GraphDB Talk to Your Graph是否支持OpenSearch向量数据库？

尝试使用OpenSearch作为向量数据库配置GraphDB的Talk to Your Graph功能，但启动ChatGPT检索插件时出现错误，提示不支持OpenSearch。使用ElasticSearch配置时功能可正常运行。现需确认：

• 该问题是否由配置错误导致？
• ChatGPT检索插件目前是否暂未集成OpenSearch支持？
• 未来版本是否有可能加入OpenSearch作为向量数据库的支持？

启动错误日志 #

INFO:     Started server process [1]
INFO:     Waiting for application startup.
ERROR:    Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 671, in lifespan
async with self.lifespan_context(app):
File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 566, in __aenter__
await self._router.startup()
File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 648, in startup
await handler()
File "/code/./server/main.py", line 159, in startup
datastore = await get_datastore()
File "/code/./datastore/factory.py", line 66, in get_datastore
raise ValueError(
ValueError: Unsupported vector database: opensearch-node2. Try one of the following: llama, elasticsearch, pinecone, weaviate, milvus, zilliz, redis, or qdrant

已配置的docker-compose文件 #

version: '3.4'
services:
  retrieval:
    build:
      context: .
      dockerfile: Dockerfile.run
    extra_hosts:
    - "{azure open.ai host}"
    ports:
    - 8000:8000
    restart: on-failure
    environment:
      OPENAI_API_KEY: "{azureopenaiapi_key}"
      OPENAI_API_BASE: "{azure_open_ai_url}"
      OPENAI_API_TYPE: "azure"
      OPENAI_EMBEDDINGMODEL_DEPLOYMENTID: "-text-embedding-ada-002"
      OPENAI_COMPLETIONMODEL_DEPLYOMENTID: "gpt-4-1106-preview"
      DATASTORE: 'opensearch-node2'
      OPENSEARCH_URL: 'http://opensearch:9200'
      OPENSEARCH_INDEX: 'grapes'
      CHUNK_SIZE: '400'
      BEARER_TOKEN: '{token}'
      LOGURU_LEVEL: "INFO"
    links:
      - opensearch-node2
  opensearch-node2:
    image: opensearchproject/opensearch:latest
    container_name: opensearch-node2
    environment:
      - discovery.type=single-node
      - OPENSEARCH_JAVA_OPTS=-Xms3g -Xmx4g  
      - OPENSEARCH_INITIAL_ADMIN_PASSWORD={password}  
    volumes:
      - opensearch-data2:/usr/share/opensearch/data
    ports:
      - 9200:9200
      - 9600:9600  

  graphdb:
    image: ontotext/graphdb:10.6.2
    extra_hosts:
    - "{openai.azure host}"
    restart: always
    ports:
      - "7200:7200"
    environment:
      GDB_JAVA_OPTS: >-
        -Xmx2g -Xms2g
        -Dhealth.max.query.time.seconds=60
        -Dgraphdb.append.request.id.headers=true
        -Dgraphdb.gpt.token={token}-Dgraphdb.gpt.url={azure openai chat url}
        -Dgraphdb.gpt.auth=api-key
        -Dgraphdb.workbench.importDirectory=/opt/graphdb/home/graphdb-import
    links:
      - opensearch-node2
    volumes:
      - ./data/graphdb:/opt/graphdb/home

volumes:
  opensearch-data2:
    driver: local

补充说明 #

已修改requirements.txt文件，添加了opensearch-py包的安装配置。

内容的提问来源于stack exchange，提问作者Eva Agrawal