refactor: move backends into the backends directory

Signed-off-by: Ettore Di Giacinto <[email protected]>

Author: mudler

.github/workflows/test.yml

@@ -78,7 +78,7 @@ jobs:
           sudo apt-get install -y libopencv-dev && sudo ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
           
           sudo rm -rfv /usr/bin/conda || true
-          PATH=$PATH:/opt/conda/bin make -C extra/grpc/huggingface
+          PATH=$PATH:/opt/conda/bin make -C backend/python/huggingface
 
           # Pre-build piper before we start tests in order to have shared libraries in place
           make go-piper && \

Dockerfile

@@ -12,7 +12,7 @@ ARG TARGETARCH
 ARG TARGETVARIANT
 
 ENV BUILD_TYPE=${BUILD_TYPE}
-ENV EXTERNAL_GRPC_BACKENDS="huggingface-embeddings:/build/extra/grpc/huggingface/run.sh,autogptq:/build/extra/grpc/autogptq/run.sh,bark:/build/extra/grpc/bark/run.sh,diffusers:/build/extra/grpc/diffusers/run.sh,exllama:/build/extra/grpc/exllama/run.sh,vall-e-x:/build/extra/grpc/vall-e-x/run.sh,vllm:/build/extra/grpc/vllm/run.sh"
+ENV EXTERNAL_GRPC_BACKENDS="huggingface-embeddings:/build/backend/python/huggingface/run.sh,autogptq:/build/backend/python/autogptq/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,exllama:/build/backend/python/exllama/run.sh,vall-e-x:/build/backend/python/vall-e-x/run.sh,vllm:/build/backend/python/vllm/run.sh"
 ENV GALLERIES='[{"name":"model-gallery", "url":"github:go-skynet/model-gallery/index.yaml"}, {"url": "github:go-skynet/model-gallery/huggingface.yaml","name":"huggingface"}]'
 ARG GO_TAGS="stablediffusion tts"
 
@@ -64,20 +64,10 @@ RUN curl https://repo.anaconda.com/pkgs/misc/gpgkeys/anaconda.asc | gpg --dearmo
     apt-get update && \
     apt-get install -y conda
 
-COPY extra/requirements.txt /build/extra/requirements.txt
 ENV PATH="/root/.cargo/bin:${PATH}"
 RUN pip install --upgrade pip
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
-#RUN if [ "${TARGETARCH}" = "amd64" ]; then \
-#        pip install git+https://github.com/suno-ai/bark.git diffusers invisible_watermark transformers accelerate safetensors;\
-#    fi
-#RUN if [ "${BUILD_TYPE}" = "cublas" ] && [ "${TARGETARCH}" = "amd64" ]; then \
-#        pip install torch vllm && pip install auto-gptq https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu${CUDA_MAJOR_VERSION}${CUDA_MINOR_VERSION}-cp39-cp39-linux_x86_64.whl;\
- #   fi
-#RUN pip install -r /build/extra/requirements.txt && rm -rf /build/extra/requirements.txt
 
-# Vall-e-X
-RUN git clone https://github.com/Plachtaa/VALL-E-X.git /usr/lib/vall-e-x && cd /usr/lib/vall-e-x && pip install -r requirements.txt
 
 # \
 #    ; fi
@@ -162,25 +152,25 @@ COPY --from=builder /build/backend-assets/grpc/stablediffusion ./backend-assets/
 
 ## Duplicated from Makefile to avoid having a big layer that's hard to push
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/autogptq \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/autogptq \
     ; fi
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/bark \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/bark \
     ; fi
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/diffusers \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/diffusers \
     ; fi
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/vllm \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/vllm \
     ; fi
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/huggingface \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/huggingface \
     ; fi
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/vall-e-x \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/vall-e-x \
     ; fi
 RUN if [ "${IMAGE_TYPE}" = "extras" ]; then \
-	PATH=$PATH:/opt/conda/bin make -C extra/grpc/exllama \
+	PATH=$PATH:/opt/conda/bin make -C backend/python/exllama \
     ; fi
 
 # Copy VALLE-X as it's not a real "lib"
@@ -190,7 +180,7 @@ RUN if [ -d /usr/lib/vall-e-x ]; then \
 
 # we also copy exllama libs over to resolve exllama import error
 RUN if [ -d /usr/local/lib/python3.9/dist-packages/exllama ]; then \
-        cp -rfv /usr/local/lib/python3.9/dist-packages/exllama extra/grpc/exllama/;\
+        cp -rfv /usr/local/lib/python3.9/dist-packages/exllama backend/python/exllama/;\
     fi
 
 # Define the health check command

Makefile

@@ -306,7 +306,7 @@ test: prepare test-models/testmodel grpcs
 	@echo 'Running tests'
 	export GO_TAGS="tts stablediffusion"
 	$(MAKE) prepare-test
-	HUGGINGFACE_GRPC=$(abspath ./)/extra/grpc/huggingface/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
+	HUGGINGFACE_GRPC=$(abspath ./)/backend/python/huggingface/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!gpt4all && !llama && !llama-gguf"  --flake-attempts 5 --fail-fast -v -r ./api ./pkg
 	$(MAKE) test-gpt4all
 	$(MAKE) test-llama
@@ -374,27 +374,27 @@ protogen: protogen-go protogen-python
 
 protogen-go:
 	protoc --go_out=. --go_opt=paths=source_relative --go-grpc_out=. --go-grpc_opt=paths=source_relative \
-    pkg/grpc/proto/backend.proto
+    backend/backend.proto
 
 protogen-python:
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/huggingface/ --grpc_python_out=extra/grpc/huggingface/ pkg/grpc/proto/backend.proto
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/autogptq/ --grpc_python_out=extra/grpc/autogptq/ pkg/grpc/proto/backend.proto
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/exllama/ --grpc_python_out=extra/grpc/exllama/ pkg/grpc/proto/backend.proto
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/bark/ --grpc_python_out=extra/grpc/bark/ pkg/grpc/proto/backend.proto
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/diffusers/ --grpc_python_out=extra/grpc/diffusers/ pkg/grpc/proto/backend.proto
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/vall-e-x/ --grpc_python_out=extra/grpc/vall-e-x/ pkg/grpc/proto/backend.proto
-	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=extra/grpc/vllm/ --grpc_python_out=extra/grpc/vllm/ pkg/grpc/proto/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/huggingface/ --grpc_python_out=backend/python/huggingface/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/autogptq/ --grpc_python_out=backend/python/autogptq/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/exllama/ --grpc_python_out=backend/python/exllama/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/bark/ --grpc_python_out=backend/python/bark/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/diffusers/ --grpc_python_out=backend/python/diffusers/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/vall-e-x/ --grpc_python_out=backend/python/vall-e-x/ backend/backend.proto
+	python3 -m grpc_tools.protoc -Ipkg/grpc/proto/ --python_out=backend/python/vllm/ --grpc_python_out=backend/python/vllm/ backend/backend.proto
 
 ## GRPC
 # Note: it is duplicated in the Dockerfile
 prepare-extra-conda-environments:
-	$(MAKE) -C extra/grpc/autogptq
-	$(MAKE) -C extra/grpc/bark
-	$(MAKE) -C extra/grpc/diffusers
-	$(MAKE) -C extra/grpc/vllm
-	$(MAKE) -C extra/grpc/huggingface
-	$(MAKE) -C extra/grpc/vall-e-x
-	$(MAKE) -C extra/grpc/exllama
+	$(MAKE) -C backend/python/autogptq
+	$(MAKE) -C backend/python/bark
+	$(MAKE) -C backend/python/diffusers
+	$(MAKE) -C backend/python/vllm
+	$(MAKE) -C backend/python/huggingface
+	$(MAKE) -C backend/python/vall-e-x
+	$(MAKE) -C backend/python/exllama
 
 
 backend-assets/grpc:

pkg/grpc/proto/backend.proto backend/backend.proto

@@ -36,7 +36,7 @@ include_directories(${Protobuf_INCLUDE_DIRS})
 message(STATUS "Using protobuf version ${Protobuf_VERSION} | Protobuf_INCLUDE_DIRS: ${Protobuf_INCLUDE_DIRS} | CMAKE_CURRENT_BINARY_DIR: ${CMAKE_CURRENT_BINARY_DIR}")
 
 # Proto file
-get_filename_component(hw_proto "../../../../../../pkg/grpc/proto/backend.proto" ABSOLUTE)
+get_filename_component(hw_proto "../../../../../../backend/backend.proto" ABSOLUTE)
 get_filename_component(hw_proto_path "${hw_proto}" PATH)
 
 # Generated sources

backend/cpp/llama/CMakeLists.txt

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

pkg/backend/image/stablediffusion.go backend/go/image/stablediffusion.go

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

pkg/backend/llm/bert/bert.go backend/go/llm/bert/bert.go

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

pkg/backend/llm/gpt4all/gpt4all.go backend/go/llm/gpt4all/gpt4all.go

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

pkg/backend/llm/langchain/langchain.go backend/go/llm/langchain/langchain.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	gpt4all "github.com/go-skynet/LocalAI/pkg/backend/llm/gpt4all"
+	gpt4all "github.com/go-skynet/LocalAI/backend/go/llm/gpt4all"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

pkg/backend/llm/llama-stable/llama.go backend/go/llm/llama-stable/llama.go

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

pkg/backend/llm/llama/llama.go backend/go/llm/llama/llama.go

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

pkg/backend/llm/rwkv/rwkv.go backend/go/llm/rwkv/rwkv.go

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

pkg/backend/llm/transformers/dolly.go backend/go/llm/transformers/dolly.go

@@ -3,7 +3,7 @@ package main
 import (
 	"flag"
 
-	llama "github.com/go-skynet/LocalAI/pkg/backend/llm/llama-stable"
+	llama "github.com/go-skynet/LocalAI/backend/go/llm/llama-stable"
 
 	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )

pkg/backend/llm/transformers/falcon.go backend/go/llm/transformers/falcon.go

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

pkg/backend/llm/transformers/gpt2.go backend/go/llm/transformers/gpt2.go

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

pkg/backend/llm/transformers/gptj.go backend/go/llm/transformers/gptj.go

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

pkg/backend/llm/transformers/gptneox.go backend/go/llm/transformers/gptneox.go

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

pkg/backend/llm/transformers/mpt.go backend/go/llm/transformers/mpt.go

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

pkg/backend/llm/transformers/predict.go backend/go/llm/transformers/predict.go

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

pkg/backend/llm/transformers/replit.go backend/go/llm/transformers/replit.go

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

pkg/backend/llm/transformers/starcoder.go backend/go/llm/transformers/starcoder.go

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