yafitzdev/fitz-ai
Intelligent, honest knowledge retrieval in 5 minutes. No infrastructure. No boilerplate.
Implements KRAG (Knowledge Routing Augmented Generation), which parses documents into typed retrieval units (code symbols, sections, tables) and routes queries to specialized search strategies rather than treating all content uniformly. Enforces answer honesty through an ML governance classifier validated against a 2,920-case adversarial benchmark, achieving 86.5% recall at detecting unanswerable questions with only 5.7% false-positive rate. Supports immediate querying via progressive background indexing while handling temporal queries, code symbol extraction, and tabular SQL natively—requiring only Ollama or OpenAI/Cohere API keys, with no framework assembly needed.
20 stars and 1,116 monthly downloads. Available on PyPI.
Stars
20
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Monthly downloads
1,116
Commits (30d)
0
Dependencies
16
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/yafitzdev/fitz-ai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
0verL1nk/PaperSage
📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent...
RapidFireAI/rapidfireai
RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning