*/
    LlmChatResponse chat(LlmChatRequest request);

    /**
     * Performs a streaming chat completion request.
     * The callback is invoked for each chunk of the response.
     *
     * @param request the chat request containing messages and parameters
     * @param callback the callback to receive streaming chunks
     * @throws LlmException if an error occurs during the request
     */

            throw new LlmException("LLM chat request failed", e);
        }
    }

    /**
     * Performs a streaming chat completion request using the configured LLM client.
     *
     * @param request the chat request
     * @param callback the callback to receive streaming chunks
     * @throws LlmException if LLM is not available or an error occurs
     */

import jakarta.servlet.FilterChain;
import jakarta.servlet.ServletException;
import jakarta.servlet.http.HttpServletRequest;
import jakarta.servlet.http.HttpServletResponse;

/**
 * API Manager for RAG chat endpoints with SSE streaming support.
 *
 * @author FessProject
 */
public class ChatApiManager extends BaseApiManager {

    private static final Logger logger = LogManager.getLogger(ChatApiManager.class);

        elements.chatInput.val('');
        updateCharCount();
        autoResizeTextarea();

        // Add thinking indicator
        var thinkingId = addThinkingIndicator();

        // Use SSE for streaming
        streamChat(message, thinkingId);
    }

    /**
     * Stream chat using Server-Sent Events
     */
    function streamChat(message, thinkingId) {

        }
    }

    /**
     * Performs an enhanced streaming chat request with multi-phase RAG flow.
     *
     * @param sessionId the session ID (can be null for new sessions)
     * @param userMessage the user's message
     * @param userId the user ID (can be null for anonymous users)
     * @param callback the callback to receive phase notifications and streaming chunks

# 串流 JSON Lines { #stream-json-lines }

當你有一連串資料想以「**串流**」方式傳送時，可以使用 **JSON Lines**。

/// info

在 FastAPI 0.134.0 新增。

///

## 什麼是串流？ { #what-is-a-stream }

「**Streaming**」資料表示你的應用會在整個資料序列尚未完全準備好之前，就開始將資料項目傳送給用戶端。

也就是說，它會先送出第一個項目，用戶端接收並開始處理時，你的應用可能仍在產生下一個項目。

```mermaid
sequenceDiagram
    participant App
    participant Client

    App->>App: Produce Item 1
    App->>Client: Send Item 1

- Introduces new staging modules `k8s.io/streaming` and `k8s.io/cri-streaming` for Kubernetes streaming transport and CRI streaming server code.
  
  `k8s.io/apimachinery/pkg/util/httpstream` (including `spdy` and `wsstream`) remains available as a deprecated compatibility wrapper backed by `k8s.io/streaming`.
  

            throw new LlmException("Request interrupted", LlmException.ERROR_TIMEOUT);
        }
    }

    /**
     * Executes a streaming chat request with concurrency control via Semaphore.
     *
     * @param request the chat request
     * @param callback the streaming callback
     * @throws LlmException if too many concurrent requests or interrupted
     */

/// tip | Consejo

Si quieres hacer streaming de datos binarios, por ejemplo video o audio, Revisa la guía avanzada: [Stream Data](../advanced/stream-data.md).

///

## Streaming de SSE con FastAPI { #stream-sse-with-fastapi }

Para hacer streaming de SSE con FastAPI, usa `yield` en tu path operation function y establece `response_class=EventSourceResponse`.

- **Desplegar en FastAPI Cloud** - Deployment con un clic de tu app a [FastAPI Cloud](https://fastapicloud.com/).
- **Streaming de logs de la aplicación** - Streaming en tiempo real de logs desde tu aplicación desplegada en FastAPI Cloud, con filtrado por nivel y búsqueda de texto.