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.

27
/ 100
Experimental

This tool helps researchers, students, or anyone needing in-depth knowledge to find highly relevant information from over 10 million Wikipedia documents. You input your search query, and it provides a ranked list of Wikipedia articles that are semantically related to your question. This is ideal for quickly understanding complex topics or exploring subject areas with nuanced meaning.

No commits in the last 6 months.

Use this if you need to find precise, contextually relevant information from Wikipedia beyond simple keyword matching, especially for complex or ambiguous queries.

Not ideal if you're looking for real-time news, very niche data outside of general knowledge, or prefer only exact keyword matches.

information-retrieval academic-research knowledge-discovery content-exploration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 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.