← BACK TO PROJECT

PROJECT / RAG / Evaluation

Document QA System

A retrieval system built to make document answers traceable, measurable, and fast enough to use.

RAGEvaluationRetrieval
STATUS
shipped
YEAR
2026
ROLE
Backend & AI Engineer
STACK
Python · FastAPI · PostgreSQL · pgvector

SYSTEM / ARCHITECTURE

How it fits together

  1. 01Document pipeline
  2. 02Hybrid retriever
  3. 03Reranker
  4. 04Citation builder
  5. 05Evaluation service
Recall@5
93.2%
P95 latency
820ms
Evaluated queries
500
01

The problem

Prototype question-answering felt impressive but could not show why an answer was trustworthy. The product needed citations, predictable latency, and a repeatable quality measure.

  • Mixed document formats
  • Ambiguous user vocabulary
  • Answers must trace back to exact passages
02

The system

Documents are normalized and chunked with structural metadata. Lexical and vector results are merged, reranked, then passed to an answer step that can only cite retrieved passages.

  • Hybrid retrieval
  • Offline golden-query evaluation
  • Per-stage latency and quality telemetry
03

Outcome

The shipped service made retrieval quality measurable and reduced the time needed to diagnose bad answers from hours to minutes.