GitHub · Jupyter Notebook
moksh-m9u/Ki-Craft
Production-ready multimodal RAG pipeline for PDFs. Extracts text, tables, and images down to the atomic element level via unstructured, chunks and AI-enriches them with a vision LLM, stores them in ChromaDB, and answers queries with full multimodal context
- Stars
- 6
- Forks
- 3
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: chromadb, multimodal-ai, pdf-processing, rag, rag-pipeline, streamlit-dashboard, unstructured-data
Latest data point: Nov 21, 2026 · 6 stars · 3 forks