DRAFT: Big Refactor [prep for mqtt]

.github/workflows/image_build.yml

@@ -108,7 +108,6 @@ jobs:
           flavor: |
             latest=${{ inputs.tag-latest }}
             suffix=${{ inputs.tag-suffix }}
-
       - name: Set up QEMU
         uses: docker/setup-qemu-action@master
         with:
@@ -125,7 +124,11 @@ jobs:
           registry: quay.io
           username: ${{ secrets.dockerUsername }}
           password: ${{ secrets.dockerPassword }}
-
+        env: 
+          VERSION: "dev"
+      - name: Capture $VERSION from git tag
+        run: |
+          echo "VERSION=$(git describe --always --tags || echo 'dev')" >> "$GITHUB_ENV"
       - name: Build and push
         uses: docker/build-push-action@v5
         with:
@@ -136,6 +139,8 @@ jobs:
             CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
             FFMPEG=${{ inputs.ffmpeg }}
             IMAGE_TYPE=${{ inputs.image-type }}
+            COMMIT_HASH=${{ github.sha }}
+            VERSION=${{ env.VERSION }}
           context: .
           file: ./Dockerfile
           platforms: ${{ inputs.platforms }}

.github/workflows/test.yml

@@ -96,7 +96,7 @@ jobs:
           GO_TAGS="stablediffusion tts" make test
 
   tests-apple:
-    runs-on: macOS-latest
+    runs-on: macOS-13
     strategy:
       matrix:
         go-version: ['1.21.x']
@@ -112,11 +112,14 @@ jobs:
       # You can test your matrix by printing the current Go version
       - name: Display Go version
         run: go version
+      - name: Display OSX version info
+        run: system_profiler SPSoftwareDataType SPHardwareDataType
       - name: Dependencies
         run: |
           brew install protobuf grpc
+      - name: Build
+        run: |
+          CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make -j12 build
       - name: Test
         run: |
-          export C_INCLUDE_PATH=/usr/local/include
-          export CPLUS_INCLUDE_PATH=/usr/local/include
-          CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make test
+          CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make -j12 test

.gitignore

@@ -19,8 +19,8 @@ LocalAI
 local-ai
 # prevent above rules from omitting the helm chart
 !charts/*
-# prevent above rules from omitting the api/localai folder
-!api/localai
+# prevent above rules from omitting the core/**/localai folder
+!core/**/localai
 
 # Ignore models
 models/*

Dockerfile

@@ -79,6 +79,8 @@ FROM requirements-${IMAGE_TYPE} as builder
 ARG GO_TAGS="stablediffusion tts"
 ARG GRPC_BACKENDS
 ARG BUILD_GRPC=true
+ARG VERSION
+ARG COMMIT_HASH
 ENV GRPC_BACKENDS=${GRPC_BACKENDS}
 ENV GO_TAGS=${GO_TAGS}
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
@@ -88,7 +90,7 @@ ENV NVIDIA_VISIBLE_DEVICES=all
 WORKDIR /build
 
 COPY . .
-COPY .git .
+# COPY .git .
 RUN make prepare
 
 # stablediffusion does not tolerate a newer version of abseil, build it first

Makefile

@@ -50,10 +50,11 @@ TEST_DIR=/tmp/test
 RANDOM := $(shell bash -c 'echo $$RANDOM')
 
 VERSION?=$(shell git describe --always --tags || echo "dev" )
+COMMIT_HASH?=$(shell git rev-parse HEAD)
 # go tool nm ./local-ai | grep Commit
 LD_FLAGS?=
 override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Version=$(VERSION)"
-override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Commit=$(shell git rev-parse HEAD)"
+override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Commit=$(COMMIT_HASH)"
 
 OPTIONAL_TARGETS?=
 
@@ -73,7 +74,11 @@ UNAME_S := $(shell uname -s)
 endif
 
 ifeq ($(OS),Darwin)
+	export BUILD_GRPC_FOR_BACKEND_LLAMA=true
+	export C_INCLUDE_PATH +=/opt/homebrew/include:/usr/local/include
+    export CPLUS_INCLUDE_PATH +=/opt/homebrew/include:/usr/local/include
 	CGO_LDFLAGS += -lcblas -framework Accelerate
+
 	ifeq ($(OSX_SIGNING_IDENTITY),)
 		OSX_SIGNING_IDENTITY := $(shell security find-identity -v -p codesigning | grep '"' | head -n 1 | sed -E 's/.*"(.*)"/\1/')
 	endif
@@ -85,6 +90,7 @@ ifeq ($(OS),Darwin)
 	else ifneq ($(BUILD_TYPE),metal)
 		CMAKE_ARGS+=-DLLAMA_METAL=OFF
 	endif
+
 endif
 
 ifeq ($(BUILD_TYPE),openblas)
@@ -467,19 +473,21 @@ ADDED_CMAKE_ARGS=-Dabsl_DIR=${INSTALLED_LIB_CMAKE}/absl \
 
 backend/cpp/llama/grpc-server:
 ifdef BUILD_GRPC_FOR_BACKEND_LLAMA
+	@echo "=== Building gRPC for llama backend... ==="
 	backend/cpp/grpc/script/build_grpc.sh ${INSTALLED_PACKAGES}
-	export _PROTOBUF_PROTOC=${INSTALLED_PACKAGES}/bin/proto && \
-	export _GRPC_CPP_PLUGIN_EXECUTABLE=${INSTALLED_PACKAGES}/bin/grpc_cpp_plugin && \
-	export PATH=${PATH}:${INSTALLED_PACKAGES}/bin && \
-	CMAKE_ARGS="${CMAKE_ARGS} ${ADDED_CMAKE_ARGS}" LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
+	@echo "=== gRPC Built! making backend/cpp/llama/grpc-server! ==="
+	PATH=${INSTALLED_PACKAGES}/bin:${PATH} \
+	CMAKE_ARGS="${CMAKE_ARGS} ${ADDED_CMAKE_ARGS} -D_PROTOBUF_PROTOC='${INSTALLED_PACKAGES}/bin/protoc' -D_GRPC_CPP_PLUGIN_EXECUTABLE='${INSTALLED_PACKAGES}/bin/grpc_cpp_plugin'" LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
 else
-	echo "BUILD_GRPC_FOR_BACKEND_LLAMA is not defined."
-	LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server			
+	@echo "BUILD_GRPC_FOR_BACKEND_LLAMA is not defined, making backend/cpp/llama grpc-server"
+	LLAMA_VERSION=$(CPPLLAMA_VERSION) $(MAKE) -C backend/cpp/llama grpc-server
 endif
+
 ## BACKEND CPP LLAMA END
-		
+
 ##
 backend-assets/grpc/llama-cpp: backend-assets/grpc backend/cpp/llama/grpc-server
+	@echo "=== backend-assets/grpc/llama-cpp ==="
 	cp -rfv backend/cpp/llama/grpc-server backend-assets/grpc/llama-cpp
 # TODO: every binary should have its own folder instead, so can have different metal implementations
 ifeq ($(BUILD_TYPE),metal)