Merge branch 'main' into helm-ci

Author: ZePan110

.github/workflows/_run-helm-chart.yml

@@ -155,7 +155,7 @@ jobs:
             exit 0
           fi
 
-          if ! helm install --create-namespace --namespace $NAMESPACE $RELEASE_NAME oci://ghcr.io/opea-project/charts/${CHART_NAME} --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} -f comps/${{ inputs.service }}/deployment/kubernetes/${value_file} --version 0-latest ; then
+          if ! helm install --create-namespace --namespace $NAMESPACE $RELEASE_NAME oci://ghcr.io/opea-project/charts/${CHART_NAME} --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} --set global.modelUseHostPath=/home/sdp/.cache/huggingface/hub -f comps/${{ inputs.service }}/deployment/kubernetes/${value_file} --version 0-latest --wait; then
             echo "Failed to install chart ${{ inputs.service }}"
             echo "skip_validate=true" >> $GITHUB_ENV
             .github/workflows/scripts/k8s-utils.sh dump_pods_status $NAMESPACE

.github/workflows/docker/compose/llms-compose.yaml

@@ -11,10 +11,6 @@ services:
     build:
       dockerfile: comps/llms/src/text-generation/Dockerfile.intel_hpu
     image: ${REGISTRY:-opea}/llm-textgen-gaudi:${TAG:-latest}
-  llm-ollama:
-    build:
-      dockerfile: comps/llms/text-generation/ollama/langchain/Dockerfile
-    image: ${REGISTRY:-opea}/llm-ollama:${TAG:-latest}
   llm-docsum:
     build:
       dockerfile: comps/llms/src/doc-summarization/Dockerfile

.github/workflows/pr-link-path-scan.yaml

@@ -139,7 +139,7 @@ jobs:
                   fi
                 fi
               else
-                echo "$check_path does not exist"
+                echo "Invalid reference path from $refer_path, reference path: $(echo $png_line | cut -d ']' -f2)"
                 fail="TRUE"
               fi
             done

.github/workflows/pr-microservice-test.yml

@@ -33,14 +33,24 @@ jobs:
       - name: Clean Up Working Directory
         run: |
           sudo rm -rf ${{github.workspace}}/*
-          docker system prune -f
+          cid=$(docker ps -aq --filter "name=test-comps-*")
+          if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
           docker rmi $(docker images --filter reference="*/*:comps" -q) || true
+          docker system prune -f
+          docker ps
 
       - name: Checkout out Repo
         uses: actions/checkout@v4
         with:
           ref: "refs/pull/${{ github.event.number }}/merge"
 
+      - name: Get AWS Credentials
+        uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502
+        if: ${{ contains(matrix.service, 'bedrock') }}
+        with:
+          role-to-assume: ${{ secrets.AWS_IAM_ROLE_ARN }}
+          aws-region: us-east-1
+
       - name: Run microservice test
         env:
           HF_TOKEN: ${{ secrets.HF_TOKEN }}
@@ -56,7 +66,6 @@ jobs:
           timeout 60m bash $(find . -type f -name test_${service}.sh)
 
       - name: Clean up container
-        if: cancelled() || failure()
         run: |
           cid=$(docker ps -aq --filter "name=test-comps-*")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi

comps/__init__.py

@@ -3,6 +3,8 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+import os
+
 # Document
 from comps.cores.proto.docarray import (
     Audio2TextDoc,
@@ -49,7 +51,8 @@
 from comps.cores.mega.micro_service import MicroService, register_microservice, opea_microservices
 
 # Telemetry
-from comps.cores.telemetry.opea_telemetry import opea_telemetry
+if os.getenv("ENABLE_OPEA_TELEMETRY", "false").lower() == "true":
+    from comps.cores.telemetry.opea_telemetry import opea_telemetry
 
 # Common
 from comps.cores.common.component import OpeaComponent, OpeaComponentRegistry, OpeaComponentLoader

comps/asr/src/README.md

@@ -74,14 +74,14 @@ Alternatively, you can also start the ASR microservice with Docker.
 
 ```bash
 cd ../..
-docker build -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/src/integrations/dependency/Dockerfile .
+docker build -t opea/whisper:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/src/integrations/dependency/whisper/Dockerfile .
 ```
 
 - Gaudi2 HPU
 
 ```bash
 cd ../..
-docker build -t opea/whisper-gaudi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/src/integrations/dependency/Dockerfile.intel_hpu .
+docker build -t opea/whisper-gaudi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/asr/src/integrations/dependency/whisper/Dockerfile.intel_hpu .
 ```
 
 #### 2.1.2 ASR Service Image

comps/cores/proto/docarray.py

@@ -278,7 +278,7 @@ class GraphDoc(BaseDoc):
 
 
 class LVMDoc(BaseDoc):
-    image: str
+    image: Union[str, List[str]]
     prompt: str
     max_new_tokens: conint(ge=0, le=1024) = 512
     top_k: int = 10

comps/dataprep/multimodal/redis/langchain/README.md

@@ -5,6 +5,7 @@ This `dataprep` microservice accepts the following from the user and ingests the
 - Videos (mp4 files) and their transcripts (optional)
 - Images (gif, jpg, jpeg, and png files) and their captions (optional)
 - Audio (wav files)
+- PDFs (with text and images)
 
 ## 🚀1. Start Microservice with Python（Option 1）
 
@@ -111,18 +112,19 @@ docker container logs -f dataprep-multimodal-redis
 
 ## 🚀4. Consume Microservice
 
-Once this dataprep microservice is started, user can use the below commands to invoke the microservice to convert images and videos and their transcripts (optional) to embeddings and save to the Redis vector store.
+Once this dataprep microservice is started, user can use the below commands to invoke the microservice to convert images, videos, text, and PDF files to embeddings and save to the Redis vector store.
 
 This microservice provides 3 different ways for users to ingest files into Redis vector store corresponding to the 3 use cases.
 
 ### 4.1 Consume _ingest_with_text_ API
 
-**Use case:** This API is used when videos are accompanied by transcript files (`.vtt` format) or images are accompanied by text caption files (`.txt` format).
+**Use case:** This API is used for videos accompanied by transcript files (`.vtt` format), images accompanied by text caption files (`.txt` format), and PDF files containing a mix of text and images.
 
 **Important notes:**
 
 - Make sure the file paths after `files=@` are correct.
 - Every transcript or caption file's name must be identical to its corresponding video or image file's name (except their extension - .vtt goes with .mp4 and .txt goes with .jpg, .jpeg, .png, or .gif). For example, `video1.mp4` and `video1.vtt`. Otherwise, if `video1.vtt` is not included correctly in the API call, the microservice will return an error `No captions file video1.vtt found for video1.mp4`.
+- It is assumed that PDFs will contain at least one image. Each image in the file will be embedded along with the text that appears on the same page as the image.
 
 #### Single video-transcript pair upload
 
@@ -157,6 +159,7 @@ curl -X POST \
     -F "files=@./image1.txt" \
     -F "files=@./image2.jpg" \
     -F "files=@./image2.txt" \
+    -F "files=@./example.pdf" \
     http://localhost:6007/v1/ingest_with_text
 ```