Available for work
AI · RAG pipeline/2026/Live

DocMind

Ask any PDF a question and get an answer you can check.

DocMind preview
Overview

A production-grade RAG pipeline focused on retrieval quality and verifiability. Every answer cites the exact source chunk it came from, so you never have to take the model's word for it.

Stack
  • Node.js
  • TypeScript
  • OpenAI API
  • pgvector
  • PostgreSQL
  • Prisma
  • Docker
How it works
  1. 01

    Built a full ingest pipeline: PDF parsing, 500-token chunking with overlap, batched embeddings, and vector storage in pgvector, so any document is queryable within seconds of upload.

  2. 02

    Implemented cosine similarity retrieval on pgvector's native operator, with optional HNSW indexing for scale and per-document scoping for multi-tenant use.

  3. 03

    Engineered a streaming generation layer with citation parsing: the model references numbered sources that map back to real chunks and render as clickable references in the UI.

  4. 04

    Wrote a Precision@3 evaluation script that scores retrieval against a test suite, measuring whether the right chunk lands in the top three and logging citation rate across every question.

Menu00%