rag-retrieval

# RAG Retrieval

Combine vector search with LLM generation for accurate, grounded responses.

## Basic RAG Pattern

```python
async def rag_query(question: str, top_k: int = 5) -> str:
    """Basic RAG: retrieve then generate."""
    # 1. Retrieve relevant documents
    docs = await vector_db.search(question, limit=top_k)

    # 2. Construct context
    context = "\n\n".join([
        f"[{i+1}] {doc.text}"
        for i, doc in enumerate(docs)
    ])

    # 3. Generate with context
    response = await llm.chat([
        {"role": "system", "content":
            "Answer using ONLY the provided context. "
            "If not in context, say 'I don't have that information.'"},
        {"role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}"}
    ])

    return response.content
```

## RAG with Citations

```python
async def rag_with_citations(question: str) -> dict:
    """RAG with inline citations [1], [2], etc."""
    docs = await vector_db.search(question, limit=5)

    context = "\n\n".join([
        f"[{i+1}] {doc.text}\nSource: {doc.metadata['source']}"
        for i, doc in enumerate(docs)
    ])

    response = await llm.chat([
        {"role": "system", "content":
            "Answer with inline citations like [1], [2]. "
            "End with a Sources section."},
        {"role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}"}
    ])

    return {
        "answer": response.content,
        "sources": [doc.metadata['source'] for doc in docs]
    }
```

## Hybrid Search (Semantic + Keyword)

```python
def reciprocal_rank_fusion(
    semantic_results: list,
    keyword_results: list,
    k: int = 60
) -> list:
    """Combine semantic and keyword search with RRF."""
    scores = {}

    for rank, doc in enumerate(semantic_results):
        scores[doc.id] = scores.get(doc.id, 0) + 1 / (k + rank + 1)

    for rank, doc in enumerate(keyword_results):
        scores[doc.id] = scores.get(doc.id, 0) + 1 / (k + rank + 1)

    # So