Merge branch 'main' into ecrag_v1

.github/workflows/check-online-doc-build.yml

@@ -0,0 +1,32 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check Online Document Building
+permissions: {}
+
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        path: GenAIExamples
+
+    - name: Checkout docs
+      uses: actions/checkout@v4
+      with:
+        repository: opea-project/docs
+        path: docs
+
+    - name: Build Online Document
+      shell: bash
+      run: |
+        echo "build online doc"
+        cd docs
+        bash scripts/build.sh

ChatQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -26,7 +26,7 @@ To set up environment variables for deploying ChatQnA services, follow these ste
    export http_proxy="Your_HTTP_Proxy"
    export https_proxy="Your_HTTPs_Proxy"
    # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
-   export no_proxy="Your_No_Proxy",chatqna-gaudi-ui-server,chatqna-gaudi-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service,vllm-ray-service,guardrails
+   export no_proxy="Your_No_Proxy",chatqna-gaudi-ui-server,chatqna-gaudi-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service,guardrails
    ```
 
 3. Set up other environment variables:
@@ -227,7 +227,7 @@ For users in China who are unable to download models directly from Huggingface,
    export http_proxy="Your_HTTP_Proxy"
    export https_proxy="Your_HTTPs_Proxy"
    # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
-   export no_proxy="Your_No_Proxy",chatqna-gaudi-ui-server,chatqna-gaudi-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service,vllm-ray-service,guardrails
+   export no_proxy="Your_No_Proxy",chatqna-gaudi-ui-server,chatqna-gaudi-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service,guardrails
    ```
 
 3. Set up other environment variables:
@@ -257,12 +257,6 @@ If use vllm for llm backend.
 docker compose -f compose_vllm.yaml up -d
 ```
 
-If use vllm-on-ray for llm backend.
-
-```bash
-docker compose -f compose_vllm_ray.yaml up -d
-```
-
 If you want to enable guardrails microservice in the pipeline, please follow the below command instead:
 
 ```bash
@@ -351,13 +345,6 @@ For validation details, please refer to [how-to-validate_service](./how_to_valid
      }'
    ```
 
-   ```bash
-   #vLLM-on-Ray Service
-   curl http://${host_ip}:8006/v1/chat/completions \
-     -H "Content-Type: application/json" \
-     -d '{"model": "${LLM_MODEL_ID}", "messages": [{"role": "user", "content": "What is Deep Learning?"}]}'
-   ```
-
 5. MegaService
 
    ```bash

ChatQnA/docker_image_build/build.yaml

@@ -77,12 +77,6 @@ services:
       dockerfile: comps/llms/text-generation/vllm/langchain/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest}
-  llm-vllm-ray-hpu:
-    build:
-      context: GenAIComps
-      dockerfile: comps/llms/text-generation/vllm/ray/dependency/Dockerfile
-    extends: chatqna
-    image: ${REGISTRY:-opea}/llm-vllm-ray-hpu:${TAG:-latest}
   dataprep-redis:
     build:
       context: GenAIComps