A 24-hour plan for a legal PDF RAG chatbot with Gemini Flash
An internship task requires a first working version of a legal document chatbot within 24 hours. Users upload one or more legal PDFs and ask questions about those documents through a ChatGPT-like chat screen.
The goal is not to train a new model, but to build a clean that processes the PDFs, indexes them, retrieves the most relevant document chunks, and lets Gemini Flash write answers from that context. The fixed stack is Vite and for the frontend, Go for the backend, SQLite for storage, and Gemini Flash as the .
The intended flow is PDF upload, and indexing, questions, retrieval of matching chunks, and grounded answers with citations when possible. The open design questions are the simplest that can still scale later, which to pair with Gemini Flash, and how SQLite should fit into the setup.
Key points
- The first working version must be built within 24 hours.
- The chatbot lets users upload legal PDFs and ask questions about them.
- The goal is a , not training a new model.
- The stack is Vite, , Go, SQLite, and Gemini Flash.
- The system should retrieve relevant chunks and answer with citations when possible.