Merge branch 'main' into embeddings-comp

opea-project · Sep 16, 2024 · 9ab7265 · 9ab7265
2 parents 5638034 + 29fe569
commit 9ab7265
Show file tree

Hide file tree

Showing 87 changed files with 1,572 additions and 436 deletions.
diff --git a/.github/workflows/_comps-workflow.yml b/.github/workflows/_comps-workflow.yml
@@ -6,9 +6,6 @@ permissions: read-all
 on:
   workflow_call:
     inputs:
-      node:
-        required: true
-        type: string
       service:
         required: true
         type: string
@@ -36,7 +33,7 @@ jobs:
   # Image Build
   ####################################################################################################
   build-images:
-    runs-on: "docker-build-${{ inputs.node }}"
+    runs-on: "docker-build-gaudi"
     continue-on-error: true
     outputs:
       file_exists: ${{ steps.get-yaml-path.outputs.file_exists }}
@@ -84,10 +81,9 @@ jobs:
   ####################################################################################################
   test-service-compose:
     needs: [build-images]
-    if: ${{ fromJSON(inputs.test) && needs.build-images.outputs.file_exists == 'true' }}
+    if: ${{ fromJSON(inputs.test) }}
     uses: ./.github/workflows/_run-docker-compose.yml
     with:
       tag: ${{ inputs.tag }}
       service: ${{ inputs.service }}
-      hardware: ${{ inputs.node }}
     secrets: inherit
diff --git a/.github/workflows/_run-docker-compose.yml b/.github/workflows/_run-docker-compose.yml
@@ -20,10 +20,6 @@ on:
         description: Example to test
         required: true
         type: string
-      hardware:
-        description: Hardware to run the test on
-        required: true
-        type: string
 jobs:
   get-test-case:
     runs-on: ubuntu-latest
@@ -55,16 +51,17 @@ jobs:
           set -x
           service_l=$(echo ${{ inputs.service }} | tr '[:upper:]' '[:lower:]')
           cd ${{ github.workspace }}/tests
-          test_cases=$(find . -type f -name "test_${service_l}*.sh" -print | cut -d/ -f2 | jq -R '.' | jq -sc '.')
+          test_cases=$(find . -type f -name "test_${service_l}*.sh" -print | jq -R '.' | jq -sc '.')
           echo "test_cases=$test_cases" >> $GITHUB_OUTPUT
+          # TODO: get hardware for test matrix
 
   run-test:
     needs: [get-test-case]
     strategy:
       matrix:
         test_case: ${{ fromJSON(needs.get-test-case.outputs.test_cases) }}
       fail-fast: false
-    runs-on: ${{ inputs.hardware }}
+    runs-on: gaudi
     continue-on-error: true
     steps:
       - name: Clean up Working Directory
@@ -88,11 +85,10 @@ jobs:
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           PINECONE_KEY: ${{ secrets.PINECONE_KEY }}
           service: ${{ inputs.service }}
-          hardware: ${{ inputs.hardware }}
           test_case: ${{ matrix.test_case }}
         run: |
           cd ${{ github.workspace }}/tests
-          service=$(echo "${test_case}" | sed 's/test_\(.*\)\.sh/\1/')
+          service=$(echo "${test_case}" | cut -d'_' -f2- |cut -d'.' -f1)
           echo "service=${service}" >> $GITHUB_ENV
           if [ -f ${test_case} ]; then timeout 30m bash ${test_case}; else echo "Test script {${test_case}} not found, skip test!"; fi
 

diff --git a/.github/workflows/docker/compose/dataprep-compose-cd.yaml b/.github/workflows/docker/compose/dataprep-compose-cd.yaml
@@ -19,11 +19,15 @@ services:
     build:
       dockerfile: comps/dataprep/pinecone/langchain/Dockerfile
     image: ${REGISTRY:-opea}/dataprep-pinecone:${TAG:-latest}
-  dataprep-redis: #need to rename
+  dataprep-multimodal-redis:
     build:
       dockerfile: comps/dataprep/multimodal/redis/langchain/Dockerfile
-    image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
-  dataprep-vdmsxx: #need to rename
+    image: ${REGISTRY:-opea}/dataprep-multimodal-redis:${TAG:-latest}
+  dataprep-vdms:
     build:
       dockerfile: comps/dataprep/vdms/langchain/Dockerfile
     image: ${REGISTRY:-opea}/dataprep-vdms:${TAG:-latest}
+  dataprep-neo4j:
+    build:
+      dockerfile: comps/dataprep/neo4j/langchain/Dockerfile
+    image: ${REGISTRY:-opea}/dataprep-neo4j:${TAG:-latest}
diff --git a/.github/workflows/docker/compose/dataprep-compose.yaml b/.github/workflows/docker/compose/dataprep-compose.yaml
@@ -17,7 +17,7 @@ services:
     build:
       dockerfile: comps/dataprep/redis/langchain_ray/Dockerfile
     image: ${REGISTRY:-opea}/dataprep-on-ray-redis:${TAG:-latest}
-  dataprep-vdms:
+  dataprep-multimodal-vdms:
     build:
       dockerfile: comps/dataprep/vdms/multimodal_langchain/Dockerfile
-    image: ${REGISTRY:-opea}/dataprep-vdms:${TAG:-latest}
+    image: ${REGISTRY:-opea}/dataprep-multimodal-vdms:${TAG:-latest}
diff --git a/.github/workflows/docker/compose/embeddings-compose-cd.yaml b/.github/workflows/docker/compose/embeddings-compose-cd.yaml
@@ -22,7 +22,7 @@ services:
     build:
       dockerfile: comps/embeddings/multimodal/bridgetower/Dockerfile.intel_hpu
     image: ${REGISTRY:-opea}/bridgetower-embedder-gaudi:${TAG:-latest}
-  embedding-multimodalxx: #need to rename
+  embedding-multimodal:
     build:
       dockerfile: comps/embeddings/multimodal/multimodal_langchain/Dockerfile
     image: ${REGISTRY:-opea}/embedding-multimodal:${TAG:-latest}

diff --git a/.github/workflows/docker/compose/embeddings-compose.yaml b/.github/workflows/docker/compose/embeddings-compose.yaml
@@ -8,7 +8,7 @@ services:
     build:
       dockerfile: comps/embeddings/tei/langchain/Dockerfile
     image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
-  embedding-multimodal:
+  embedding-multimodal-clip:
     build:
       dockerfile: comps/embeddings/multimodal_clip/Dockerfile
-    image: ${REGISTRY:-opea}/embedding-multimodal:${TAG:-latest}
+    image: ${REGISTRY:-opea}/embedding-multimodal-clip:${TAG:-latest}
diff --git a/.github/workflows/docker/compose/llms-compose-cd.yaml b/.github/workflows/docker/compose/llms-compose-cd.yaml
@@ -11,10 +11,10 @@ services:
       context: vllm-openvino
       dockerfile: Dockerfile.openvino
     image: ${REGISTRY:-opea}/vllm-openvino:${TAG:-latest}
-  llm-nativexx: #need to rename
+  llm-eval:
     build:
       dockerfile: comps/llms/utils/lm-eval/Dockerfile
-    image: ${REGISTRY:-opea}/llm-native:${TAG:-latest}
+    image: ${REGISTRY:-opea}/llm-eval:${TAG:-latest}
   llm-vllm-llamaindex:
     build:
       dockerfile: comps/llms/text-generation/vllm/llama_index/Dockerfile

diff --git a/.github/workflows/docker/compose/reranks-compose.yaml b/.github/workflows/docker/compose/reranks-compose.yaml
@@ -8,7 +8,7 @@ services:
     build:
       dockerfile: comps/reranks/tei/Dockerfile
     image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
-  reranking-videoragqna:
+  reranking-videoqna:
     build:
-      dockerfile: comps/reranks/video-rag-qna/Dockerfile
-    image: ${REGISTRY:-opea}/reranking-videoragqna:${TAG:-latest}
+      dockerfile: comps/reranks/videoqna/Dockerfile
+    image: ${REGISTRY:-opea}/reranking-videoqna:${TAG:-latest}
diff --git a/.github/workflows/docker/compose/retrievers-compose-cd.yaml b/.github/workflows/docker/compose/retrievers-compose-cd.yaml
@@ -27,3 +27,7 @@ services:
     build:
       dockerfile: comps/retrievers/multimodal/redis/langchain/Dockerfile
     image: ${REGISTRY:-opea}/multimodal-retriever-redis:${TAG:-latest}
+  retriever-neo4j:
+    build:
+      dockerfile: comps/retrievers/neo4j/langchain/Dockerfile
+    image: ${REGISTRY:-opea}/retriever-neo4j:${TAG:-latest}
diff --git a/.github/workflows/manual-comps-test.yml b/.github/workflows/manual-comps-test.yml
@@ -56,7 +56,6 @@ jobs:
     with:
       service: ${{ matrix.service }}
       tag: ${{ inputs.tag }}
-      node: gaudi
       mode: ${{ inputs.mode }}
       test: ${{ inputs.test }}
     secrets: inherit
diff --git a/comps/__init__.py b/comps/__init__.py
@@ -46,9 +46,9 @@
     AudioQnAGateway,
     RetrievalToolGateway,
     FaqGenGateway,
-    VideoRAGQnAGateway,
+    VideoQnAGateway,
     VisualQnAGateway,
-    MultimodalRAGWithVideosGateway,
+    MultimodalQnAGateway,
 )
 
 # Telemetry

diff --git a/comps/cores/mega/constants.py b/comps/cores/mega/constants.py
@@ -38,12 +38,12 @@ class MegaServiceEndpoint(Enum):
     CHAT_QNA = "/v1/chatqna"
     AUDIO_QNA = "/v1/audioqna"
     VISUAL_QNA = "/v1/visualqna"
-    VIDEO_RAG_QNA = "/v1/videoragqna"
+    VIDEO_RAG_QNA = "/v1/videoqna"
     CODE_GEN = "/v1/codegen"
     CODE_TRANS = "/v1/codetrans"
     DOC_SUMMARY = "/v1/docsum"
     SEARCH_QNA = "/v1/searchqna"
-    MULTIMODAL_RAG_WITH_VIDEOS = "/v1/mmragvideoqna"
+    MULTIMODAL_QNA = "/v1/multimodalqna"
     TRANSLATION = "/v1/translation"
     RETRIEVALTOOL = "/v1/retrievaltool"
     FAQ_GEN = "/v1/faqgen"

diff --git a/comps/cores/mega/gateway.py b/comps/cores/mega/gateway.py
@@ -548,7 +548,7 @@ async def handle_request(self, request: Request):
         return ChatCompletionResponse(model="visualqna", choices=choices, usage=usage)
 
 
-class VideoRAGQnAGateway(Gateway):
+class VideoQnAGateway(Gateway):
     def __init__(self, megaservice, host="0.0.0.0", port=8888):
         super().__init__(
             megaservice,
@@ -594,7 +594,7 @@ async def handle_request(self, request: Request):
                 finish_reason="stop",
             )
         )
-        return ChatCompletionResponse(model="videoragqna", choices=choices, usage=usage)
+        return ChatCompletionResponse(model="videoqna", choices=choices, usage=usage)
 
 
 class RetrievalToolGateway(Gateway):
@@ -634,14 +634,14 @@ def parser_input(data, TypeClass, key):
         return response
 
 
-class MultimodalRAGWithVideosGateway(Gateway):
+class MultimodalQnAGateway(Gateway):
     def __init__(self, multimodal_rag_megaservice, lvm_megaservice, host="0.0.0.0", port=9999):
         self.lvm_megaservice = lvm_megaservice
         super().__init__(
             multimodal_rag_megaservice,
             host,
             port,
-            str(MegaServiceEndpoint.MULTIMODAL_RAG_WITH_VIDEOS),
+            str(MegaServiceEndpoint.MULTIMODAL_QNA),
             ChatCompletionRequest,
             ChatCompletionResponse,
         )
@@ -737,7 +737,7 @@ async def handle_request(self, request: Request):
         data = await request.json()
         stream_opt = bool(data.get("stream", False))
         if stream_opt:
-            print("[ MultimodalRAGWithVideosGateway ] stream=True not used, this has not support streaming yet!")
+            print("[ MultimodalQnAGateway ] stream=True not used, this has not support streaming yet!")
             stream_opt = False
         chat_request = ChatCompletionRequest.model_validate(data)
         # Multimodal RAG QnA With Videos has not yet accepts image as input during QnA.
@@ -803,4 +803,4 @@ async def handle_request(self, request: Request):
                 metadata=metadata,
             )
         )
-        return ChatCompletionResponse(model="multimodalragwithvideos", choices=choices, usage=usage)
+        return ChatCompletionResponse(model="multimodalqna", choices=choices, usage=usage)
diff --git a/comps/dataprep/multimodal/redis/langchain/README.md b/comps/dataprep/multimodal/redis/langchain/README.md
@@ -83,13 +83,13 @@ export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
 
 ```bash
 cd ../../../../
-docker build -t opea/dataprep-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/multimodal/redis/langchain/Dockerfile .
+docker build -t opea/dataprep-multimodal-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/multimodal/redis/langchain/Dockerfile .
 ```
 
 ### 2.5 Run Docker with CLI (Option A)
 
 ```bash
-docker run -d --name="dataprep-redis-server" -p 6007:6007 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e REDIS_URL=$REDIS_URL -e INDEX_NAME=$INDEX_NAME -e LVM_ENDPOINT=$LVM_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN opea/dataprep-redis:latest
+docker run -d --name="dataprep-multimodal-redis" -p 6007:6007 --runtime=runc --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e REDIS_URL=$REDIS_URL -e INDEX_NAME=$INDEX_NAME -e LVM_ENDPOINT=$LVM_ENDPOINT -e HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN opea/dataprep-multimodal-redis:latest
 ```
 
 ### 2.6 Run with Docker Compose (Option B - deprecated, will move to genAIExample in future)
@@ -102,7 +102,7 @@ docker compose -f docker-compose-dataprep-redis.yaml up -d
 ## 🚀3. Status Microservice
 
 ```bash
-docker container logs -f dataprep-redis-server
+docker container logs -f dataprep-multimodal-redis
 ```
 
 ## 🚀4. Consume Microservice

diff --git a/comps/dataprep/multimodal/redis/langchain/docker-compose-dataprep-redis.yaml b/comps/dataprep/multimodal/redis/langchain/docker-compose-dataprep-redis.yaml
@@ -9,9 +9,9 @@ services:
     ports:
       - "6379:6379"
       - "8001:8001"
-  dataprep-redis:
-    image: opea/dataprep-redis:latest
-    container_name: dataprep-redis-server
+  dataprep-multimodal-redis:
+    image: opea/dataprep-multimodal-redis:latest
+    container_name: dataprep-multimodal-redis
     ports:
       - "6007:6007"
     ipc: host

diff --git a/comps/dataprep/neo4j/langchain/Dockerfile b/comps/dataprep/neo4j/langchain/Dockerfile
@@ -0,0 +1,38 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM python:3.11-slim
+
+ENV LANG=C.UTF-8
+
+ARG ARCH="cpu"
+
+RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
+    build-essential \
+    default-jre \
+    libgl1-mesa-glx \
+    libjemalloc-dev
+
+RUN useradd -m -s /bin/bash user && \
+    mkdir -p /home/user && \
+    chown -R user /home/user/
+
+USER user
+
+COPY comps /home/user/comps
+
+RUN pip install --no-cache-dir --upgrade pip setuptools && \
+    if [ ${ARCH} = "cpu" ]; then pip install --no-cache-dir torch torchvision --index-url https://download.pytorch.org/whl/cpu; fi && \
+    pip install --no-cache-dir -r /home/user/comps/dataprep/neo4j/langchain/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home/user
+
+USER root
+
+RUN mkdir -p /home/user/comps/dataprep/qdrant/langchain/uploaded_files && chown -R user /home/user/comps/dataprep/neo4j/langchain/uploaded_files
+
+USER user
+
+WORKDIR /home/user/comps/dataprep/neo4j/langchain
+
+ENTRYPOINT ["python", "prepare_doc_neo4j.py"]