> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Retrieval

> Information retrieval strategies

Retrieval strategies determine how knowledge is fetched.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Retrieval"
        Q[❓ Query] --> S[🔍 Search]
        S --> R[📄 Results]
        R --> RR[📊 Rerank]
        RR --> T[🔝 Top-K]
    end
    
    classDef query fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef process fill:#F59E0B,stroke:#7C90A0,color:#fff
    
    class Q query
    class S,R,RR,T process
```

## Quick Start

<Steps>
  <Step title="Configure Retrieval">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{Agent, KnowledgeConfig};

    let config = KnowledgeConfig::new()
        .source("docs/")
        .retrieval_k(10)       // Fetch 10 results
        .with_rerank()         // Re-rank for relevance
        .retrieval_threshold(0.7);

    let agent = Agent::new()
        .name("Assistant")
        .knowledge(config)
        .build()?;
    ```
  </Step>
</Steps>

***

## Retrieval Options

| Option                | Description        |
| --------------------- | ------------------ |
| `retrieval_k`         | Number of results  |
| `with_rerank`         | Enable reranking   |
| `retrieval_threshold` | Minimum similarity |

***

## Related

<CardGroup cols={2}>
  <Card title="Knowledge" icon="book" href="/docs/rust/knowledge">
    Knowledge base
  </Card>

  <Card title="RAG" icon="database" href="/docs/rust/rag">
    RAG pipeline
  </Card>
</CardGroup>