filippostanghellini/DocFinder
DocFinder is a local-first indexing and searching documents using semantic embeddings stored in SQLite. Everything runs on your machine, no external services required.
This tool helps you quickly find information across all your personal documents—PDFs, Word files, Markdown, and plain text—by understanding the meaning of your search query, not just keywords. It takes your collection of documents and a natural language question, then provides relevant passages and answers. Anyone who deals with a large personal archive of documents—like researchers, lawyers, or writers—will find this useful.
Use this if you need to quickly locate information or get answers from a large personal collection of documents without relying on cloud services for privacy.
Not ideal if you need to search public web content, shared network drives, or a very small number of documents where simple file search is sufficient.
Stars
14
Forks
3
Language
Python
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/filippostanghellini/DocFinder"
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
Dicklesworthstone/frankensearch
Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M,...