Refactor web retrievers links (#1338)

Author: Spycsh

SearchQnA/docker_compose/intel/cpu/xeon/README.md

@@ -15,7 +15,7 @@ docker build --no-cache -t opea/embedding:latest --build-arg https_proxy=$https_
 ### 2. Build Retriever Image
 
 ```bash
-docker build --no-cache -t opea/web-retriever-chroma:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/web_retrievers/chroma/langchain/Dockerfile .
+docker build --no-cache -t opea/web-retriever:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/web_retrievers/src/Dockerfile .
 ```
 
 ### 3. Build Rerank Image
@@ -52,7 +52,7 @@ docker build --no-cache -t opea/opea/searchqna-ui:latest --build-arg https_proxy
 Then run the command `docker images`, you will have following images ready:
 
 1. `opea/embedding:latest`
-2. `opea/web-retriever-chroma:latest`
+2. `opea/web-retriever:latest`
 3. `opea/reranking:latest`
 4. `opea/llm-textgen:latest`
 5. `opea/searchqna:latest`

SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml

@@ -39,8 +39,8 @@ services:
       LOGFLAG: ${LOGFLAG}
     restart: unless-stopped
   web-retriever:
-    image: ${REGISTRY:-opea}/web-retriever-chroma:${TAG:-latest}
-    container_name: web-retriever-chroma-server
+    image: ${REGISTRY:-opea}/web-retriever:${TAG:-latest}
+    container_name: web-retriever-server
     ports:
       - "3003:7077"
     ipc: host

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

@@ -17,7 +17,7 @@ docker build --no-cache -t opea/embedding:latest --build-arg https_proxy=$https_
 ### 2. Build Retriever Image
 
 ```bash
-docker build --no-cache -t opea/web-retriever-chroma:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/web_retrievers/chroma/langchain/Dockerfile .
+docker build --no-cache -t opea/web-retriever:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/web_retrievers/src/Dockerfile .
 ```
 
 ### 3. Build Rerank Image
@@ -52,7 +52,7 @@ docker build --no-cache -t opea/searchqna:latest --build-arg https_proxy=$https_
 Then run the command `docker images`, you will have
 
 1. `opea/embedding:latest`
-2. `opea/web-retriever-chroma:latest`
+2. `opea/web-retriever:latest`
 3. `opea/reranking:latest`
 4. `opea/llm-textgen:latest`
 5. `opea/searchqna:latest`

SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -47,8 +47,8 @@ services:
       LOGFLAG: ${LOGFLAG}
     restart: unless-stopped
   web-retriever:
-    image: ${REGISTRY:-opea}/web-retriever-chroma:${TAG:-latest}
-    container_name: web-retriever-chroma-server
+    image: ${REGISTRY:-opea}/web-retriever:${TAG:-latest}
+    container_name: web-retriever-server
     ports:
       - "3003:7077"
     ipc: host

SearchQnA/docker_image_build/build.yaml

@@ -23,12 +23,12 @@ services:
       dockerfile: comps/embeddings/src/Dockerfile
     extends: searchqna
     image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
-  web-retriever-chroma:
+  web-retriever:
     build:
       context: GenAIComps
-      dockerfile: comps/web_retrievers/chroma/langchain/Dockerfile
+      dockerfile: comps/web_retrievers/src/Dockerfile
     extends: searchqna
-    image: ${REGISTRY:-opea}/web-retriever-chroma:${TAG:-latest}
+    image: ${REGISTRY:-opea}/web-retriever:${TAG:-latest}
   reranking:
     build:
       context: GenAIComps

SearchQnA/tests/test_compose_on_gaudi.sh

@@ -19,7 +19,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever-chroma reranking llm-textgen"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -72,7 +72,7 @@ function validate_megaservice() {
     result=$(curl http://${ip_address}:3008/v1/searchqna -X POST -d '{"messages": "What is the capital of China?", "stream": "False"}' -H 'Content-Type: application/json')
     echo $result
 
-    docker logs web-retriever-chroma-server > ${LOG_PATH}/web-retriever-chroma-server.log
+    docker logs web-retriever-server > ${LOG_PATH}/web-retriever-server.log
     docker logs searchqna-gaudi-backend-server > ${LOG_PATH}/searchqna-gaudi-backend-server.log
     docker logs tei-embedding-gaudi-server > ${LOG_PATH}/tei-embedding-gaudi-server.log
     docker logs embedding-gaudi-server > ${LOG_PATH}/embedding-gaudi-server.log

SearchQnA/tests/test_compose_on_xeon.sh

@@ -19,7 +19,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever-chroma reranking llm-textgen"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -70,7 +70,7 @@ function validate_megaservice() {
     result=$(curl http://${ip_address}:3008/v1/searchqna -X POST -d '{"messages": "What is the capital of China?", "stream": "False"}' -H 'Content-Type: application/json')
     echo $result
 
-    docker logs web-retriever-chroma-server > ${LOG_PATH}/web_retriever.log
+    docker logs web-retriever-server > ${LOG_PATH}/web_retriever.log
     docker logs searchqna-xeon-backend-server > ${LOG_PATH}/searchqna_backend.log
 
     if [[ $result == *"capital"* ]]; then

docker_images_list.md

@@ -96,6 +96,6 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the
 | [opea/vllm](https://hub.docker.com/r/opea/vllm)                                                                     | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.cpu)                                                                      | The docker image powered by vllm-project for deploying and serving vllm Models                                                                                                                                             |
 | [opea/vllm-gaudi]()                                                                                                 | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.hpu)                                                              | The docker image powered by vllm-fork for deploying and serving vllm-gaudi Models                                                                                                                                          |
 | [opea/vllm-openvino](https://hub.docker.com/r/opea/vllm-openvino)                                                   | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.openvino)                                                                 | The docker image powered by vllm-project for deploying and serving vllm Models of the Openvino Framework                                                                                                                   |
-| [opea/web-retriever-chroma](https://hub.docker.com/r/opea/web-retriever-chroma)                                     | [Link](https://github.com/opea-project/GenAIComps/tree/main/comps/web_retrievers/chroma/langchain/Dockerfile)                              | The docker image exposed the OPEA retrieval microservice based on chroma vectordb for GenAI application use                                                                                                                |
+| [opea/web-retriever]()                                                                                              | [Link](https://github.com/opea-project/GenAIComps/tree/main/comps/web_retrievers/src/Dockerfile)                                           | The docker image exposed the OPEA web retrieval microservice based on a search engine and vector DB                                                                                                                        |
 | [opea/whisper](https://hub.docker.com/r/opea/whisper)                                                               | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/integrations/dependency/whisper/Dockerfile)                      | The docker image exposed the OPEA Whisper service for GenAI application use                                                                                                                                                |
 | [opea/whisper-gaudi](https://hub.docker.com/r/opea/whisper-gaudi)                                                   | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/src/integrations/dependency/whisper/Dockerfile.intel_hpu)            | The docker image exposed the OPEA Whisper service on Gaudi2 for GenAI application use                                                                                                                                      |