> ## 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.

# Streaming

> Stream LLM responses in real-time for better user experience

Display AI responses as they generate, creating a natural chat experience.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Streaming Response"
        U[💬 User] --> A[🤖 Agent]
        A --> S[⚡ Stream]
        S --> |word by word| D[📺 Display]
    end
    
    classDef user fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef agent fill:#F59E0B,stroke:#7C90A0,color:#fff
    classDef output fill:#10B981,stroke:#7C90A0,color:#fff
    
    class U user
    class A,S agent
    class D output
```

## Quick Start

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

    let agent = Agent::new()
        .name("Assistant")
        .instructions("You are helpful")
        .stream(true)  // Enable streaming
        .build()?;

    agent.chat("Tell me a story").await?;
    // Response appears word by word
    ```
  </Step>

  <Step title="Disable Streaming">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::Agent;

    let agent = Agent::new()
        .name("Assistant")
        .stream(false)  // Wait for complete response
        .build()?;
    ```
  </Step>
</Steps>

***

## How It Works

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
    participant User
    participant Agent
    participant LLM
    
    User->>Agent: chat("question")
    Agent->>LLM: Request (stream=true)
    loop Each token
        LLM-->>Agent: StreamEvent::DeltaText
        Agent-->>User: Display token
    end
    LLM-->>Agent: StreamEvent::StreamEnd
    Agent-->>User: Complete
```

***

## Stream Events

Events emitted during streaming.

| Event             | Description                 |
| ----------------- | --------------------------- |
| `RequestStart`    | API call initiated          |
| `HeadersReceived` | HTTP headers arrived        |
| `FirstToken`      | First content (TTFT marker) |
| `DeltaText`       | Text content chunk          |
| `DeltaToolCall`   | Tool call in progress       |
| `ToolCallEnd`     | Tool call complete          |
| `LastToken`       | Final content chunk         |
| `StreamEnd`       | Stream completed            |
| `Error`           | Error occurred              |

***

## Configuration

| Option   | Type   | Default | Description               |
| -------- | ------ | ------- | ------------------------- |
| `stream` | `bool` | `true`  | Enable response streaming |

***

## Best Practices

<AccordionGroup>
  <Accordion title="Enable for chat interfaces">
    Streaming provides immediate feedback, improving perceived performance.
  </Accordion>

  <Accordion title="Disable for batch processing">
    When processing many requests, disable streaming for efficiency.
  </Accordion>
</AccordionGroup>

***

## Related

<CardGroup cols={2}>
  <Card title="Agent" icon="robot" href="/docs/rust/agent">
    Agent configuration
  </Card>

  <Card title="Callbacks" icon="phone" href="/docs/rust/callbacks">
    Handle stream events
  </Card>
</CardGroup>