Generative AI
RAG Document Assistant
Teams keep knowledge in PDFs and documents that are slow to search. This project builds an assistant that answers questions from your own documents and shows where each answer came from.
What you'll build
- Document ingestion and chunking pipeline
- Embedding and vector index
- Retriever with metadata filters
- Answer generation grounded in retrieved context
- Chat interface with source citations
You'll leave with: Working assistant · GitHub repository with README · Evaluation notes · Demo walkthrough
- LLMs
- Embeddings
- Vector Databases
- RAG
- APIs
- Python
