zilliztech / zilliztech/vector-graph-rag

Support incremental knowledge base updates

Open
#32 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
245
Forks
38
PR merge metrics
No merged PRs in 30d

Description

Currently the add_documents method drops all collections before recreating them and importing the documents. This requires all documents to be provided to the add_documents method whenever calling it which makes the update latency grow with the amount of documents.

Instead, it would be great if there would be a way to update the knowledge base incrementally.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in src/vector_graph_rag/rag.py at the add_documents method and inspect the collection recreation described around line 372. Trace how repeated calls currently rebuild the knowledge base. Done means later calls can add documents incrementally without requiring all previous documents or dropping the existing collections.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
databases
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.