Issue: AssertionError: Unknown arguments: ['fetch_k', 'maximal_marginal_relevance'] when specifyig search_kwargs ini from_llm() function call

[codingMMax]

Issue you'd like to raise.

Hi there, I am recently using Langchain to build my toy chatbot. I used both Qdrant cloud storage and local storage for test. However, when I am using local storage for vector_store and search_kwargs, everything is good. But, when I switch to the Qdrant cloud storage, the retriever of vectorDB is reporting no machtching search_kwargs. My partial codes shown below.

The error:

Suggestion:

No response

[dosubot]

Answer generated by a 🤖

Answer

Hello,

Thank you for reaching out and providing detailed information about your issue. I understand that you're encountering an AssertionError when specifying search_kwargs in the from_llm() function call while using Qdrant cloud storage.

Unfortunately, I can't see the images you've attached, but based on your description, it seems like the search_kwargs you're using (fetch_k, maximal_marginal_relevance) might not be supported when using Qdrant cloud storage.

The from_llm() function in LangChain accepts a variety of arguments, but the specific search_kwargs that are accepted when using Qdrant cloud storage are not explicitly documented in the repository. It's possible that the search_kwargs you're using are specific to local storage and not supported by Qdrant.

To help you further, could you please provide the exact code snippet where you're calling the from_llm() function and specifying search_kwargs? This would help me understand the context better and provide a more accurate solution.

Also, if you could provide the exact error message you're receiving, that would be very helpful. It might contain additional information about why the search_kwargs are not being accepted.

In the meantime, you might want to check the documentation or source code of Qdrant to see if there's any information about the specific search_kwargs it supports. If the search_kwargs you're using are not supported by Qdrant, you might need to modify your code to use different search_kwargs when using Qdrant cloud storage.

I hope this helps, and I look forward to your response.

Best,
Dosu

Sources

• libs/langchain/langchain/utilities/google_search.py
• libs/langchain/langchain/vectorstores/qdrant.py

---

This response is meant to be useful, save you time, and share context. 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.