qnguyen3/docpixie

Multimodal RAG using vision AI instead of embeddings

View on index · View in 3D Map

Related repos

• All-in-one RAG system for multimodal document processing
• Chat with websites using local embeddings
• open-source RAG engine for deep document understanding
• Platform for agentic AI workflows and RAG pipelines
• multimodal AI model for real-time text, image, audio, and video chat
• step-by-step notebooks for building RAG with LangChain
• chatbot UI for Q&A with your docs using RAG
• rag app building blocks for GenAI projects
• fine-tunes embeddings for better retrieval in RAG pipelines
• AI toolbox for speech, video, and image tasks on desktop