dcarpintero/wikisearch

Multilingual Semantic Search with Reranking on a prepared large vectorized dataset comprising 10 million Wikipedia documents. It supports dense retrieval, keyword search, and hybrid search.

20
/ 100
Experimental

Implements a three-stage retrieval pipeline combining Weaviate vector database queries (BM25, dense, hybrid) with Cohere's rerank and generation APIs to progressively refine search results and synthesize answers. The architecture supports multiple languages through language-filtered embeddings and includes exponential backoff retry logic for API resilience, deployed as a Streamlit web application.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

MIT

Last pushed

Nov 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/dcarpintero/wikisearch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.