Dicklesworthstone/frankensearch
Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M, quality-refined rankings in 150ms via MiniLM-L6-v2. Combines lexical (Tantivy BM25) and semantic (vector cosine) search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.
This tool helps technical professionals quickly find information within their local files, like project documentation or codebases. It takes a natural language query or keywords as input and provides a fast initial set of relevant results, followed by a more refined and accurate ranking shortly after. Software developers, operations engineers, or researchers working with large local text corpora would find this useful.
Use this if you need to perform rapid, high-quality searches across your personal or project-specific files, blending keyword precision with semantic understanding.
Not ideal if you need to search public web content, manage a global enterprise search engine, or if your primary need is strictly exact keyword matching without semantic nuance.
Stars
41
Forks
9
Language
Rust
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Dicklesworthstone/frankensearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
winkjs/wink-bm25-text-search
Fast Full Text Search based on BM25
run-llama/semtools
Semantic search and document parsing tools for the command line
Hamza5/file-brain
Smart local file search app that understands your files
OpenConceptLab/oclmap
OCL Mapper (beta): an open-source AI-supported terminology mapping solution for the global community
filippostanghellini/DocFinder
DocFinder is a local-first indexing and searching documents using semantic embeddings stored in...