AnswerDotAI / AnswerDotAI/RAGatouille

RuntimeError when indexing with FAISS

Open
#232 6 comments 1 reaction 0 assignees View on GitHub
Dominant language
Python
Stars
4k
Forks
276
PR merge metrics
No merged PRs in 30d

Description

I'm getting this error when I try to index document with FAISS. Is there way change number or cluster?
`RuntimeError: Error in void faiss::Clustering::train_encoded(faiss::idx_t, const uint8_t*, const faiss::Index*, faiss::Index&, const float*) at /project/faiss/faiss/Clustering.cpp:261: Error: 'nx >= k' failed: Number of training points (109) should be at least as large as number of clusters (128)`

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by tracing the document-indexing entry point that invokes FAISS and compare its cluster count with the 109 training points reported in the error. Determine how the number of clusters can be changed or validated, and consider the issue done when indexing a smaller document set no longer raises this RuntimeError.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, search
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.