feat: knowledge - re-use embeddings on document layer (copy embeddings from docs with same content) #444
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Outdated suggestions cannot be applied.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 PR: re-use existing embeddings on a per-document (chunk) basis if content matches anything already in the DB
Also, the embedding model used for those embeddings must match.
Follow-Up: re-use existing documents on a per-file basis by comparing file checksums
Flow
file.txt
into datasetfoo
using text-embedding-3-large -> embeddings get generatedfile.txt
into datasetbar
using text-embedding-3-large -> embeddings from documents in dataset foo get re-used -> no embeddings get generatedfile.txt
into datasetspam
using text-embedding-3-small -> embeddings get generatedIssue obot-platform/obot#1799