Refactor Vectorstores to E-RAG Style (#1159)

Move DBs with yaml/Dockerfile into third_parties folder and delete vectorstores folder.
Modify related components for change of vectordb folder path.
Remained vectorestores:
- thirdparties
    - elasticsearch
    - milvus
    - opensearch
    - pathway
    - pgvector
    - redis
    - vdms

Fix issue https://github.com/opea-project/GenAIComps/issues/1008.

Signed-off-by: letonghan <letong.han@intel.com>

.github/CODEOWNERS

@@ -26,5 +26,4 @@
 /comps/text2image/ xinyu.ye@intel.com liang1.lv@intel.com
 /comps/text2sql/ yogesh.pandey@intel.com qing.yao@intel.com
 /comps/tts/ sihan.chen@intel.com letong.han@intel.com
-/comps/vectorstores/ xinyu.ye@intel.com letong.han@intel.com
 /comps/web_retrievers/ sihan.chen@intel.com liang1.lv@intel.com

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

@@ -18,6 +18,10 @@ services:
     build:
       dockerfile: comps/third_parties/bridgetower/src/Dockerfile.intel_hpu
     image: ${REGISTRY:-opea}/embedding-multimodal-bridgetower-gaudi:${TAG:-latest}
+  pathway:
+    build:
+      dockerfile: comps/third_parties/pathway/src/Dockerfile
+    image: ${REGISTRY:-opea}/pathway:${TAG:-latest}
   wav2lip:
     build:
       dockerfile: comps/third_parties/wav2lip/src/Dockerfile

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

@@ -1,9 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-# this file should be run in the root of the repo
-services:
-  vectorstore-pathway:
-    build:
-      dockerfile: comps/vectorstores/pathway/Dockerfile
-    image: ${REGISTRY:-opea}/vectorstore-pathway:${TAG:-latest}

.github/workflows/manual-comps-test.yml

@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: "asr"
-        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,intent_detection,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,vectorstores,web_retrievers]"
+        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,intent_detection,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
         required: true
         type: string
       build:

.github/workflows/manual-docker-publish.yml

@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: ""
-        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,intent_detection,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,vectorstores,web_retrievers]"
+        description: "List of services to test [agent,asr,chathistory,dataprep,embeddings,feedback_management,finetuning,guardrails,intent_detection,knowledgegraphs,llms,lvms,nginx,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
         required: false
         type: string
       images:

.github/workflows/manual-docker-scan.yml

@@ -7,7 +7,7 @@ on:
     inputs:
       services:
         default: "asr"
-        description: "List of services to test [agent_langchain,asr,chathistory_mongo,dataprep_milvus...]" #,embeddings,guardrails,llms,lvms,prompt_registry,ragas,rerankings,retrievers,tts,vectorstores,web_retrievers]"
+        description: "List of services to test [agent_langchain,asr,chathistory_mongo,dataprep_milvus...]" #,embeddings,guardrails,llms,lvms,prompt_registry,ragas,rerankings,retrievers,tts,web_retrievers]"
         required: false
         type: string
       images:

comps/dataprep/elasticsearch/langchain/README.md

@@ -17,7 +17,7 @@ export INDEX_NAME=${your_index_name}
 
 ### 1.3 Start Elasticsearch
 
-Please refer to this [readme](../../../vectorstores/elasticsearch/README.md).
+Please refer to this [readme](../../../third_parties/elasticsearch/src/README.md).
 
 ### 1.4 Start Document Preparation Microservice for Elasticsearch with Python Script
 
@@ -31,7 +31,7 @@ python prepare_doc_elastic.py
 
 ### 2.1 Start Elasticsearch
 
-Please refer to this [readme](../../../vectorstores/elasticsearch/README.md).
+Please refer to this [readme](../../../third_parties/elasticsearch/src/README.md).
 
 ### 2.2 Setup Environment Variables
 

comps/dataprep/milvus/langchain/README.md

@@ -13,7 +13,7 @@ apt-get install poppler-utils -y
 
 ### 1.2 Start Milvus Server
 
-Please refer to this [readme](../../../vectorstores/milvus/README.md).
+Please refer to this [readme](../../../third_parties/milvus/src/README.md).
 
 ### 1.3 Setup Environment Variables
 
@@ -56,7 +56,7 @@ python prepare_doc_milvus.py
 
 ### 2.1 Start Milvus Server
 
-Please refer to this [readme](../../../vectorstores/milvus/README.md).
+Please refer to this [readme](../../../third_parties/milvus/src/README.md).
 
 ### 2.2 Build Docker Image
 

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

@@ -23,7 +23,7 @@ pip install -r requirements.txt
 
 ### 1.2 Start Redis Stack Server
 
-Please refer to this [readme](../../../../vectorstores/redis/README.md).
+Please refer to this [readme](../../../../third_parties/redis/src/README.md).
 
 ### 1.3 Setup Environment Variables
 
@@ -58,7 +58,7 @@ python prepare_videodoc_redis.py
 
 ### 2.1 Start Redis Stack Server
 
-Please refer to this [readme](../../../../vectorstores/redis/README.md).
+Please refer to this [readme](../../../../third_parties/redis/src/README.md).
 
 ### 2.2 Start LVM Microservice (Optional)
 

comps/dataprep/opensearch/README.md

@@ -18,7 +18,7 @@ pip install -r requirements.txt
 
 ### 1.2 Start OpenSearch Stack Server
 
-Please refer to this [readme](../../vectorstores/opensearch/README.md).
+Please refer to this [readme](../../third_parties/opensearch/src/README.md).
 
 ### 1.3 Setup Environment Variables
 
@@ -69,7 +69,7 @@ python prepare_doc_opensearch.py
 
 ### 2.1 Start OpenSearch Stack Server
 
-Please refer to this [readme](../../vectorstores/opensearch/README.md).
+Please refer to this [readme](../../third_parties/opensearch/src/README.md).
 
 ### 2.2 Setup Environment Variables
 

comps/dataprep/pgvector/langchain/README.md

@@ -17,7 +17,7 @@ export INDEX_NAME=${your_index_name}
 
 ### 1.3 Start PGVector
 
-Please refer to this [readme](../../../vectorstores/pgvector/README.md).
+Please refer to this [readme](../../../third_parties/pgvector/src/README.md).
 
 ### 1.4 Start Document Preparation Microservice for PGVector with Python Script
 
@@ -31,7 +31,7 @@ python prepare_doc_pgvector.py
 
 ### 2.1 Start PGVector
 
-Please refer to this [readme](../../../vectorstores/pgvector/README.md).
+Please refer to this [readme](../../../third_parties/pgvector/src/README.md).
 
 ### 2.2 Setup Environment Variables
 

comps/dataprep/pinecone/langchain/README.md

@@ -10,7 +10,24 @@ pip install -r requirements.txt
 
 ### Start Pinecone Server
 
-Please refer to this [readme](../../../vectorstores/pinecone/README.md).
+1. Create Pinecone account from the below link
+
+https://app.pinecone.io/
+
+More details from Pinecone quick start guide https://docs.pinecone.io/guides/get-started/quickstart
+
+2. Get API key
+
+API Key is needed to make the API calls. API key can get it from the Project -> Manage -> API keys
+
+3. Create the index in https://app.pinecone.io/
+
+Following details are to be provided
+
+    - Index name
+    - Based on the embedding model selected, following has to be provided
+        a. Dimensions
+        b. Metric
 
 ### Setup Environment Variables
 

comps/dataprep/qdrant/langchain/README.md

@@ -13,7 +13,7 @@ apt-get install poppler-utils -y
 
 ### Start Qdrant Server
 
-Please refer to this [readme](../../../vectorstores/qdrant/README.md).
+docker run -p 6333:6333 -p 6334:6334 -v ./qdrant_storage:/qdrant/storage:z qdrant/qdrant
 
 ### Setup Environment Variables
 

comps/dataprep/redis/README.md

@@ -33,7 +33,7 @@ cd langchain_ray; pip install -r requirements_ray.txt
 
 ### 1.2 Start Redis Stack Server
 
-Please refer to this [readme](../../vectorstores/redis/README.md).
+Please refer to this [readme](../../third_parties/redis/src/README.md).
 
 ### 1.3 Setup Environment Variables
 
@@ -90,7 +90,7 @@ python prepare_doc_redis_on_ray.py
 
 ### 2.1 Start Redis Stack Server
 
-Please refer to this [readme](../../vectorstores/redis/README.md).
+Please refer to this [readme](../../third_parties/redis/src/README.md).
 
 ### 2.2 Setup Environment Variables
 

comps/dataprep/vdms/README.md

@@ -27,7 +27,7 @@ cd langchain_ray; pip install -r requirements_ray.txt
 
 ### 1.2 Start VDMS Server
 
-Refer to this [readme](../../vectorstores/vdms/README.md).
+Refer to this [readme](../../third_parties/vdms/src/README.md).
 
 ### 1.3 Setup Environment Variables
 
@@ -60,7 +60,7 @@ python prepare_doc_redis_on_ray.py
 
 ### 2.1 Start VDMS Server
 
-Refer to this [readme](../../vectorstores/vdms/README.md).
+Refer to this [readme](../../third_parties/vdms/src/README.md).
 
 ### 2.2 Setup Environment Variables
 

comps/third_parties/pathway/src/Dockerfile

@@ -15,12 +15,12 @@ RUN apt-get update && apt-get install -y \
 
 WORKDIR /app
 
-COPY comps/vectorstores/pathway/requirements.txt /app/
+COPY comps/third_parties/pathway/src/requirements.txt /app/
 
 RUN 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 requirements.txt
 
-COPY comps/vectorstores/pathway/vectorstore_pathway.py /app/
+COPY comps/third_parties/pathway/src/vectorstore_pathway.py /app/
 
 
 CMD ["python", "vectorstore_pathway.py"]

comps/third_parties/pathway/src/README.md

@@ -56,7 +56,7 @@ For more information, see the relevant Pathway docs:
 Build the Docker and run the Pathway Vector Store:
 
 ```bash
-docker build --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -t opea/vectorstore-pathway:latest -f comps/vectorstores/src/pathway/Dockerfile .
+docker build --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -t opea/vectorstore-pathway:latest -f comps/third_parties/pathway/src/Dockerfile .
 
 # with locally loaded model, you may add `EMBED_MODEL` env variable to configure the model.
 docker run -e PATHWAY_HOST=${PATHWAY_HOST} -e PATHWAY_PORT=${PATHWAY_PORT} -e http_proxy=$http_proxy -e https_proxy=$https_proxy -v ./data:/app/data -p ${PATHWAY_PORT}:${PATHWAY_PORT} opea/vectorstore-pathway:latest

comps/vectorstores/README.md

@@ -1,39 +0,0 @@
-# Vectorstores Microservice
-
-The Vectorstores Microservice provides convenient way to start various vector database servers.
-
-## Vectorstores Microservice with Redis
-
-For details, please refer to this [readme](redis/README.md)
-
-## Vectorstores Microservice with Qdrant
-
-For details, please refer to this [readme](qdrant/README.md)
-
-## Vectorstores Microservice with PGVector
-
-For details, please refer to this [readme](pgvector/README.md)
-
-## Vectorstores Microservice with Pinecone
-
-For details, please refer to this [readme](pinecone/README.md)
-
-## Vectorstores Microservice with Pathway
-
-For details, please refer to this [readme](pathway/README.md)
-
-## Vectorstores Microservice with Milvus
-
-For details, please refer to this [readme](milvus/README.md)
-
-## Vectorstores Microservice with LanceDB
-
-For details, please refer to this [readme](lancedb/README.md)
-
-## Vectorstores Microservice with Chroma
-
-For details, please refer to this [readme](chroma/README.md)
-
-## Vectorstores Microservice with VDMS
-
-For details, please refer to this [readme](vdms/README.md)

comps/vectorstores/chroma/README.md

@@ -1,38 +0,0 @@
-# Start Chroma server
-
-## Introduction
-
-Chroma is a AI-native open-source vector database focused on developer productivity and happiness. Chroma is licensed under Apache 2.0. Chroma runs in various modes, we can deploy it as a server running your local machine or in the cloud.
-
-## Getting Started
-
-### Start Chroma Server
-
-To start the Chroma server on your local machine, follow these steps:
-
-```bash
-git clone https://github.com/chroma-core/chroma.git
-cd chroma
-docker compose up -d
-```
-
-### Start Log Output
-
-Upon starting the server, you should see log outputs similar to the following:
-
-```
-server-1  | Starting 'uvicorn chromadb.app:app' with args: --workers 1 --host 0.0.0.0 --port 8000 --proxy-headers --log-config chromadb/log_config.yml --timeout-keep-alive 30
-server-1  | INFO:     [02-08-2024 07:03:19] Set chroma_server_nofile to 65536
-server-1  | INFO:     [02-08-2024 07:03:19] Anonymized telemetry enabled. See                     https://docs.trychroma.com/telemetry for more information.
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component System
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component OpenTelemetryClient
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component SqliteDB
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component QuotaEnforcer
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component Posthog
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component LocalSegmentManager
-server-1  | DEBUG:    [02-08-2024 07:03:19] Starting component SegmentAPI
-server-1  | INFO:     [02-08-2024 07:03:19] Started server process [1]
-server-1  | INFO:     [02-08-2024 07:03:19] Waiting for application startup.
-server-1  | INFO:     [02-08-2024 07:03:19] Application startup complete.
-server-1  | INFO:     [02-08-2024 07:03:19] Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
-```

comps/vectorstores/lancedb/README.md

@@ -1,139 +0,0 @@
-# Start LanceDB Server
-
-LanceDB is an embedded vector database for AI applications. It is open source and distributed with an Apache-2.0 license.
-
-LanceDB datasets are persisted to disk and can be shared in Python.
-
-## Setup
-
-```bash
-npm install -S vectordb
-```
-
-## Usage
-
-### Create a new index from texts
-
-```python
-import os
-import tempfile
-from langchain.vectorstores import LanceDB
-from langchain.embeddings.openai import OpenAIEmbeddings
-from vectordb import connect
-
-
-async def run():
-    dir = tempfile.mkdtemp(prefix="lancedb-")
-    db = await connect(dir)
-    table = await db.create_table("vectors", [{"vector": [0] * 1536, "text": "sample", "id": 1}])
-
-    vector_store = await LanceDB.from_texts(
-        ["Hello world", "Bye bye", "hello nice world"],
-        [{"id": 2}, {"id": 1}, {"id": 3}],
-        OpenAIEmbeddings(),
-        table=table,
-    )
-
-    result_one = await vector_store.similarity_search("hello world", 1)
-    print(result_one)
-    # [ Document(page_content='hello nice world', metadata={'id': 3}) ]
-
-
-# Run the function
-import asyncio
-
-asyncio.run(run())
-```
-
-API Reference:
-
-- `LanceDB` from `@langchain/community/vectorstores/lancedb`
-- `OpenAIEmbeddings` from `@langchain/openai`
-
-### Create a new index from a loader
-
-```python
-import os
-import tempfile
-from langchain.vectorstores import LanceDB
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.document_loaders.fs import TextLoader
-from vectordb import connect
-
-# Create docs with a loader
-loader = TextLoader("src/document_loaders/example_data/example.txt")
-docs = loader.load()
-
-
-async def run():
-    dir = tempfile.mkdtemp(prefix="lancedb-")
-    db = await connect(dir)
-    table = await db.create_table("vectors", [{"vector": [0] * 1536, "text": "sample", "source": "a"}])
-
-    vector_store = await LanceDB.from_documents(docs, OpenAIEmbeddings(), table=table)
-
-    result_one = await vector_store.similarity_search("hello world", 1)
-    print(result_one)
-    # [
-    #   Document(page_content='Foo\nBar\nBaz\n\n', metadata={'source': 'src/document_loaders/example_data/example.txt'})
-    # ]
-
-
-# Run the function
-import asyncio
-
-asyncio.run(run())
-```
-
-API Reference:
-
-- `LanceDB` from `@langchain/community/vectorstores/lancedb`
-- `OpenAIEmbeddings` from `@langchain/openai`
-- `TextLoader` from `langchain/document_loaders/fs/text`
-
-### Open an existing dataset
-
-```python
-import os
-import tempfile
-from langchain.vectorstores import LanceDB
-from langchain.embeddings.openai import OpenAIEmbeddings
-from vectordb import connect
-
-
-async def run():
-    uri = await create_test_db()
-    db = await connect(uri)
-    table = await db.open_table("vectors")
-
-    vector_store = LanceDB(OpenAIEmbeddings(), table=table)
-
-    result_one = await vector_store.similarity_search("hello world", 1)
-    print(result_one)
-    # [ Document(page_content='Hello world', metadata={'id': 1}) ]
-
-
-async def create_test_db():
-    dir = tempfile.mkdtemp(prefix="lancedb-")
-    db = await connect(dir)
-    await db.create_table(
-        "vectors",
-        [
-            {"vector": [0] * 1536, "text": "Hello world", "id": 1},
-            {"vector": [0] * 1536, "text": "Bye bye", "id": 2},
-            {"vector": [0] * 1536, "text": "hello nice world", "id": 3},
-        ],
-    )
-    return dir
-
-
-# Run the function
-import asyncio
-
-asyncio.run(run())
-```
-
-API Reference:
-
-- `LanceDB` from `@langchain/community/vectorstores/lancedb`
-- `OpenAIEmbeddings` from `@langchain/openai`

comps/vectorstores/pgvector/__init__.py

@@ -1,2 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0

comps/vectorstores/pinecone/README.md

@@ -1,20 +0,0 @@
-# Pinecone setup
-
-## 1. Create Pinecone account from the below link
-
-https://app.pinecone.io/
-
-More details from Pinecone quick start guide https://docs.pinecone.io/guides/get-started/quickstart
-
-## 2. Get API key
-
-API Key is needed to make the API calls. API key can get it from the Project -> Manage -> API keys
-
-## 3. Create the index in https://app.pinecone.io/
-
-Following details are to be provided
-
-1. Index name
-2. Based on the embedding model selected, following has to be provided
-   a. Dimensions
-   b. Metric

comps/vectorstores/pinecone/__init__.py

@@ -1,2 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0

comps/vectorstores/qdrant/README.md

@@ -1,13 +0,0 @@
-# Start Qdrant server
-
-## 1. Download Qdrant image
-
-```bash
-docker pull qdrant/qdrant
-```
-
-## 2. Run Qdrant service
-
-```bash
-docker run -p 6333:6333 -p 6334:6334 -v $(pwd)/qdrant_storage:/qdrant/storage:z qdrant/qdrant
-```

comps/vectorstores/qdrant/__init__.py

@@ -1,2 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0

comps/vectorstores/redis/__init__.py

@@ -1,2 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0

comps/vectorstores/vdms/__init__.py

@@ -1,2 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0

tests/dataprep/test_dataprep_pgvector_langchain.sh

@@ -30,7 +30,7 @@ function start_service() {
     export POSTGRES_PASSWORD=testpwd
     export POSTGRES_DB=vectordb
 
-    docker run --name test-comps-vectorstore-postgres -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -p 5432:5432 -d -v $WORKPATH/comps/vectorstores/pgvector/init.sql:/docker-entrypoint-initdb.d/init.sql pgvector/pgvector:0.7.0-pg16
+    docker run --name test-comps-vectorstore-postgres -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -p 5432:5432 -d -v $WORKPATH/comps/third_parties/pgvector/src/init.sql:/docker-entrypoint-initdb.d/init.sql pgvector/pgvector:0.7.0-pg16
 
     sleep 10s
 

tests/retrievers/test_retrievers_pathway.sh

@@ -10,7 +10,7 @@ ip_address=$(hostname -I | awk '{print $1}')
 function build_docker_images() {
     cd $WORKPATH
 
-    docker build --no-cache --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -t opea/vectorstore-pathway:comps -f comps/vectorstores/pathway/Dockerfile .
+    docker build --no-cache --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -t opea/vectorstore-pathway:comps -f comps/third_parties/pathway/src/Dockerfile .
 
     docker build --no-cache -t opea/retriever-pathway:comps --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/src/Dockerfile .
     if [ $? -ne 0 ]; then
@@ -34,7 +34,7 @@ function start_service() {
     export PATHWAY_HOST="0.0.0.0"
     export PATHWAY_PORT=5433
 
-    docker run -d --name="test-comps-retriever-pathway-vectorstore" -e PATHWAY_HOST=${PATHWAY_HOST} -e PATHWAY_PORT=${PATHWAY_PORT} -e TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} -e http_proxy=$http_proxy -e https_proxy=$https_proxy -v $WORKPATH/comps/vectorstores/pathway/README.md:/app/data/README.md -p ${PATHWAY_PORT}:${PATHWAY_PORT} --network="host" opea/vectorstore-pathway:comps
+    docker run -d --name="test-comps-retriever-pathway-vectorstore" -e PATHWAY_HOST=${PATHWAY_HOST} -e PATHWAY_PORT=${PATHWAY_PORT} -e TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} -e http_proxy=$http_proxy -e https_proxy=$https_proxy -v $WORKPATH/comps/third_parties/pathway/src/README.md:/app/data/README.md -p ${PATHWAY_PORT}:${PATHWAY_PORT} --network="host" opea/vectorstore-pathway:comps
 
     sleep 30s
 

tests/retrievers/test_retrievers_pgvector.sh

@@ -25,7 +25,7 @@ function start_service() {
     export POSTGRES_DB=vectordb
 
     pgvector_port=5079
-    docker run --name test-comps-retriever-pgvector-vectorstore -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -d -v $WORKPATH/comps/vectorstores/pgvector/init.sql:/docker-entrypoint-initdb.d/init.sql -p $pgvector_port:5432 pgvector/pgvector:0.7.0-pg16
+    docker run --name test-comps-retriever-pgvector-vectorstore -e POSTGRES_USER=${POSTGRES_USER} -e POSTGRES_HOST_AUTH_METHOD=trust -e POSTGRES_DB=${POSTGRES_DB} -e POSTGRES_PASSWORD=${POSTGRES_PASSWORD} -d -v $WORKPATH/comps/third_parties/pgvector/src/init.sql:/docker-entrypoint-initdb.d/init.sql -p $pgvector_port:5432 pgvector/pgvector:0.7.0-pg16
     sleep 10s
 
     # pgvector retriever

tests/third_parties/test_third_parties_milvus.sh

@@ -10,7 +10,7 @@ ip_address=$(hostname -I | awk '{print $1}')
 
 
 function start_service() {
-    cd $WORKPATH/comps/vectorstores/milvus
+    cd $WORKPATH/comps/third_parties/milvus/deployment/docker_compose
     rm -rf volumes/
 
     docker compose up -d

tests/third_parties/test_third_parties_pathway.sh

@@ -10,7 +10,7 @@ ip_address=$(hostname -I | awk '{print $1}')
 function build_docker_images() {
     cd $WORKPATH
 
-    docker build --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -t opea/vectorstore-pathway:comps -f comps/vectorstores/pathway/Dockerfile .
+    docker build --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -t opea/vectorstore-pathway:comps -f comps/third_parties/pathway/src/Dockerfile .
 
     cd $WORKPATH
 
@@ -45,7 +45,7 @@ function start_service() {
     export PATHWAY_HOST="0.0.0.0"
     export PATHWAY_PORT=5437
 
-    docker run -d --name="test-comps-vectorstore-pathway-ms" -e PATHWAY_HOST=${PATHWAY_HOST} -e PATHWAY_PORT=${PATHWAY_PORT} -e TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} -e http_proxy=$http_proxy -e https_proxy=$https_proxy -v $WORKPATH/comps/vectorstores/pathway/README.md:/app/data/README.md -p ${PATHWAY_PORT}:${PATHWAY_PORT} --network="host" opea/vectorstore-pathway:comps
+    docker run -d --name="test-comps-vectorstore-pathway-ms" -e PATHWAY_HOST=${PATHWAY_HOST} -e PATHWAY_PORT=${PATHWAY_PORT} -e TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} -e http_proxy=$http_proxy -e https_proxy=$https_proxy -v $WORKPATH/comps/third_parties/pathway/src/README.md:/app/data/README.md -p ${PATHWAY_PORT}:${PATHWAY_PORT} --network="host" opea/vectorstore-pathway:comps
 
     sleep 70s