Jiaping(JP) Zhang

It would be nice to support HTML format so that we can avoid rendering Rmarkdown in the run time, which might require installing additional packages for rendering in the docker...

> I am facing similar situation with off topic conversations as described [issue](https://github.com/hwchase17/langchain/issues/3963) > > When I printed the value of similarity scores from the similarity_search revealed that the similarity...

> Is this merged with Langchain 0.0.170 yet? I am still getting errors for **search_type='similarity_score_threshold'** Did you use the async version? There's another PR for that

It seems there are some linting problems with the output type since the "relevance_score" method returns the tuple. What's the best way to fix that?

Just FYI, I also implemented the same idea in this PR #3675 . I think this could be a practical and useful feature.

Same question here, how do you use the structured tool to wrap the ConversationalChatAgent so that it can also be passed with the `chat_history`?

I got the same error. not sure whether it's a new bug introduced.

@hwchase17 any insights on how to fix the bug to make it compatible with the current version?

Does score mean the "distance"? (so smaller distance means higher similarity)... it seems there's no `_similarity_search_with_relevance_scores` function in the `chromna.py` to normalize the similarity score like faiss/redis/weaviate.

> Fix version of these dependence: > > ``` > typing-inspect==0.8.0 > typing_extensions==4.5.0 > ``` > > Solve the issue for me: Hmm it's not working for me. I had...