Generative AI
DocRAG
Retrieval-augmented Q&A over your own documents. Upload PDFs into groups, ask questions, and get answers grounded in the files rather than the model's general knowledge.
Overview
A generative AI application for asking natural language questions against your own documents. Users organise PDFs into groups of up to three, and queries are answered strictly from the content of those files.
Role
I built all of it: the React and shadcn/ui frontend, the FastAPI backend, and everything between a PDF being uploaded and an answer coming back.
The hard part
How good the answers are comes down to how good the retrieval is. Most of my time went into how documents get split up and which chunks get pulled back, not into the prompt. Get that wrong and the model quietly fills the gaps from its own training data, which is exactly what this was built to avoid.
Architecture
A React and shadcn/ui frontend talking to a FastAPI backend that handles ingestion, chunking and vector storage. When a question comes in, the relevant chunks are fetched and handed to the model as context. PostgreSQL keeps the group and document metadata, and the vector store holds the embeddings used for semantic search.
Stack
- React
- TypeScript
- FastAPI
- Python
- PostgreSQL
- LangChain
- Tailwind CSS
Test credentials
Throwaway accounts for the live demo.
- testing1@gmail.comPassword123
- testing2@gmail.comPassword123