Allow query embeddings to be searched for in vectorstore #25691
rishabh208gupta
announced in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Checked
Feature request
As part of elastic/elasticsearch-py#2620, we wanted to have the ability to do an mmr search just using the vector embeddings instead of a text query. It would be nice to make query as optional and also allow a vector embedding as an optional param to https://github.com/langchain-ai/langchain/blob/b28bc252c4e7058951c9d3be8ee81595029eab83/libs/core/langchain_core/vectorstores/base.py#L679C9-L679C38
Motivation
To have the flexibility to perform a max_marginal_relevance search using either a text query or a query vector
Proposal (If applicable)
No response
Beta Was this translation helpful? Give feedback.
All reactions