Skip to content

learningmapn/fast-local-rag

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🌐 Language · Ngôn ngữ: 🇬🇧 English (viewing) · 🇻🇳 Tiếng Việt

FastLocalRAG

Authors: learningmap.net (Please visit and support us! Many thanks.)

A local-first document search & Q&A system (Retrieval-Augmented Generation). Ask a question in English or Vietnamese → get a synthesized answer with source citations from your own document collection. Every model runs on your machine — no cloud calls.

Supported formats: PDF (text + scanned/OCR) · Word (.docx) · Excel (.xlsx) · Plain text (.txt) · Markdown (.md) · plus a built-in editor to create notes directly from the UI.

Stack: PyMuPDF + PaddleOCR · python-docx · openpyxl · BGE-M3 (embedding) · BGE-reranker-v2-m3 · ChromaDB · Qwen2.5:3b through Ollama · FastAPI + Gradio (dark theme).

Quickstart

make install        # create venv, install deps
ollama serve        # in another terminal
make models         # download BGE-M3, reranker, Qwen2.5:3b
# drop documents (PDF/DOCX/XLSX/TXT/MD) into data/raw/
make ingest         # parse + embed + index
make ui             # open http://localhost:7860

Documentation

About

This Project make a fast local RAG using LLM on local PC

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors