Symposium PDF RAG Bot
A focused PDF question-answering assistant for a symposium guide. A responsive browser chat connects to a FastAPI retrieval service, combining OpenAI answers with inspectable page references for schedules, event rules, and registration.
The problem
A focused PDF question-answering assistant for a symposium guide. A responsive browser chat connects to a FastAPI retrieval service, combining OpenAI answers with inspectable page references for schedules, event rules, and registration.
My contribution
I integrated PDF ingestion, retrieval, answer generation, page-reference display, public API admission, and Vercel delivery.
Product features
- Separate PDF ingestion builds a FAISS index of overlapping source passages.
- Retrieval supplies relevant guide excerpts to the answer prompt.
- Answers show deduplicated source-page references in expandable chat details.
- Index metadata checks help detect a source or embedding mismatch.
- Shared Upstash admission limits requests before provider work.
Engineering work
- Document retrieval: Ingest the guide separately and retrieve relevant FAISS passages for each question.
- Page-level context: Keep source metadata through generation and show deduplicated page references in chat.
- Public delivery: Connect a responsive JavaScript interface to FastAPI with input validation and shared Upstash admission.
Outcome & scope
Turns a five-page guide into a searchable conversation backed by 9 indexed passages. The live date-and-venue question returned the correct event details and page references; no user-adoption metrics are available.
Public PDF Q&A demo · 5-page event guide · Page references