iaavas/simile-search
Simile combines the power of AI embeddings with fuzzy string matching and keyword search to deliver highly relevant search results—all running locally, no API calls required.
This project helps anyone needing to quickly find specific information within large sets of text or product descriptions, even if there are typos or the search terms aren't exact. You feed it your catalog of items (like product descriptions, document titles, or user profiles) and it allows you to search them using natural language. The result is a list of the most relevant items, ranked by how closely they match your query, making it ideal for e-commerce managers, content librarians, or HR professionals.
Available on npm.
Use this if you need an intelligent search function that understands context and tolerates typos, without relying on external internet services or APIs.
Not ideal if your application requires searching live, constantly changing external data sources or you need a full-text search engine with advanced linguistic analysis for very complex queries.
Stars
28
Forks
1
Language
TypeScript
License
MIT
Category
Last pushed
Dec 28, 2025
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/iaavas/simile-search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ghatdev/embedding-benchmark
Local Embedding models benchmark tool & result
iahuang/stembed-rs
Lightweight static embedding implementation in Rust designed for embedded systems and edge...
rauleli/tclembedding
High-performance Tcl extension for local vector embeddings via ONNX Runtime, optimized for RAG and MySQL.