zayedrais/DocumentSearchEngine
Document Search Engine project with TF-IDF abd Google universal sentence encoder model
This helps data scientists or researchers build a search engine that understands the meaning of text, not just keywords. You provide a collection of documents (like articles or newsgroup posts) as input, and it processes them to enable a search where you can ask natural language questions and get back the most relevant documents. This is useful for anyone needing to intelligently sift through large amounts of textual information.
No commits in the last 6 months.
Use this if you need to set up a system where users can find relevant documents by searching with sentences or questions, not just exact keywords.
Not ideal if you need a simple keyword-matching search or if your primary users are non-technical individuals who require a ready-to-use application rather than a coding project.
Stars
55
Forks
24
Language
Jupyter Notebook
License
—
Category
Last pushed
May 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/zayedrais/DocumentSearchEngine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrickfrank1/chesspos
Embedding based chess position search and embedding learning for chess positions
alexklibisz/elastiknn
Elasticsearch plugin for nearest neighbor search. Store vectors and run similarity search using...
freedmand/semantra
Multi-tool for semantic search
koursaros-ai/nboost
NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve...
Mubelotix/SimRepo
Shows similar repositories in the sidebar