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.
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.
Stars
15
Forks
1
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
AmenRa/retriv
A Python Search Engine for Humans 🥸
AKSW/sante
The Ontology, Dataset and Knowledge Search Engine
gnes-ai/gnes
GNES is Generic Neural Elastic Search, a cloud-native semantic search system based on deep...
raphaelsty/cherche
Neural Search
erenisci/wikipedia_synonym_search
Semantic search engine over Turkish Wikipedia. Uses a 3-stage pipeline (MongoDB → Word2Vec →...