DocRAG
Generative AI
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.
Live demo · Source: Frontend · Source: Backend
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
Sole engineer. React and shadcn/ui frontend, FastAPI backend, and the full ingestion-to-retrieval pipeline.
The hard part
Answer quality is retrieval quality. Keeping responses grounded in the uploaded documents, instead of letting the model fill gaps from training data, meant the chunking and retrieval step was where the work went rather than the prompt.
Architecture
React and shadcn/ui frontend against a FastAPI backend handling ingestion, chunking and vector storage. At query time the relevant chunks are retrieved and passed to the model as context. PostgreSQL holds group and document metadata; the vector store handles embeddings for semantic search.
Stack
React · TypeScript · FastAPI · Python · PostgreSQL · LangChain · Tailwind CSS
Test credentials
Throwaway accounts for the live demo.
- testing1@gmail.com · Password123
- testing2@gmail.com · Password123