# RAG Agent with Grounded Citations

> Retrieval-augmented answering that cites source chunks and refuses when the context does not support an answer.

Category: AI Agent Workflows  
Tags: rag, retrieval, citations, embeddings  
Setup time (estimate): 2-4 hours  
Estimated cost: One-time embedding cost for your corpus plus per-query embedding and generation.  
Last verified: not yet independently verified

## Pipeline

1. **Ingest**: split documents into ~300-800 token chunks with overlap; keep `doc_id`, `title`, `url`, and position metadata.
2. **Embed and index** chunks in a vector store (pgvector, SQLite-vec, Qdrant, etc.). Optionally add a keyword (BM25) index for hybrid search.
3. **Retrieve** top-k (e.g. 20) candidates, then **rerank** to the best 5.
4. **Generate** with the prompt below; chunks are labelled `[1]..[n]`.
5. **Validate**: check every citation number exists; if the answer has no citations, treat it as unsupported.

## Prompt

```text
Answer the question using ONLY the sources below.
Cite sources inline like [2]. Every factual sentence needs a citation.
If the sources do not contain the answer, say "I don't know based on the provided sources."

Sources:
{{#each chunks}}[{{@index1}}] {{title}}: {{text}}
{{/each}}

Question: {{question}}
```

## Tips

- Hybrid (vector + keyword) retrieval handles names, codes, and IDs far better than vectors alone.
- Evaluate with a small fixed question set and track answer correctness and citation accuracy over time.

## Failure modes

- Citations that point to chunks that don't support the claim; validate cited IDs.
- Poor chunking splits answers across chunks.
- Stale index returns outdated facts; schedule re-indexing.