Add initial support for PGVector #45
Open
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
added 9 commits
February 24, 2025 07:39
Fix NODE_MODULE_VERSION error from "better-sqlite3"
Add support for PGVector langchain-postgres psycopg[binary,pool]
Refactor: embedding into get_embedding() vectorstore to get_vectorstore_chromaDB(), this maintains the original behavior and get_vectorstore_PGVector(), this returns a vectorstore that uses Postgres as the backend.
A unified configuration file for the backend.
Add missing requirements.
Improve PGVector support.
Missing pgvector package
Add initial support for PGVector as vectorstore backing.
|
To get it working you need to:
In config.py you need to:
Also you'll have to set the |
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Outdated suggestions cannot be applied.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.
Changes:
Fix NODE_MODULE_VERSION error from "better-sqlite3"
Refactor get_vectorstore() into separate functions:
get_embeddings()
get_chromaDB_vectorstore(), this is the original but separated into a function of it's own.
get_PGVector_vectorstore(), this provides support for PGVector as the vectorstore
Add which_vectorstore to the function signature of get_vectorstore() to specify if ChromaDB or PGVector should be used.
Create config.py where various parameters for the backend can be set instead of being hardcoded.