ConversationalRetrievalQAChain cannot use the ChatBaiduWenxin model, will it consider compatibility in the future?

[zandko]

[dosubot[bot]]

🤖

Hello,

Thank you for your question. As per the current compatibility of the ConversationalRetrievalQAChain in the langchainjs codebase, it is compatible with the "gpt-3.5-turbo", "gpt-4", and "text-ada-001" language models. This is evident from the code snippets where instances of the ChatOpenAI and OpenAI classes are created with these model names and used to create a ConversationalRetrievalQAChain.

Regarding the compatibility with the ChatBaiduWenxin model, I couldn't find any ongoing work or planned feature in the langchainjs repository. However, it's worth noting that the framework is designed to be extensible and it's possible that support for additional models could be added in the future.

As for the issue you're experiencing, there was a similar issue reported previously (#1162) where the solution was to upgrade the LangChain package from version 0.0.67 to 0.0.72. If you're using an older version of LangChain, I would recommend trying this solution.

Please note that I cannot see the image you've attached. If you're still experiencing issues, could you please provide more details about the error message or the context in which the error occurs?

Best regards, Dosu

Sources

• Getting Argument of type 'ChatOpenAI' is not assignable to parameter of type 'BaseLLM'. when trying to pass ChatOpenAI to RetrievalQAChain or ConversationalRetrievalQAChain
• examples/src/chains/conversational_qa_built_in_memory.ts
• langchain/src/chains/tests/conversational_retrieval_chain.int.test.ts
• examples/src/chains/conversational_qa.ts

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[jacoblee93]

Hey @zandko, you can recreate the same functionality with runnables:

https://js.langchain.com/docs/expression_language/cookbook#conversational-retrieval-chain

You can see where to pass in/modify the prompt. We'll be prioritizing this approach going forwards.