support for similarity threshold in VectorStoreChatMemoryAdvisor #3341
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Can you follow the DCO guidelines outlined here and resubmit the PR? https://spring.io/blog/2025/01/06/hello-dco-goodbye-cla-simplifying-contributions-to-spring. Thanks! |
Signed-off-by: Peter Keeler <[email protected]>
scionaltera
force-pushed
the
add-vector-store-similarity
branch
from
2fdf065 to
c2e65ff
Compare
|
Closing and resubmitting this to comply with new DCO policy. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This advisor did not have support for setting the similarity threshold, so it defaulted to returning every document regardless of similarity. In a conversation where the user has changed to a different topic the result was returning a bunch of documents with no relevance to the user's latest input.
I experimented with setting a value greater than 0 and liked the results because it would begin to include results more relevant to the conversation. I thought it would be nice to contribute the change back.
I left the default at 0 so as not to change the earlier behavior.