Claus Thomasen comments

Results 7 comments of


                                            Claus Thomasen

Implement similarity_search_by_vector in Chroma

This has been fixed by #1568.

ValueError(f"Could not parse LLM output: `{llm_output}`")

This can happen if the model does not follow the given instructions. In most of the cases I have seen, it would proabably be better to simply return the output...

Bug with parsing

This issue is a duplicate of #1477.

ValueError: Could not parse LLM output

This issue is a duplicate of #1477.

similarity search by vector chroma

> can we change `similarity_search_with_score` to call this method now? to avoid duplicated code Hmm, the `similarity_search_with_score` needs the scores, which are not returned by the `similarity_search_by_vector`, at least not...

similarity search by vector chroma

This PR is replaced by #1568 to fix my mistaken commits resulting in merge commits, sorry.

Embedding individual text

You can use a Vector Db to store the embeddings, like Chroma. langchain has a nice wrapper for Chroma, that can be used for adding documents (products in your case)...