JulioPeixoto/softrag
Minimal local-first multimodal RAG library powered by SQLite + sqlite-vec.
This project helps developers build applications that can understand and answer questions using information from a variety of sources, including PDFs, web pages, images, and text documents. It takes your raw data in different formats and allows you to query across all of it, generating answers based on both text and visual content. It's ideal for developers who need to create custom search or question-answering tools for their users.
No commits in the last 6 months. Available on PyPI.
Use this if you are a developer needing to build an application that can process and semantically search across various document types and images, all stored and handled locally.
Not ideal if you are an end-user looking for a ready-to-use application, as this is a library designed for developers to integrate into their own projects.
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
pmbstyle/Alice
Alice is a voice-first desktop AI assistant application built with Vue.js, Vite, and Electron....
ob-labs/ChatBot
ChatBot, show how to implement a RAG based on OceanBase or OceanBase seekdb AI capabilities...
rustyneuron01/Conversation-Genome-Project
Structured data & semantic tagging pipeline. Turns raw text (conversations, web pages, surveys)...
stackitcloud/rag-template
Template for AI chatbots & document management using Retrieval-Augmented Generation with vector...
zaldivards/ContextQA
ContextQA - The open-source tool for data-driven conversations