class="h-10 mr-3 border-2 border-gray-300 shadow rounded"></a>
                 <a href="/" class="text-white text-xl font-bold">LocalAI</a>
             </div>
             <!-- Menu button for small screens -->
@@ -114,12 +114,12 @@ var modelPageTemplate string = `
 
 	<h2 class="text-center text-3xl font-semibold text-gray-100">
 
-	 🖼️ Available {{.AvailableModels}} models</i> <a href="https://localai.io/models/" target="_blank" >
+	 🖼️ Available {{.AvailableModels}} models</i> repositories     <a href="https://localai.io/models/" target="_blank" >
 			<i class="fas fa-circle-info pr-2"></i>
 		</a></h2> 
 
 	<h3>	  
-	Refer to the Model gallery <a href="https://localai.io/models/" target="_blank" ><i class="fas fa-circle-info pr-2"></i></a> for more information on how to use the models with LocalAI.<br>
+	Refer to <a href="https://localai.io/models" target=_blank> Model gallery</a> for more information on how to use the models with LocalAI.
 
 	You can install models with the CLI command <code>local-ai models install <model-name></code>. or by using the WebUI.
 	</h3>

.github/workflows/image-pr.yml

@@ -32,7 +32,7 @@ jobs:
     strategy:
       # Pushing with all jobs in parallel
       # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 4 || 8 }}
+      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
           - build-type: ''
@@ -46,7 +46,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg'
@@ -119,7 +119,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg-core'
@@ -128,12 +128,3 @@ jobs:
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"

.github/workflows/image.yml

@@ -39,7 +39,7 @@ jobs:
     strategy:
       # Pushing with all jobs in parallel
       # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 6 || 12 }}
+      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
           # Extra images
@@ -64,7 +64,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11'
@@ -75,7 +75,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12'
@@ -86,7 +86,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-cublas-cuda11-ffmpeg'
@@ -100,7 +100,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-cublas-cuda12-ffmpeg'
@@ -266,61 +266,52 @@ jobs:
             ffmpeg: 'true'
             image-type: 'core'
             base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             aio: "-aio-cpu"
             latest-image: 'latest-cpu'
             latest-image-aio: 'latest-aio-cpu'
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11-core'
             ffmpeg: ''
             image-type: 'core'
             base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-core'
             ffmpeg: ''
             image-type: 'core'
             base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64,linux/arm64'
-            tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"

.github/workflows/image_build.yml

@@ -19,11 +19,11 @@ on:
         type: string
       cuda-major-version:
         description: 'CUDA major version'
-        default: "12"
+        default: "11"
         type: string
       cuda-minor-version:
         description: 'CUDA minor version'
-        default: "5"
+        default: "7"
         type: string
       platforms:
         description: 'Platforms'

.github/workflows/release.yaml

@@ -40,7 +40,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y cuda-cross-aarch64 cuda-nvcc-cross-aarch64-${CUDA_VERSION} libcublas-cross-aarch64-${CUDA_VERSION}
         env:
-          CUDA_VERSION: 12-5
+          CUDA_VERSION: 12-4
       - name: Cache grpc
         id: cache-grpc
         uses: actions/cache@v4
@@ -100,14 +100,7 @@ jobs:
           go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.0
           export PATH=$PATH:$GOPATH/bin
           export PATH=/usr/local/cuda/bin:$PATH
-          sudo rm -rf /usr/aarch64-linux-gnu/lib/libstdc++.so.6
+          GO_TAGS=p2p GOOS=linux GOARCH=arm64 CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
-          sudo cp -rf /usr/aarch64-linux-gnu/lib/libstdc++.so* /usr/aarch64-linux-gnu/lib/libstdc++.so.6
-          sudo cp /usr/aarch64-linux-gnu/lib/ld-linux-aarch64.so.1 ld.so
-          GO_TAGS=p2p \
-          BACKEND_LIBS="./grpc/cmake/cross_build/third_party/re2/libre2.a ./grpc/cmake/cross_build/libgrpc.a ./grpc/cmake/cross_build/libgrpc++.a ./grpc/cmake/cross_build/third_party/protobuf/libprotobuf.a /usr/aarch64-linux-gnu/lib/libc.so.6 /usr/aarch64-linux-gnu/lib/libstdc++.so.6 /usr/aarch64-linux-gnu/lib/libgomp.so.1 /usr/aarch64-linux-gnu/lib/libm.so.6 /usr/aarch64-linux-gnu/lib/libgcc_s.so.1 /usr/aarch64-linux-gnu/lib/libdl.so.2 /usr/aarch64-linux-gnu/lib/libpthread.so.0 ./ld.so" \
-          GOOS=linux \
-          GOARCH=arm64 \
-          CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
       - uses: actions/upload-artifact@v4
         with:
           name: LocalAI-linux-arm64
@@ -118,13 +111,7 @@ jobs:
         with:
           files: |
             release/*
-      - name: Setup tmate session if tests fail
+
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
   build-linux:
     runs-on: arc-runner-set
     steps:
@@ -203,7 +190,6 @@ jobs:
       - name: Install gRPC
         run: |
           cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install
-      # BACKEND_LIBS needed for gpu-workload: /opt/intel/oneapi/*/lib/libiomp5.so /opt/intel/oneapi/*/lib/libmkl_core.so /opt/intel/oneapi/*/lib/libmkl_core.so.2 /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so.2 /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so.4 /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so.2 /opt/intel/oneapi/*/lib/libsycl.so /opt/intel/oneapi/*/lib/libsycl.so.7 /opt/intel/oneapi/*/lib/libsycl.so.7.1.0 /opt/rocm-*/lib/libamdhip64.so /opt/rocm-*/lib/libamdhip64.so.5 /opt/rocm-*/lib/libamdhip64.so.6 /opt/rocm-*/lib/libamdhip64.so.6.1.60100 /opt/rocm-*/lib/libhipblas.so /opt/rocm-*/lib/libhipblas.so.2 /opt/rocm-*/lib/libhipblas.so.2.1.60100 /opt/rocm-*/lib/librocblas.so /opt/rocm-*/lib/librocblas.so.4 /opt/rocm-*/lib/librocblas.so.4.1.60100 /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1.0.0 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/local/cuda-*/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-*/targets/x86_64-linux/lib/stubs/libcuda.so
       - name: Build
         id: build
         run: |
@@ -213,10 +199,7 @@ jobs:
           export PATH=/usr/local/cuda/bin:$PATH
           export PATH=/opt/rocm/bin:$PATH
           source /opt/intel/oneapi/setvars.sh
-          sudo cp /lib64/ld-linux-x86-64.so.2 ld.so
+          GO_TAGS=p2p make -j4 dist
-          GO_TAGS=p2p \
-          BACKEND_LIBS="./ld.so /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/libgomp.so.1" \
-          make -j4 dist
       - uses: actions/upload-artifact@v4
         with:
           name: LocalAI-linux
@@ -227,13 +210,7 @@ jobs:
         with:
           files: |
             release/*
-      - name: Setup tmate session if tests fail
+
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
   build-stablediffusion:
     runs-on: ubuntu-latest
     steps:
@@ -272,6 +249,11 @@ jobs:
   build-macOS-arm64:
     runs-on: macos-14
     steps:
+      - name: Setup tmate session if tests fail
+        uses: mxschmitt/action-tmate@v3.18
+        with:
+          connect-timeout-seconds: 180
+          limit-access-to-actor: true
       - name: Clone
         uses: actions/checkout@v4
         with:
@@ -291,8 +273,7 @@ jobs:
           export C_INCLUDE_PATH=/usr/local/include
           export CPLUS_INCLUDE_PATH=/usr/local/include
           export PATH=$PATH:$GOPATH/bin
-
+          GO_TAGS=p2p make dist
-          BACKEND_LIBS="$(ls /opt/homebrew/opt/grpc/lib/*.dylib /opt/homebrew/opt/re2/lib/*.dylib /opt/homebrew/opt/openssl@3/lib/*.dylib /opt/homebrew/opt/protobuf/lib/*.dylib /opt/homebrew/opt/abseil/lib/*.dylib | xargs)" GO_TAGS=p2p make dist
       - uses: actions/upload-artifact@v4
         with:
           name: LocalAI-MacOS-arm64
@@ -303,10 +284,3 @@ jobs:
         with:
           files: |
             release/*
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true

Dockerfile

@@ -33,7 +33,7 @@ RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | ta
 ENV PATH $PATH:/root/go/bin:/usr/local/go/bin
 
 # Install grpc compilers
-RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
+RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.1 && \
     go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
 
 COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
@@ -98,27 +98,11 @@ RUN pip install --user grpcio-tools
 FROM requirements-${IMAGE_TYPE} AS requirements-drivers
 
 ARG BUILD_TYPE
-ARG CUDA_MAJOR_VERSION=12
+ARG CUDA_MAJOR_VERSION=11
-ARG CUDA_MINOR_VERSION=5
+ARG CUDA_MINOR_VERSION=8
 
 ENV BUILD_TYPE=${BUILD_TYPE}
 
-# Vulkan requirements
-RUN <<EOT bash
-    if [ "${BUILD_TYPE}" = "vulkan" ]; then
-        apt-get update && \
-        apt-get install -y  --no-install-recommends \
-                        software-properties-common pciutils wget gpg-agent && \
-        wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
-        wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
-        apt-get update && \
-            apt-get install -y \
-            vulkan-sdk && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/*
-    fi
-EOT
-
 # CuBLAS requirements
 RUN <<EOT bash
     if [ "${BUILD_TYPE}" = "cublas" ]; then
@@ -308,7 +292,7 @@ ENV REBUILD=false
 ENV HEALTHCHECK_ENDPOINT=http://localhost:8080/readyz
 ENV MAKEFLAGS=${MAKEFLAGS}
 
-ARG CUDA_MAJOR_VERSION=12
+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

Makefile

@@ -5,7 +5,7 @@ BINARY_NAME=local-ai
 
 # llama.cpp versions
 GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=e112b610a1a75cb7fa8351e1a933e2e7a755a5ce
+CPPLLAMA_VERSION?=172c8256840ffd882ab9992ecedbb587d9b21f15
 
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
@@ -103,10 +103,6 @@ ifeq ($(BUILD_TYPE),cublas)
 	CGO_LDFLAGS_WHISPER+=-L$(CUDA_LIBPATH)/stubs/ -lcuda -lcufft
 endif
 
-ifeq ($(BUILD_TYPE),vulkan)
-	CMAKE_ARGS+=-DLLAMA_VULKAN=1
-endif
-
 ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_HOME ?= /opt/rocm
 	ROCM_PATH ?= /opt/rocm
@@ -317,10 +313,6 @@ build: prepare backend-assets grpcs ## Build the project
 	$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
 	$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
 	$(info ${GREEN}I LD_FLAGS: ${YELLOW}$(LD_FLAGS)${RESET})
-ifneq ($(BACKEND_LIBS),)
-	$(MAKE) backend-assets/lib
-	cp $(BACKEND_LIBS) backend-assets/lib/
-endif
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./
 
 build-minimal:
@@ -329,11 +321,8 @@ build-minimal:
 build-api:
 	BUILD_GRPC_FOR_BACKEND_LLAMA=true BUILD_API_ONLY=true GO_TAGS=none $(MAKE) build
 
-backend-assets/lib:
-	mkdir -p backend-assets/lib
-
 dist:
-	$(MAKE) backend-assets/grpc/llama-cpp-avx2
+	STATIC=true $(MAKE) backend-assets/grpc/llama-cpp-avx2
 ifeq ($(OS),Darwin)
 	$(info ${GREEN}I Skip CUDA/hipblas build on MacOS${RESET})
 else
@@ -342,7 +331,7 @@ else
 	$(MAKE) backend-assets/grpc/llama-cpp-sycl_f16
 	$(MAKE) backend-assets/grpc/llama-cpp-sycl_f32
 endif
-	STATIC=true $(MAKE) build
+	$(MAKE) build
 	mkdir -p release
 # if BUILD_ID is empty, then we don't append it to the binary name
 ifeq ($(BUILD_ID),)
@@ -355,7 +344,7 @@ endif
 
 dist-cross-linux-arm64: 
 	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_NATIVE=off" GRPC_BACKENDS="backend-assets/grpc/llama-cpp-fallback backend-assets/grpc/llama-cpp-grpc backend-assets/util/llama-cpp-rpc-server" \
-	STATIC=true $(MAKE) build
+	$(MAKE) build
 	mkdir -p release
 # if BUILD_ID is empty, then we don't append it to the binary name
 ifeq ($(BUILD_ID),)
@@ -404,7 +393,7 @@ 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 $(TEST_DIR)/ggllm-test-model.bin
-	docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=5 --build-arg FFMPEG=true -t localai-tests .
+	docker build --build-arg GRPC_BACKENDS="$(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 $(abspath ./tests/e2e-fixtures)
@@ -814,17 +803,6 @@ docker:
 		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
 		-t $(DOCKER_IMAGE) .
 
-docker-cuda11:
-	docker build \
-		--build-arg CUDA_MAJOR_VERSION=11 \
-		--build-arg CUDA_MINOR_VERSION=8 \
-		--build-arg BASE_IMAGE=$(BASE_IMAGE) \
-		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
-		--build-arg GO_TAGS="$(GO_TAGS)" \
-		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
-		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
-		-t $(DOCKER_IMAGE)-cuda11 .
-
 docker-aio:
 	@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"
 	docker build \

README.md

@@ -48,13 +48,6 @@
 
 ![screen](https://github.com/mudler/LocalAI/assets/2420543/20b5ccd2-8393-44f0-aaf6-87a23806381e)
 
-Run the installer script:
-
-```bash
-curl https://localai.io/install.sh | sh
-```
-
-Or run with docker:
 ```bash
 docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
 # Alternative images:
@@ -72,7 +65,6 @@ docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
 
 [Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
 
-- 🆕 You can browse now the model gallery without LocalAI! Check out https://models.localai.io
 - 🔥🔥 Decentralized llama.cpp:  https://github.com/mudler/LocalAI/pull/2343 (peer2peer llama.cpp!) 👉 Docs  https://localai.io/features/distribute/
 - 🔥🔥 Openvoice: https://github.com/mudler/LocalAI/pull/2334
 - 🆕 Function calls without grammars and mixed mode: https://github.com/mudler/LocalAI/pull/2328

backend/backend.proto

@@ -230,7 +230,6 @@ message TranscriptRequest {
   string dst = 2;
   string language = 3;
   uint32 threads = 4;
-  bool translate = 5;
 }
 
 message TranscriptResult {

backend/go/image/stablediffusion/main.go

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

backend/go/image/stablediffusion/stablediffusion.go

@@ -3,9 +3,9 @@ package main
 // This is a wrapper to statisfy the GRPC service interface
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/stablediffusion"
+	"github.com/go-skynet/LocalAI/pkg/stablediffusion"
 )
 
 type Image struct {

backend/go/image/tinydream/main.go

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

backend/go/image/tinydream/tinydream.go

@@ -3,9 +3,9 @@ package main
 // This is a wrapper to statisfy the GRPC service interface
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/tinydream"
+	"github.com/go-skynet/LocalAI/pkg/tinydream"
 )
 
 type Image struct {

backend/go/llm/bert/bert.go

@@ -5,8 +5,8 @@ package main
 import (
 	bert "github.com/go-skynet/go-bert.cpp"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )
 
 type Embeddings struct {

backend/go/llm/bert/main.go

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

backend/go/llm/gpt4all/gpt4all.go

@@ -5,8 +5,8 @@ package main
 import (
 	"fmt"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	gpt4all "github.com/nomic-ai/gpt4all/gpt4all-bindings/golang"
 )
 

backend/go/llm/gpt4all/main.go

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

backend/go/llm/langchain/langchain.go

@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"os"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/langchain"
+	"github.com/go-skynet/LocalAI/pkg/langchain"
 )
 
 type LLM struct {

backend/go/llm/langchain/main.go

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

backend/go/llm/llama-ggml/llama.go

@@ -5,9 +5,9 @@ package main
 import (
 	"fmt"
 
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	"github.com/go-skynet/go-llama.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
 )
 
 type LLM struct {

backend/go/llm/llama-ggml/main.go

@@ -3,7 +3,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/llama/llama.go

@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"path/filepath"
 
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
 	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	"github.com/go-skynet/go-llama.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
 )
 
 type LLM struct {

backend/go/llm/llama/main.go

@@ -7,7 +7,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/rwkv/main.go

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

backend/go/llm/rwkv/rwkv.go

@@ -7,8 +7,8 @@ import (
 	"path/filepath"
 
 	"github.com/donomii/go-rwkv.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )
 
 const tokenizerSuffix = ".tokenizer.json"
@@ -31,7 +31,7 @@ func (llm *LLM) Load(opts *pb.ModelOptions) error {
 	model := rwkv.LoadFiles(opts.ModelFile, tokenizerPath, uint32(opts.GetThreads()))
 
 	if model == nil {
-		return fmt.Errorf("rwkv could not load model")
+		return fmt.Errorf("could not load model")
 	}
 	llm.rwkv = model
 	return nil

backend/go/stores/main.go

@@ -6,7 +6,7 @@ import (
 	"flag"
 	"os"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )

backend/go/stores/store.go

@@ -8,8 +8,8 @@ import (
 	"math"
 	"slices"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 
 	"github.com/rs/zerolog/log"
 )

backend/go/transcribe/main.go

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

backend/go/transcribe/transcript.go

@@ -8,7 +8,7 @@ import (
 
 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
 	"github.com/go-audio/wav"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 )
 
 func ffmpegCommand(args []string) (string, error) {
@@ -29,7 +29,7 @@ func audioToWav(src, dst string) error {
 	return nil
 }
 
-func Transcript(model whisper.Model, audiopath, language string, translate bool, threads uint) (schema.TranscriptionResult, error) {
+func Transcript(model whisper.Model, audiopath, language string, threads uint) (schema.TranscriptionResult, error) {
 	res := schema.TranscriptionResult{}
 
 	dir, err := os.MkdirTemp("", "whisper")
@@ -75,10 +75,6 @@ func Transcript(model whisper.Model, audiopath, language string, translate bool,
 		context.SetLanguage("auto")
 	}
 
-	if translate {
-		context.SetTranslate(true)
-	}
-
 	if err := context.Process(data, nil, nil); err != nil {
 		return res, err
 	}

backend/go/transcribe/whisper.go

@@ -4,9 +4,9 @@ package main
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )
 
 type Whisper struct {
@@ -22,5 +22,5 @@ func (sd *Whisper) Load(opts *pb.ModelOptions) error {
 }
 
 func (sd *Whisper) AudioTranscription(opts *pb.TranscriptRequest) (schema.TranscriptionResult, error) {
-	return Transcript(sd.whisper, opts.Dst, opts.Language, opts.Translate, uint(opts.Threads))
+	return Transcript(sd.whisper, opts.Dst, opts.Language, uint(opts.Threads))
 }

backend/go/tts/main.go

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

backend/go/tts/piper.go

@@ -7,8 +7,8 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	piper "github.com/mudler/go-piper"
 )
 

backend/python/diffusers/backend.py

@@ -17,7 +17,7 @@ import backend_pb2_grpc
 
 import grpc
 
-from diffusers import StableDiffusion3Pipeline, StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler
+from diffusers import StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler
 from diffusers import StableDiffusionImg2ImgPipeline, AutoPipelineForText2Image, ControlNetModel, StableVideoDiffusionPipeline
 from diffusers.pipelines.stable_diffusion import safety_checker
 from diffusers.utils import load_image,export_to_video
@@ -225,17 +225,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                         torch_dtype=torchType, 
                         use_safetensors=True, 
                         variant=variant)
-            elif request.PipelineType == "StableDiffusion3Pipeline":
-                if fromSingleFile:
-                    self.pipe = StableDiffusion3Pipeline.from_single_file(modelFile,
-                                                               torch_dtype=torchType,
-                                                               use_safetensors=True)
-                else:
-                    self.pipe = StableDiffusion3Pipeline.from_pretrained(
-                        request.Model, 
-                        torch_dtype=torchType, 
-                        use_safetensors=True, 
-                        variant=variant)
 
             if CLIPSKIP and request.CLIPSkip != 0:
                 self.clip_skip = request.CLIPSkip

backend/python/diffusers/requirements.txt

@@ -5,7 +5,6 @@ grpcio==1.64.0
 opencv-python
 pillow
 protobuf
-sentencepiece
 torch
 transformers
 certifi

core/application.go

@@ -1,9 +1,9 @@
 package core
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )
 
 // The purpose of this structure is to hold pointers to all initialized services, to make plumbing easy

core/backend/embeddings.go

@@ -3,10 +3,10 @@ package backend
 import (
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() ([]float32, error), error) {

core/backend/image.go

@@ -1,10 +1,10 @@
 package backend
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negative_prompt, src, dst string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() error, error) {

core/backend/llm.go

@@ -9,14 +9,14 @@ import (
 	"sync"
 	"unicode/utf8"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )
 
 type LLMResponse struct {

core/backend/options.go

@@ -5,9 +5,9 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/backend/rerank.go

@@ -4,9 +4,9 @@ import (
 	"context"
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func Rerank(backend, modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

core/backend/stores.go

@@ -1,10 +1,10 @@
 package backend
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func StoreBackend(sl *model.ModelLoader, appConfig *config.ApplicationConfig, storeName string) (grpc.Backend, error) {

core/backend/transcript.go

@@ -4,14 +4,14 @@ import (
 	"context"
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
-func ModelTranscription(audio, language string, translate bool, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {
+func ModelTranscription(audio, language string, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {
 
 	opts := modelOpts(backendConfig, appConfig, []model.Option{
 		model.WithBackendString(model.WhisperBackend),
@@ -31,9 +31,8 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 	}
 
 	return whisperModel.AudioTranscription(context.Background(), &proto.TranscriptRequest{
-		Dst:       audio,
+		Dst:      audio,
-		Language:  language,
+		Language: language,
-		Translate: translate,
+		Threads:  uint32(*backendConfig.Threads),
-		Threads:   uint32(*backendConfig.Threads),
 	})
 }

core/backend/tts.go

@@ -6,11 +6,11 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )
 
 func generateUniqueFileName(dir, baseName, ext string) string {

core/cli/cli.go

@@ -1,8 +1,8 @@
 package cli
 
 import (
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/cli/worker"
+	"github.com/go-skynet/LocalAI/core/cli/worker"
 )
 
 var CLI struct {

core/cli/models.go

@@ -4,12 +4,10 @@ import (
 	"encoding/json"
 	"fmt"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/startup"
-	"github.com/mudler/LocalAI/pkg/startup"
 	"github.com/rs/zerolog/log"
 	"github.com/schollz/progressbar/v3"
 )
@@ -35,7 +33,7 @@ type ModelsCMD struct {
 }
 
 func (ml *ModelsList) Run(ctx *cliContext.Context) error {
-	var galleries []config.Gallery
+	var galleries []gallery.Gallery
 	if err := json.Unmarshal([]byte(ml.Galleries), &galleries); err != nil {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
@@ -55,11 +53,10 @@ func (ml *ModelsList) Run(ctx *cliContext.Context) error {
 }
 
 func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
-	var galleries []config.Gallery
+	var galleries []gallery.Gallery
 	if err := json.Unmarshal([]byte(mi.Galleries), &galleries); err != nil {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
-
 	for _, modelName := range mi.ModelArgs {
 
 		progressBar := progressbar.NewOptions(
@@ -81,15 +78,13 @@ func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
 			return err
 		}
 
-		if !downloader.LooksLikeOCI(modelName) {
+		model := gallery.FindModel(models, modelName, mi.ModelsPath)
-			model := gallery.FindModel(models, modelName, mi.ModelsPath)
+		if model == nil {
-			if model == nil {
+			log.Error().Str("model", modelName).Msg("model not found")
-				log.Error().Str("model", modelName).Msg("model not found")
+			return err
-				return err
-			}
-
-			log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
 		}
+
+		log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
 		err = startup.InstallModels(galleries, "", mi.ModelsPath, progressCallback, modelName)
 		if err != nil {
 			return err

core/cli/run.go

@@ -6,11 +6,11 @@ import (
 	"strings"
 	"time"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http"
+	"github.com/go-skynet/LocalAI/core/http"
-	"github.com/mudler/LocalAI/core/p2p"
+	"github.com/go-skynet/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/startup"
+	"github.com/go-skynet/LocalAI/core/startup"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )
@@ -43,7 +43,6 @@ type RunCMD struct {
 	Address              string   `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
 	CORS                 bool     `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
 	CORSAllowOrigins     string   `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
-	LibraryPath          string   `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
 	CSRF                 bool     `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
 	UploadLimit          int      `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
 	APIKeys              []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
@@ -81,7 +80,6 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		config.WithCors(r.CORS),
 		config.WithCorsAllowOrigins(r.CORSAllowOrigins),
 		config.WithCsrf(r.CSRF),
-		config.WithLibPath(r.LibraryPath),
 		config.WithThreads(r.Threads),
 		config.WithBackendAssets(ctx.BackendAssets),
 		config.WithBackendAssetsOutput(r.BackendAssetsPath),

core/cli/transcript.go

@@ -5,10 +5,10 @@ import (
 	"errors"
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 
@@ -18,7 +18,6 @@ type TranscriptCMD struct {
 	Backend           string `short:"b" default:"whisper" help:"Backend to run the transcription model"`
 	Model             string `short:"m" required:"" help:"Model name to run the TTS"`
 	Language          string `short:"l" help:"Language of the audio file"`
-	Translate         bool   `short:"t" help:"Translate the transcription to english"`
 	Threads           int    `short:"t" default:"1" help:"Number of threads used for parallel computation"`
 	ModelsPath        string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
 	BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
@@ -51,7 +50,7 @@ func (t *TranscriptCMD) Run(ctx *cliContext.Context) error {
 		}
 	}()
 
-	tr, err := backend.ModelTranscription(t.Filename, t.Language, t.Translate, ml, c, opts)
+	tr, err := backend.ModelTranscription(t.Filename, t.Language, ml, c, opts)
 	if err != nil {
 		return err
 	}

core/cli/tts.go

@@ -7,10 +7,10 @@ import (
 	"path/filepath"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/cli/util.go

@@ -5,7 +5,7 @@ import (
 
 	"github.com/rs/zerolog/log"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
 	gguf "github.com/thxcode/gguf-parser-go"
 )
 

core/cli/worker/worker_llamacpp.go

@@ -5,9 +5,8 @@ import (
 	"os"
 	"syscall"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/pkg/assets"
+	"github.com/go-skynet/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
 	"github.com/rs/zerolog/log"
 )
 
@@ -28,18 +27,17 @@ func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
 		return fmt.Errorf("usage: local-ai worker llama-cpp-rpc -- <llama-rpc-server-args>")
 	}
 
-	grpcProcess := assets.ResolvePath(
-		r.BackendAssetsPath,
-		"util",
-		"llama-cpp-rpc-server",
-	)
-
-	args := os.Args[4:]
-	args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
-	args = append([]string{grpcProcess}, args...)
 	return syscall.Exec(
-		grpcProcess,
+		assets.ResolvePath(
-		args,
+			r.BackendAssetsPath,
+			"util",
+			"llama-cpp-rpc-server",
+		),
+		append([]string{
+			assets.ResolvePath(
+				r.BackendAssetsPath,
+				"util",
+				"llama-cpp-rpc-server",
+			)}, os.Args[4:]...),
 		os.Environ())
 }

core/cli/worker/worker_nop2p.go

@@ -6,7 +6,7 @@ package worker
 import (
 	"fmt"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
 )
 
 type P2P struct{}

core/cli/worker/worker_p2p.go

@@ -10,10 +10,9 @@ import (
 	"os/exec"
 	"time"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/p2p"
+	"github.com/go-skynet/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/pkg/assets"
+	"github.com/go-skynet/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
 	"github.com/phayes/freeport"
 	"github.com/rs/zerolog/log"
 )
@@ -72,18 +71,13 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 	go func() {
 		for {
 			log.Info().Msgf("Starting llama-cpp-rpc-server on '%s:%d'", address, port)
-
-			grpcProcess := assets.ResolvePath(
-				r.BackendAssetsPath,
-				"util",
-				"llama-cpp-rpc-server",
-			)
-
-			args := append([]string{"--host", address, "--port", fmt.Sprint(port)}, r.ExtraLLamaCPPArgs...)
-			args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
 			cmd := exec.Command(
-				grpcProcess, args...,
+				assets.ResolvePath(
+					r.BackendAssetsPath,
+					"util",
+					"llama-cpp-rpc-server",
+				),
+				append([]string{"--host", address, "--port", fmt.Sprint(port)}, r.ExtraLLamaCPPArgs...)...,
 			)
 
 			cmd.Env = os.Environ()
@@ -92,7 +86,7 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 			cmd.Stdout = os.Stdout
 
 			if err := cmd.Start(); err != nil {
-				log.Error().Any("grpcProcess", grpcProcess).Any("args", args).Err(err).Msg("Failed to start llama-cpp-rpc-server")
+				log.Error().Err(err).Msg("Failed to start llama-cpp-rpc-server")
 			}
 
 			cmd.Wait()

core/config/application_config.go

@@ -6,7 +6,8 @@ import (
 	"encoding/json"
 	"time"
 
-	"github.com/mudler/LocalAI/pkg/xsysinfo"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/xsysinfo"
 	"github.com/rs/zerolog/log"
 )
 
@@ -14,7 +15,6 @@ type ApplicationConfig struct {
 	Context                             context.Context
 	ConfigFile                          string
 	ModelPath                           string
-	LibPath                             string
 	UploadLimitMB, Threads, ContextSize int
 	DisableWebUI                        bool
 	F16                                 bool
@@ -35,7 +35,7 @@ type ApplicationConfig struct {
 
 	ModelLibraryURL string
 
-	Galleries []Gallery
+	Galleries []gallery.Gallery
 
 	BackendAssets     embed.FS
 	AssetsDestination string
@@ -101,12 +101,6 @@ func WithModelLibraryURL(url string) AppOption {
 	}
 }
 
-func WithLibPath(path string) AppOption {
-	return func(o *ApplicationConfig) {
-		o.LibPath = path
-	}
-}
-
 var EnableWatchDog = func(o *ApplicationConfig) {
 	o.WatchDog = true
 }
@@ -179,10 +173,10 @@ func WithBackendAssets(f embed.FS) AppOption {
 func WithStringGalleries(galls string) AppOption {
 	return func(o *ApplicationConfig) {
 		if galls == "" {
-			o.Galleries = []Gallery{}
+			o.Galleries = []gallery.Gallery{}
 			return
 		}
-		var galleries []Gallery
+		var galleries []gallery.Gallery
 		if err := json.Unmarshal([]byte(galls), &galleries); err != nil {
 			log.Error().Err(err).Msg("failed loading galleries")
 		}
@@ -190,7 +184,7 @@ func WithStringGalleries(galls string) AppOption {
 	}
 }
 
-func WithGalleries(galleries []Gallery) AppOption {
+func WithGalleries(galleries []gallery.Gallery) AppOption {
 	return func(o *ApplicationConfig) {
 		o.Galleries = append(o.Galleries, galleries...)
 	}

core/config/backend_config.go

@@ -5,10 +5,10 @@ import (
 	"regexp"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/functions"
+	"github.com/go-skynet/LocalAI/pkg/functions"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )
 
 const (
@@ -390,6 +390,10 @@ func (c *BackendConfig) Validate() bool {
 		}
 	}
 
+	if c.Name == "" {
+		return false
+	}
+
 	if c.Backend != "" {
 		// a regex that checks that is a string name with no special characters, except '-' and '_'
 		re := regexp.MustCompile(`^[a-zA-Z0-9-_]+$`)

core/config/backend_config_loader.go

@@ -11,9 +11,9 @@ import (
 	"sync"
 
 	"github.com/charmbracelet/glamour"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 	"gopkg.in/yaml.v3"
 )

core/config/backend_config_test.go

@@ -16,8 +16,7 @@ var _ = Describe("Test cases for config related functions", func() {
 			Expect(err).To(BeNil())
 			defer os.Remove(tmp.Name())
 			_, err = tmp.WriteString(
-				`backend: "../foo-bar"
+				`backend: "foo-bar"
-name: "foo"
 parameters:
   model: "foo-bar"`)
 			Expect(err).ToNot(HaveOccurred())

core/config/gallery.go

@@ -1,6 +0,0 @@
-package config
-
-type Gallery struct {
-	URL  string `json:"url" yaml:"url"`
-	Name string `json:"name" yaml:"name"`
-}

core/dependencies_manager/manager.go

@@ -5,8 +5,8 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"gopkg.in/yaml.v3"
 )
 

core/http/app.go

@@ -6,16 +6,16 @@ import (
 	"net/http"
 	"strings"
 
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/openai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/openai"
-	"github.com/mudler/LocalAI/core/http/routes"
+	"github.com/go-skynet/LocalAI/core/http/routes"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/gofiber/contrib/fiberzerolog"
 	"github.com/gofiber/fiber/v2"

core/http/app_test.go

@@ -13,15 +13,15 @@ import (
 	"path/filepath"
 	"runtime"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	. "github.com/mudler/LocalAI/core/http"
+	. "github.com/go-skynet/LocalAI/core/http"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/startup"
+	"github.com/go-skynet/LocalAI/core/startup"
 
+	"github.com/go-skynet/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/model"
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
 	"gopkg.in/yaml.v3"
@@ -74,7 +74,7 @@ func getModelStatus(url string) (response map[string]interface{}) {
 
 func getModels(url string) (response []gallery.GalleryModel) {
 	// TODO: No tests currently seem to exercise file:// urls. Fix?
-	downloader.DownloadAndUnmarshal(url, "", func(url string, i []byte) error {
+	downloader.GetURI(url, "", func(url string, i []byte) error {
 		// Unmarshal YAML data into a struct
 		return json.Unmarshal(i, &response)
 	})
@@ -247,7 +247,7 @@ var _ = Describe("API test", func() {
 			err = os.WriteFile(filepath.Join(modelDir, "gallery_simple.yaml"), out, 0600)
 			Expect(err).ToNot(HaveOccurred())
 
-			galleries := []config.Gallery{
+			galleries := []gallery.Gallery{
 				{
 					Name: "test",
 					URL:  "file://" + filepath.Join(modelDir, "gallery_simple.yaml"),
@@ -603,7 +603,7 @@ var _ = Describe("API test", func() {
 
 			c, cancel = context.WithCancel(context.Background())
 
-			galleries := []config.Gallery{
+			galleries := []gallery.Gallery{
 				{
 					Name: "model-gallery",
 					URL:  "https://raw.githubusercontent.com/go-skynet/model-gallery/main/index.yaml",

core/http/ctx/fiber.go

@@ -4,8 +4,8 @@ import (
 	"fmt"
 	"strings"
 
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/http/elements/gallery.go

@@ -6,9 +6,9 @@ import (
 
 	"github.com/chasefleming/elem-go"
 	"github.com/chasefleming/elem-go/attrs"
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/xsync"
+	"github.com/go-skynet/LocalAI/pkg/xsync"
 )
 
 const (

core/http/endpoints/elevenlabs/tts.go

@@ -1,13 +1,13 @@
 package elevenlabs
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/jina/rerank.go

@@ -1,14 +1,14 @@
 package jina
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/localai/backend_monitor.go

@@ -1,9 +1,9 @@
 package localai
 
 import (
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
 )
 
 func BackendMonitorEndpoint(bm *services.BackendMonitorService) func(c *fiber.Ctx) error {

core/http/endpoints/localai/gallery.go

@@ -5,16 +5,15 @@ import (
 	"fmt"
 	"slices"
 
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/core/services"
 	"github.com/rs/zerolog/log"
 )
 
 type ModelGalleryEndpointService struct {
-	galleries      []config.Gallery
+	galleries      []gallery.Gallery
 	modelPath      string
 	galleryApplier *services.GalleryService
 }
@@ -25,7 +24,7 @@ type GalleryModel struct {
 	gallery.GalleryModel
 }
 
-func CreateModelGalleryEndpointService(galleries []config.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
+func CreateModelGalleryEndpointService(galleries []gallery.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
 	return ModelGalleryEndpointService{
 		galleries:      galleries,
 		modelPath:      modelPath,
@@ -130,12 +129,12 @@ func (mgs *ModelGalleryEndpointService) ListModelGalleriesEndpoint() func(c *fib
 
 func (mgs *ModelGalleryEndpointService) AddModelGalleryEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		input := new(config.Gallery)
+		input := new(gallery.Gallery)
 		// Get input data from the request body
 		if err := c.BodyParser(input); err != nil {
 			return err
 		}
-		if slices.ContainsFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		if slices.ContainsFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		}) {
 			return fmt.Errorf("%s already exists", input.Name)
@@ -152,17 +151,17 @@ func (mgs *ModelGalleryEndpointService) AddModelGalleryEndpoint() func(c *fiber.
 
 func (mgs *ModelGalleryEndpointService) RemoveModelGalleryEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		input := new(config.Gallery)
+		input := new(gallery.Gallery)
 		// Get input data from the request body
 		if err := c.BodyParser(input); err != nil {
 			return err
 		}
-		if !slices.ContainsFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		if !slices.ContainsFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		}) {
 			return fmt.Errorf("%s is not currently registered", input.Name)
 		}
-		mgs.galleries = slices.DeleteFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		mgs.galleries = slices.DeleteFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		})
 		return c.Send(nil)

core/http/endpoints/localai/metrics.go

@@ -3,9 +3,9 @@ package localai
 import (
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/fiber/v2/middleware/adaptor"
-	"github.com/mudler/LocalAI/core/services"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 )
 

core/http/endpoints/localai/stores.go

@@ -1,12 +1,12 @@
 package localai
 
 import (
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/store"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/store"
 )
 
 func StoresSetEndpoint(sl *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {

core/http/endpoints/localai/tts.go

@@ -1,13 +1,13 @@
 package localai
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/localai/welcome.go

@@ -1,11 +1,11 @@
 package localai
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func WelcomeEndpoint(appConfig *config.ApplicationConfig,

core/http/endpoints/openai/assistant.go

@@ -9,10 +9,10 @@ import (
 	"sync/atomic"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	model "github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )
 
@@ -339,7 +339,7 @@ func CreateAssistantFileEndpoint(cl *config.BackendConfigLoader, ml *model.Model
 			}
 		}
 
-		return c.Status(fiber.StatusNotFound).SendString(fmt.Sprintf("Unable to find %q", assistantID))
+		return c.Status(fiber.StatusNotFound).SendString(fmt.Sprintf("Unable to find "))
 	}
 }
 

core/http/endpoints/openai/assistant_test.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"io/ioutil"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -12,9 +13,9 @@ import (
 	"testing"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/stretchr/testify/assert"
 )
 
@@ -182,7 +183,7 @@ func TestAssistantEndpoints(t *testing.T) {
 				assert.NoError(t, err)
 				assert.Equal(t, tt.expectedStatus, response.StatusCode)
 				if tt.expectedStatus != fiber.StatusOK {
-					all, _ := io.ReadAll(response.Body)
+					all, _ := ioutil.ReadAll(response.Body)
 					assert.Equal(t, tt.expectedStringResult, string(all))
 				} else {
 					var result []Assistant
@@ -278,7 +279,6 @@ func TestAssistantEndpoints(t *testing.T) {
 		assert.NoError(t, err)
 		var getAssistant Assistant
 		err = json.NewDecoder(modifyResponse.Body).Decode(&getAssistant)
-		assert.NoError(t, err)
 
 		t.Cleanup(cleanupAllAssistants(t, app, []string{getAssistant.ID}))
 
@@ -391,10 +391,7 @@ func createAssistantFile(app *fiber.App, afr AssistantFileRequest, assistantId s
 	}
 
 	var assistantFile AssistantFile
-	all, err := io.ReadAll(resp.Body)
+	all, err := ioutil.ReadAll(resp.Body)
-	if err != nil {
-		return AssistantFile{}, resp, err
-	}
 	err = json.NewDecoder(strings.NewReader(string(all))).Decode(&assistantFile)
 	if err != nil {
 		return AssistantFile{}, resp, err
@@ -425,7 +422,8 @@ func createAssistant(app *fiber.App, ar AssistantRequest) (Assistant, *http.Resp
 
 	var resultAssistant Assistant
 	err = json.NewDecoder(strings.NewReader(string(bodyString))).Decode(&resultAssistant)
-	return resultAssistant, resp, err
+
+	return resultAssistant, resp, nil
 }
 
 func cleanupAllAssistants(t *testing.T, app *fiber.App, ids []string) func() {

core/http/endpoints/openai/chat.go

@@ -8,13 +8,13 @@ import (
 	"strings"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 	"github.com/valyala/fasthttp"
 )

core/http/endpoints/openai/completion.go

@@ -8,14 +8,14 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 	"github.com/valyala/fasthttp"
 )

core/http/endpoints/openai/edit.go

@@ -5,13 +5,13 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	"github.com/go-skynet/LocalAI/core/schema"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
-	model "github.com/mudler/LocalAI/pkg/model"
 
 	"github.com/rs/zerolog/log"
 )

core/http/endpoints/openai/embeddings.go

@@ -5,12 +5,12 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
 
 	"github.com/gofiber/fiber/v2"
 	"github.com/rs/zerolog/log"

core/http/endpoints/openai/files.go

@@ -8,10 +8,10 @@ import (
 	"sync/atomic"
 	"time"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/utils"
 )
 
 var UploadedFiles []File

core/http/endpoints/openai/files_test.go

@@ -13,10 +13,10 @@ import (
 
 	"github.com/rs/zerolog/log"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	utils2 "github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	utils2 "github.com/mudler/LocalAI/pkg/utils"
 	"github.com/stretchr/testify/assert"
 
 	"testing"

core/http/endpoints/openai/image.go

@@ -13,14 +13,14 @@ import (
 	"strings"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
 
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/openai/inference.go

@@ -1,11 +1,11 @@
 package openai
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func ComputeChoices(

core/http/endpoints/openai/list.go

@@ -1,9 +1,9 @@
 package openai
 
 import (
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
 )
 
 func ListModelsEndpoint(lms *services.ListModelsService) func(ctx *fiber.Ctx) error {

core/http/endpoints/openai/request.go

@@ -2,16 +2,19 @@ package openai
 
 import (
 	"context"
+	"encoding/base64"
 	"encoding/json"
 	"fmt"
+	"io"
+	"net/http"
+	"strings"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )
 
@@ -36,6 +39,41 @@ func readRequest(c *fiber.Ctx, ml *model.ModelLoader, o *config.ApplicationConfi
 	return modelFile, input, err
 }
 
+// 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 := io.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/...;base64,", drop it
+	dropPrefix := []string{"data:image/jpeg;base64,", "data:image/png;base64,"}
+	for _, prefix := range dropPrefix {
+		if strings.HasPrefix(s, prefix) {
+			return strings.ReplaceAll(s, prefix, ""), nil
+		}
+	}
+
+	return "", fmt.Errorf("not valid string")
+}
+
 func updateRequestConfig(config *config.BackendConfig, input *schema.OpenAIRequest) {
 	if input.Echo {
 		config.Echo = input.Echo
@@ -149,7 +187,7 @@ func updateRequestConfig(config *config.BackendConfig, input *schema.OpenAIReque
 					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 := utils.GetImageURLAsBase64(pp.ImageURL.URL)
+					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
@@ -257,9 +295,5 @@ func mergeRequestWithConfig(modelFile string, input *schema.OpenAIRequest, cm *c
 	// Set the parameters for the language model prediction
 	updateRequestConfig(cfg, input)
 
-	if !cfg.Validate() {
-		return nil, nil, fmt.Errorf("failed to validate config")
-	}
-
 	return cfg, input, err
 }

core/http/endpoints/openai/transcription.go

@@ -8,9 +8,9 @@ import (
 	"path"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/gofiber/fiber/v2"
 	"github.com/rs/zerolog/log"
@@ -32,7 +32,7 @@ func TranscriptEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a
 
 		config, input, err := mergeRequestWithConfig(m, input, cl, ml, appConfig.Debug, appConfig.Threads, appConfig.ContextSize, appConfig.F16)
 		if err != nil {
-			return fmt.Errorf("failed reading parameters from request: %w", err)
+			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
 		// retrieve the file data from the request
 		file, err := c.FormFile("file")
@@ -65,7 +65,7 @@ func TranscriptEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a
 
 		log.Debug().Msgf("Audio file copied to: %+v", dst)
 
-		tr, err := backend.ModelTranscription(dst, input.Language, input.Translate, ml, *config, appConfig)
+		tr, err := backend.ModelTranscription(dst, input.Language, ml, *config, appConfig)
 		if err != nil {
 			return err
 		}

core/http/render.go

@@ -7,10 +7,10 @@ import (
 	"net/http"
 
 	"github.com/Masterminds/sprig/v3"
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
 	fiberhtml "github.com/gofiber/template/html/v2"
 	"github.com/microcosm-cc/bluemonday"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/russross/blackfriday"
 )
 
@@ -21,13 +21,14 @@ func notFoundHandler(c *fiber.Ctx) error {
 	// Check if the request accepts JSON
 	if string(c.Context().Request.Header.ContentType()) == "application/json" || len(c.Accepts("html")) == 0 {
 		// The client expects a JSON response
-		return c.Status(fiber.StatusNotFound).JSON(schema.ErrorResponse{
+		c.Status(fiber.StatusNotFound).JSON(schema.ErrorResponse{
 			Error: &schema.APIError{Message: "Resource not found", Code: fiber.StatusNotFound},
 		})
 	} else {
 		// The client expects an HTML response
-		return c.Status(fiber.StatusNotFound).Render("views/404", fiber.Map{})
+		c.Status(fiber.StatusNotFound).Render("views/404", fiber.Map{})
 	}
+	return nil
 }
 
 func renderEngine() *fiberhtml.Engine {

core/http/routes/elevenlabs.go

@@ -1,10 +1,10 @@
 package routes
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/elevenlabs"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/elevenlabs"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterElevenLabsRoutes(app *fiber.App,

core/http/routes/jina.go

@@ -1,11 +1,11 @@
 package routes
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/jina"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/jina"
 
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterJINARoutes(app *fiber.App,

core/http/routes/localai.go

@@ -1,13 +1,13 @@
 package routes
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/swagger"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterLocalAIRoutes(app *fiber.App,

core/http/routes/openai.go

@@ -1,12 +1,12 @@
 package routes
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/openai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/openai"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterOpenAIRoutes(app *fiber.App,

core/http/routes/ui.go

@@ -6,14 +6,14 @@ import (
 	"sort"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/core/http/elements"
-	"github.com/mudler/LocalAI/core/http/elements"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/internal"
-	"github.com/mudler/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/xsync"
+	"github.com/go-skynet/LocalAI/pkg/xsync"
 	"github.com/rs/zerolog/log"
 
 	"github.com/gofiber/fiber/v2"

core/http/views/talk.html

@@ -50,10 +50,6 @@
       </div>
       <div id="loader" class="my-2 loader" style="display: none;"></div>
       <div id="statustext" class="my-2 p-2 block text-white-700 text-sm font-bold mb-2" ></div>
-      <!-- Note for recording box -->
-      <div class="text-sm mb-4 text-white-500">
-        <strong>Note:</strong> You need an LLM a audio-transcription(whisper) and a tts model installed in order for this to work. Select the appropariate model from the toolbox and then click the 'Talk' button to start recording. The recording will continue until you click 'Stop recording'. Make sure your microphone is set up and enabled.
-      </div>
       <div class="mb-4" >
         <label for="modelSelect" class="block text-white-700 text-sm font-bold mb-2">LLM Model:</label>
         <select id="modelSelect"
@@ -99,7 +95,7 @@
         class="bg-red-500 hover:bg-red-700 text-white font-bold py-2 px-4 rounded focus:outline-none focus:shadow-outline"
       ><i class="fa-solid fa-microphone pr-2"></i>Talk</button>
       <a id="resetButton"
-      class="inline-block align-baseline font-bold text-sm text-blue-500 hover:text-gray-200"
+      class="inline-block align-baseline font-bold text-sm text-blue-500 hover:text-blue-800"
       href="#"
       >Reset conversation</a>
       <audio id="audioPlayback" controls hidden></audio>

core/p2p/p2p.go

@@ -13,8 +13,8 @@ import (
 	"strings"
 	"time"
 
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/libp2p/go-libp2p/core/peer"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/mudler/edgevpn/pkg/node"
 	"github.com/mudler/edgevpn/pkg/protocol"
 	"github.com/mudler/edgevpn/pkg/types"

core/schema/openai.go

@@ -3,7 +3,7 @@ package schema
 import (
 	"context"
 
-	functions "github.com/mudler/LocalAI/pkg/functions"
+	functions "github.com/go-skynet/LocalAI/pkg/functions"
 )
 
 // APIError provides error information returned by the OpenAI API.

core/schema/prediction.go

@@ -8,9 +8,6 @@ type PredictionOptions struct {
 	// Also part of the OpenAI official spec
 	Language string `json:"language"`
 
-	// Only for audio transcription
-	Translate bool `json:"translate"`
-
 	// Also part of the OpenAI official spec. use it for returning multiple results
 	N int `json:"n"`
 

core/services/backend_monitor.go

@@ -5,10 +5,10 @@ import (
 	"fmt"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/rs/zerolog/log"
 

core/services/gallery.go

@@ -8,10 +8,10 @@ import (
 	"path/filepath"
 	"sync"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/startup"
+	"github.com/go-skynet/LocalAI/pkg/startup"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"gopkg.in/yaml.v2"
 )
 
@@ -96,7 +96,6 @@ func (g *GalleryService) Start(c context.Context, cl *config.BackendConfigLoader
 				// delete a model
 				if op.Delete {
 					modelConfig := &config.BackendConfig{}
-
 					// Galleryname is the name of the model in this case
 					dat, err := os.ReadFile(filepath.Join(g.appConfig.ModelPath, op.GalleryModelName+".yaml"))
 					if err != nil {
@@ -175,7 +174,7 @@ type galleryModel struct {
 	ID                   string           `json:"id"`
 }
 
-func processRequests(modelPath string, galleries []config.Gallery, requests []galleryModel) error {
+func processRequests(modelPath string, galleries []gallery.Gallery, requests []galleryModel) error {
 	var err error
 	for _, r := range requests {
 		utils.ResetDownloadTimers()
@@ -190,7 +189,7 @@ func processRequests(modelPath string, galleries []config.Gallery, requests []ga
 	return err
 }
 
-func ApplyGalleryFromFile(modelPath, s string, galleries []config.Gallery) error {
+func ApplyGalleryFromFile(modelPath, s string, galleries []gallery.Gallery) error {
 	dat, err := os.ReadFile(s)
 	if err != nil {
 		return err
@@ -204,7 +203,7 @@ func ApplyGalleryFromFile(modelPath, s string, galleries []config.Gallery) error
 	return processRequests(modelPath, galleries, requests)
 }
 
-func ApplyGalleryFromString(modelPath, s string, galleries []config.Gallery) error {
+func ApplyGalleryFromString(modelPath, s string, galleries []gallery.Gallery) error {
 	var requests []galleryModel
 	err := json.Unmarshal([]byte(s), &requests)
 	if err != nil {

core/services/list_models.go

@@ -3,9 +3,9 @@ package services
 import (
 	"regexp"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )
 
 type ListModelsService struct {

core/services/metrics.go

@@ -31,7 +31,7 @@ func NewLocalAIMetricsService() (*LocalAIMetricsService, error) {
 		return nil, err
 	}
 	provider := metricApi.NewMeterProvider(metricApi.WithReader(exporter))
-	meter := provider.Meter("github.com/mudler/LocalAI")
+	meter := provider.Meter("github.com/go-skynet/LocalAI")
 
 	apiTimeMetric, err := meter.Float64Histogram("api_call", metric.WithDescription("api calls"))
 	if err != nil {

core/startup/config_file_watcher.go

@@ -9,8 +9,8 @@ import (
 	"time"
 
 	"github.com/fsnotify/fsnotify"
+	"github.com/go-skynet/LocalAI/core/config"
 	"github.com/imdario/mergo"
-	"github.com/mudler/LocalAI/core/config"
 	"github.com/rs/zerolog/log"
 )
 
@@ -116,7 +116,7 @@ func (c *configFileHandler) Watch() error {
 	// Add a path.
 	err = c.watcher.Add(c.appConfig.DynamicConfigsDir)
 	if err != nil {
-		return fmt.Errorf("unable to create a watcher on the configuration directory: %+v", err)
+		return fmt.Errorf("unable to establish watch on the LocalAI Configuration Directory: %+v", err)
 	}
 
 	return nil

core/startup/startup.go

@@ -4,15 +4,14 @@ import (
 	"fmt"
 	"os"
 
-	"github.com/mudler/LocalAI/core"
+	"github.com/go-skynet/LocalAI/core"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/assets"
+	"github.com/go-skynet/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
+	"github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/model"
+	pkgStartup "github.com/go-skynet/LocalAI/pkg/startup"
-	pkgStartup "github.com/mudler/LocalAI/pkg/startup"
+	"github.com/go-skynet/LocalAI/pkg/xsysinfo"
-	"github.com/mudler/LocalAI/pkg/xsysinfo"
 	"github.com/rs/zerolog/log"
 )
 
@@ -110,14 +109,6 @@ func Startup(opts ...config.AppOption) (*config.BackendConfigLoader, *model.Mode
 		}
 	}
 
-	if options.LibPath != "" {
-		// If there is a lib directory, set LD_LIBRARY_PATH to include it
-		err := library.LoadExternal(options.LibPath)
-		if err != nil {
-			log.Error().Err(err).Str("LibPath", options.LibPath).Msg("Error while loading external libraries")
-		}
-	}
-
 	// turn off any process that was started by GRPC if the context is canceled
 	go func() {
 		<-options.Context.Done()
@@ -145,37 +136,17 @@ func Startup(opts ...config.AppOption) (*config.BackendConfigLoader, *model.Mode
 	}
 
 	// Watch the configuration directory
-	startWatcher(options)
+	// If the directory does not exist, we don't watch it
+	configHandler := newConfigFileHandler(options)
+	err = configHandler.Watch()
+	if err != nil {
+		log.Error().Err(err).Msg("error establishing configuration directory watcher")
+	}
 
 	log.Info().Msg("core/startup process completed!")
 	return cl, ml, options, nil
 }
 
-func startWatcher(options *config.ApplicationConfig) {
-	if options.DynamicConfigsDir == "" {
-		// No need to start the watcher if the directory is not set
-		return
-	}
-
-	if _, err := os.Stat(options.DynamicConfigsDir); err != nil {
-		if os.IsNotExist(err) {
-			// We try to create the directory if it does not exist and was specified
-			if err := os.MkdirAll(options.DynamicConfigsDir, 0700); err != nil {
-				log.Error().Err(err).Msg("failed creating DynamicConfigsDir")
-			}
-		} else {
-			// something else happened, we log the error and don't start the watcher
-			log.Error().Err(err).Msg("failed to read DynamicConfigsDir, watcher will not be started")
-			return
-		}
-	}
-
-	configHandler := newConfigFileHandler(options)
-	if err := configHandler.Watch(); err != nil {
-		log.Error().Err(err).Msg("failed creating watcher")
-	}
-}
-
 // In Lieu of a proper DI framework, this function wires up the Application manually.
 // This is in core/startup rather than core/state.go to keep package references clean!
 func createApplication(appConfig *config.ApplicationConfig) *core.Application {

docs/content/docs/advanced/advanced-usage.md

@@ -106,202 +106,118 @@ local-ai github://mudler/LocalAI/examples/configurations/phi-2.yaml@master
 ### Full config model file reference
 
 ```yaml
-# Main configuration of the model, template, and system features.
+# Model name.
-name: "" # Model name, used to identify the model in API calls.
+# The model name is used to identify the model in the API calls.
+name: gpt-3.5-turbo
 
-# Precision settings for the model, reducing precision can enhance performance on some hardware.
+# Default model parameters.
-f16: null # Whether to use 16-bit floating-point precision.
+# These options can also be specified in the API calls
+parameters:
+  # Relative to the models path
+  model: luna-ai-llama2-uncensored.ggmlv3.q5_K_M.bin
+  # temperature
+  temperature: 0.3
+  # all the OpenAI request options here..
+  top_k: 
+  top_p: 
+  max_tokens:
+  ignore_eos: true
+  n_keep: 10
+  seed: 
+  mode: 
+  step:
+  negative_prompt:
+  typical_p:
+  tfz:
+  frequency_penalty:
 
-# Concurrency settings for the application.
+  rope_freq_base:
-threads: null # Number of threads to use for processing.
+  rope_freq_scale:
+  negative_prompt_scale:
 
-# Roles define how different entities interact in a conversational model.
+mirostat_eta:
-# It can be used to map roles to specific parts of the conversation.
+mirostat_tau:
-roles: {} # Roles for entities like user, system, assistant, etc.
+mirostat: 
+# Default context size
+context_size: 512
+# Default number of threads
+threads: 10
+# Define a backend (optional). By default it will try to guess the backend the first time the model is interacted with.
+backend: llama-stable # available: llama, stablelm, gpt2, gptj rwkv
+# stopwords (if supported by the backend)
+stopwords:
+- "HUMAN:"
+- "### Response:"
+# string to trim space to
+trimspace:
+- string
+# Strings to cut from the response
+cutstrings:
+- "string"
 
-# Backend to use for computation (like llama-cpp, diffusers, whisper).
+# Directory used to store additional assets
-backend: "" # Backend for AI computations.
+asset_dir: ""
 
-# Templates for various types of model interactions.
+# define chat roles
+roles:
+  user: "HUMAN:"
+  system: "GPT:"
+  assistant: "ASSISTANT:"
 template:
-    chat: "" # Template for chat interactions. Uses golang templates with Sprig functions.
+  # template file ".tmpl" with the prompt template to use by default on the endpoint call. Note there is no extension in the files
-    chat_message: "" # Template for individual chat messages.  Uses golang templates with Sprig functions.
+  completion: completion
-    completion: "" # Template for generating text completions. Uses golang templates with Sprig functions.
+  chat: chat
-    edit: "" # Template for edit operations. Uses golang templates with Sprig functions.
+  edit: edit_template
-    function: "" # Template for function calls. Uses golang templates with Sprig functions.
+  function: function_template
-    use_tokenizer_template: false # Whether to use a specific tokenizer template. (vLLM)
-    join_chat_messages_by_character: null # Character to join chat messages, if applicable. Defaults to newline.
 
-# Function-related settings to control behavior of specific function calls.
 function:
-    disable_no_action: false # Whether to disable the no-action behavior.
+   disable_no_action: true
-    grammar:
+   no_action_function_name: "reply"
-        parallel_calls: false # Allow to return parallel tools
+   no_action_description_name: "Reply to the AI assistant"
-        disable_parallel_new_lines: false # Disable parallel processing for new lines in grammar checks.
-        mixed_mode: false # Allow mixed-mode grammar enforcing
-        no_mixed_free_string: false # Disallow free strings in mixed mode.
-        disable: false # Completely disable grammar enforcing functionality.
-        prefix: "" # Prefix to add before grammars rules.
-        expect_strings_after_json: false # Expect string after JSON data.
-    no_action_function_name: "" # Function name to call when no action is determined.
-    no_action_description_name: "" # Description name for no-action functions.
-    response_regex: [] # Regular expressions to match response from
-    json_regex_match: [] # Regular expressions to match JSON data when in tool mode
-    replace_function_results: [] # Placeholder to replace function call results with arbitrary strings or patterns.
-    replace_llm_results: [] # Replace language model results with arbitrary strings or patterns.
-    capture_llm_results: [] # Capture language model results as text result, among JSON, in function calls. For instance, if a model returns a block for "thinking" and a block for "response", this will allow you to capture the thinking block.
-    return_name_in_function_response: false # Some models might prefer to use "name" rather then "function" when returning JSON data. This will allow to use "name" as a key in the JSON response.
 
-# Feature gating flags to enable experimental or optional features.
+system_prompt:
-feature_flags: {}
+rms_norm_eps:
-
+# Set it to 8 for llama2 70b
-# System prompt to use by default.
+ngqa: 1
-system_prompt: ""
+## LLAMA specific options
-
+# Enable F16 if backend supports it
-# Configuration for splitting tensors across GPUs.
+f16: true
+# Enable debugging
+debug: true
+# Enable embeddings
+embeddings: true
+# Mirostat configuration (llama.cpp only)
+mirostat_eta: 0.8
+mirostat_tau: 0.9
+mirostat: 1
+# GPU Layers (only used when built with cublas)
+gpu_layers: 22
+# Enable memory lock
+mmlock: true
+# GPU setting to split the tensor in multiple parts and define a main GPU
+# see llama.cpp for usage
 tensor_split: ""
-
-# Identifier for the main GPU used in multi-GPU setups.
 main_gpu: ""
-
+# Define a prompt cache path (relative to the models)
-# Small value added to the denominator in RMS normalization to prevent division by zero.
+prompt_cache_path: "prompt-cache"
-rms_norm_eps: 0
+# Cache all the prompts
-
+prompt_cache_all: true
-# Natural question generation model parameter.
+# Read only
-ngqa: 0
-
-# Path where prompt cache is stored.
-prompt_cache_path: ""
-
-# Whether to cache all prompts.
-prompt_cache_all: false
-
-# Whether the prompt cache is read-only.
 prompt_cache_ro: false
+# Enable mmap
+mmap: true
+# Enable low vram mode (GPU only)
+low_vram: true
+# Set NUMA mode (CPU only)
+numa: true
+# Lora settings
+lora_adapter: "/path/to/lora/adapter"
+lora_base: "/path/to/lora/base"
+# Disable mulmatq (CUDA)
+no_mulmatq: true
 
-# Mirostat sampling settings.
+# Diffusers/transformers
-mirostat_eta: null
+cuda: true
-mirostat_tau: null
-mirostat: null
-
-# GPU-specific layers configuration.
-gpu_layers: null
-
-# Memory mapping for efficient I/O operations.
-mmap: null
-
-# Memory locking to ensure data remains in RAM.
-mmlock: null
-
-# Mode to use minimal VRAM for GPU operations.
-low_vram: null
-
-# Words or phrases that halts processing.
-stopwords: []
-
-# Strings to cut from responses to maintain context or relevance.
-cutstrings: []
-
-# Strings to trim from responses for cleaner outputs.
-trimspace: []
-trimsuffix: []
-
-# Default context size for the model's understanding of the conversation or text.
-context_size: null
-
-# Non-uniform memory access settings, useful for systems with multiple CPUs.
-numa: false
-
-# Configuration for LoRA
-lora_adapter: ""
-lora_base: ""
-lora_scale: 0
-
-# Disable matrix multiplication queuing in GPU operations.
-no_mulmatq: false
-
-# Model for generating draft responses.
-draft_model: ""
-n_draft: 0
-
-# Quantization settings for the model, impacting memory and processing speed.
-quantization: ""
-
-# Utilization percentage of GPU memory to allocate for the model. (vLLM)
-gpu_memory_utilization: 0
-
-# Whether to trust and execute remote code.
-trust_remote_code: false
-
-# Force eager execution of TensorFlow operations if applicable. (vLLM)
-enforce_eager: false
-
-# Space allocated for swapping data in and out of memory. (vLLM)
-swap_space: 0
-
-# Maximum model length, possibly referring to the number of tokens or parameters. (vLLM)
-max_model_len: 0
-
-# Size of the tensor parallelism in distributed computing environments. (vLLM)
-tensor_parallel_size: 0
-
-# vision model to use for multimodal
-mmproj: ""
-
-# Disables offloading of key/value pairs in transformer models to save memory.
-no_kv_offloading: false
-
-# Scaling factor for the rope penalty.
-rope_scaling: ""
-
-# Type of configuration, often related to the type of task or model architecture.
-type: ""
-
-# YARN settings
-yarn_ext_factor: 0
-yarn_attn_factor: 0
-yarn_beta_fast: 0
-yarn_beta_slow: 0
-
-# AutoGPT-Q settings, for configurations specific to GPT models.
-autogptq:
-    model_base_name: "" # Base name of the model.
-    device: "" # Device to run the model on.
-    triton: false # Whether to use Triton Inference Server.
-    use_fast_tokenizer: false # Whether to use a fast tokenizer for quicker processing.
-
-# configuration for diffusers model
-diffusers:
-    cuda: false # Whether to use CUDA
-    pipeline_type: "" # Type of pipeline to use.
-    scheduler_type: "" # Type of scheduler for controlling operations.
-    enable_parameters: "" # Parameters to enable in the diffuser.
-    cfg_scale: 0 # Scale for CFG in the diffuser setup.
-    img2img: false # Whether image-to-image transformation is supported.
-    clip_skip: 0 # Number of steps to skip in CLIP operations.
-    clip_model: "" # Model to use for CLIP operations.
-    clip_subfolder: "" # Subfolder for storing CLIP-related data.
-    control_net: "" # Control net to use
-
-# Step count, usually for image processing models
-step: 0
-
-# Configuration for gRPC communication.
-grpc:
-    attempts: 0 # Number of retry attempts for gRPC calls.
-    attempts_sleep_time: 0 # Sleep time between retries.
-
-# Text-to-Speech (TTS) configuration.
-tts:
-    voice: "" # Voice setting for TTS.
-    vall-e:
-        audio_path: "" # Path to audio files for Vall-E.
-
-# Whether to use CUDA for GPU-based operations.
-cuda: false
-
-# List of files to download as part of the setup or operations.
-download_files: []
 ```
 
 ### Prompt templates