QmiAI/Qmedia
An open-source AI content search engine designed specifically for content creators. Supports extraction of text, images, and short videos. Allows full local deployment (web app, RAG server, LLM server). Supports multi-modal RAG content Q&A.
Leverages a modular three-service architecture—`mm_server` (multimodal models via Ollama, CLIP, BGE), `mmrag_server` (LlamaIndex-based RAG with content extraction and vector storage), and `qmedia_web` (Next.js frontend)—enabling independent or combined deployment. Implements content decomposition through OCR, video transcription (Faster Whisper), and visual understanding to build searchable embeddings; supports Google content integration alongside local data indexing for privacy-focused workflows.
613 stars. No commits in the last 6 months.
Stars
613
Forks
73
Language
TypeScript
License
MIT
Category
Last pushed
Mar 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/QmiAI/Qmedia"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
mazzasaverio/fastapi-langchain-rag
(Let's start with a) Scalable question-answering system utilizing FastAPI, LangChain (LCEL), and...
charliewei0716/on-your-data-with-streamlit
Showcase the use of Azure OpenAI's native On Your Data feature and integrates it with Streamlit,...
ben-ogden/pinecone-rag
Using Pinecone, LangChain + OpenAI for Generative Q&A with Retrieval Augmented Generation (RAG).
thevladdo/rag-backend
Retrieval-Augmented Generation server with Pinecone and OpenAI
teamunitlab/rag-document-app
This FastAPI-based RAG service processes OCR data, generates embeddings using OpenAI, and...