-
-
Notifications
You must be signed in to change notification settings - Fork 118
Pluggable vector storage #339
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
… kludgy. If we want to separately search description via embeddings, make it a note.
…eation functions. Switched embeddings generation for doc to a corpus action when doc is added as the embeddings are now based on corpus and not same dimension in all cases.
… version AND is going to be deprecated anyway.
…alyzer_task decorator.
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #339 +/- ##
=========================================
Coverage 89.63% 89.63%
=========================================
Files 261 278 +17
Lines 10515 12021 +1506
=========================================
+ Hits 9425 10775 +1350
- Misses 1090 1246 +156
... and 2 files with indirect coverage changes Continue to review full report in Codecov by Sentry.
🚀 New features to boost your workflow:
|
…otation_vector_store.py
…yk understand our versions.
…y functions to work with LlamaIndex agents.
pgvector doesn't make it easy to store variable dimension vectorsand we will want to mix and match vectors of same dimensions but different embeddings. This change leverages pipeline and restructured data model for embeddings to facilitate this use case where we want mixed embeddings env. Initial plan is to set at Corpus level but in theory could have mixed vectors within corpus too.