RAG: discard duplicate facts by default #952
Merged
Conversation
This file contains 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
dluc
force-pushed
the
duplicatechunks
branch
from
f08b24a to
66f7be5
Compare
dluc
force-pushed
the
duplicatechunks
branch
from
66f7be5 to
5e32680
Compare
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Outdated suggestions cannot be applied.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.
Motivation and Context (Why the change? What's the scenario?)
When importing chat messages or running tests with small files or without IDs, the storage might fill up with duplicate chunks of text that affect the number of tokens used when generating an answer.
High level description (Approach, Design)
When using the ASK API, after fetching N records from storage, discard duplicates and use only unique chunks in the RAG prompt.
The behavior is configurable via
SearchClientConfig.IncludeDuplicateFactsand request contextcustom_rag_include_duplicate_facts_boolarg.