p1 · [0/7] · 24–38h

Foundation: get a working RAG pipeline end to end

Ask a real question about your knowledge base and get an answer with accurate, verifiable citations - running locally, end to end.

You can ask a real question about your knowledge base and get an answer with accurate, verifiable citations, end to end, running locally via `docker-compose up`.

Tasks
t1-p1-01
authored

Data ingestion from three distinct source types

4–7h
t1-p1-02
authored

Two chunking strategies, recorded per chunk

4–6h
t1-p1-03
draft

Embedding and vector storage pipeline

3–6h
t1-p1-04
draft

Retrieval endpoint with k and a similarity threshold

3–5h
t1-p1-05
draft

Generation endpoint with a structured prompt

3–5h
t1-p1-06
draft

Citation validation

2–4h
t1-p1-07
authored

Minimal frontend or CLI

3–5h