# Unable to connect to vector db using RetrievalQA chain

**URL:** <https://forum.weaviate.io/t/unable-to-connect-to-vector-db-using-retrievalqa-chain/83>\
**Category:** Support\
**Created:** [May 26, 2023, 7:12am UTC](https://forum.weaviate.io/t/unable-to-connect-to-vector-db-using-retrievalqa-chain/83 "2023-05-26T07:12:40Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sriparna](https://avatars.discourse-cdn.com/v4/letter/s/9f8e36/32.png) [@Sriparna](https://forum.weaviate.io/u/Sriparna)\
**Post date:** [May 26, 2023, 7:12am UTC](https://forum.weaviate.io/t/unable-to-connect-to-vector-db-using-retrievalqa-chain/83/1 "2023-05-26T07:12:40Z")

</div>

Created a schema with text2vec-openai vectorizer at class and property level. Trying to query the schema with RetrievalQA chain and trying to run the chain using a langchain agent which throws error : NotImplementedError: Saving not supported for this chain type.

Am I missing anything here? What is the correct langchain chain name for getting data from vector db?

Also, when creating a weaviate client we specify only one Class and one property (vectorstore = Weaviate(client, “ClassName”, “PropertyName”). How to query on multiple properties or is there a way to specify multiple properties to query?  
)

---

<div class="post-metadata">

**Author:** ![sebawita](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/sebawita/32/5_2.png) [@sebawita](https://forum.weaviate.io/u/sebawita)\
**Post date:** [June 8, 2023, 8:29am UTC](https://forum.weaviate.io/t/unable-to-connect-to-vector-db-using-retrievalqa-chain/83/2 "2023-06-08T08:29:57Z")

</div>

Hi @Sriparna,  
I’ve just realised we haven’t gotten back to you yet. My apologies 🙏

This sounds more like a question/request for the LangChain community.  
Could you try to repost your question on [LangChain’s Discord](https://discord.gg/6adMQxSpJS)?