JulioPeixoto/softrag
Minimal local-first multimodal RAG library powered by SQLite + sqlite-vec.
Supports hybrid retrieval combining full-text search (FTS5) with semantic similarity, and handles multimodal content including images through vision-based analysis for unified cross-modal querying. Integrates with LangChain ecosystem and multiple LLM providers (OpenAI, Hugging Face, Ollama) while maintaining complete local-first operation with embeddings and cache persisted in a single SQLite database file.
No commits in the last 6 months. Available on PyPI.
Stars
18
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jul 26, 2025
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/JulioPeixoto/softrag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ob-labs/ChatBot
ChatBot, show how to implement a RAG based on OceanBase or OceanBase seekdb AI capabilities...
pmbstyle/Alice
Alice is a voice-first desktop AI assistant application built with Vue.js, Vite, and Electron....
stackitcloud/rag-template
Template for AI chatbots & document management using Retrieval-Augmented Generation with vector...
GGyll/condo_gpt
An intelligent assistant for querying and analyzing real estate condo data in Miami.
rustyneuron01/Conversation-Genome-Project
Structured data & semantic tagging pipeline. Turns raw text (conversations, web pages, surveys)...