Verified answer synthesized from uploaded PDF context with strict page-level source attribution and automatic model fallback.
- 01Built and deployed a document Q&A app that returns page-level cited answers and declines out-of-scope questions, through semantic search with a similarity threshold, using pgvector, Gemini embeddings, and Groq at $0 infrastructure cost
- 02Kept the app reliable within free-tier API limits through resumable batch embedding, automatic model fallback, and Postgres-backed rate limiting (3 questions per minute per visitor), using Next.js route handlers and Neon
- 03Shipped with 30+ unit tests, an evaluation harness that scores answer correctness, citation accuracy, and refusals, and CI on GitHub Actions (lint, type-check, tests, build, Docker image)
RAG Document Q&A — AI Assistant with Cited Answers
Page-level cited document Q&A with semantic search, similarity thresholding, and $0 infrastructure cost.
Built and deployed a document Q&A app that returns page-level cited answers and declines out-of-scope questions through semantic search with a similarity threshold, using pgvector, Gemini embeddings, and Groq at $0 infrastructure cost.
Standard LLM chat interfaces hallucinate answers when queried against private PDFs and fail to tell users which exact page a claim came from or when a question falls outside the uploaded documents.
Users: Training teams, researchers, analysts, and internal operations staff who need verifiable, page-cited answers from technical manuals and PDFs.


