docs/how_to/vectorstore_retriever/

[giscus[bot]]

docs/how_to/vectorstore_retriever/

A vector store retriever is a retriever that uses a vector store to retrieve documents. It is a lightweight wrapper around the vector store class to make it conform to the retriever interface.

https://python.langchain.com/docs/how_to/vectorstore_retriever/

[gelftheshot]

my Question is.
1, What if i want to get top K result with similarity_score_threshold above a certain point ?
2, What if i use both of them, what is the preference is it K OR "similarity_score_threshold"

[A-Wpro]

From what I tested it will filter on both parameters.

[alexey-asl]

Although the filter is mentioned to be in search_kwargs, the filters keyword argument is actually respected down the line in the according search methods. Would be good to document that and / or fix expectations.
https://github.com/SebanDan/langchain/blob/master/libs/community/langchain_community/vectorstores/azuresearch.py#L841-L922

[maushamkumar]

Can we do other search instead of "similarity_score_threshold". Newbie in GenAI