Skip to content

fix: update bm42 hybrid retrieval#12

Open
srini047 wants to merge 1 commit intodevrev:mainfrom
srini047:sub-2
Open

fix: update bm42 hybrid retrieval#12
srini047 wants to merge 1 commit intodevrev:mainfrom
srini047:sub-2

Conversation

@srini047
Copy link
Copy Markdown

Indexing pipeline

DocumentCleaner
→ FastembedSparseDocumentEmbedder (BM42)
→ SentenceTransformersDocumentEmbedder (mxbai-embed-large-v1, 1024-dim)
→ DocumentWriter (Qdrant)

Retrieval pipeline

FastembedSparseTextEmbedder (BM42)

  • SentenceTransformersTextEmbedder (mxbai-embed-large-v1)
    → QdrantHybridRetriever (RRF fusion, top_k=100)
    → SentenceTransformersSimilarityRanker (bge-reranker-v2-m3)
    → Top-K Results

Work item: ISS-269621

@srini047
Copy link
Copy Markdown
Author

@nimit2801 Made an another submission, please help with evaluation.

@prakhar7651
Copy link
Copy Markdown
Contributor

Hey!
There were some errors in the evaluation pipeline. These are your scores.
Recall: 0.1613
Precision: 0.1739

@prakhar7651
Copy link
Copy Markdown
Contributor

prakhar7651 commented Apr 1, 2026

Looking at the quality of submissions and eagerness for folks to contribute, we're extending the deadline to April 7th. Evaluations would be still going on. Please keep contributing.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants