# Streaming

## Stream JSON Lines

To stream JSON Lines, declare the return type and use `yield` to return the data.

```python
@app.get("/items/stream")
async def stream_items() -> AsyncIterable[Item]:
    for item in items:
        yield item
```

## Server-Sent Events (SSE)

To stream Server-Sent Events, use `response_class=EventSourceResponse` and `yield` items from the endpoint.

     */
    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
     */

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.llm;

/**
 * Callback interface for receiving streaming chat responses from LLM.
 */
@FunctionalInterface
public interface LlmStreamCallback {

    /**
     * Called for each chunk of the streaming response.
     *
     * @param chunk the text chunk from the LLM response
     * @param done true if this is the final chunk
     */

        return this;
    }

    /**
     * Checks if streaming is enabled.
     *
     * @return true if streaming is enabled
     */
    public boolean isStream() {
        return stream;
    }

    /**
     * Sets whether streaming is enabled.
     *
     * @param stream true to enable streaming
     * @return this request for method chaining
     */

     * For files larger than {@value #MAX_BUF_SIZE} bytes (10MB), an
     * {@link IORuntimeException} will be thrown to prevent OutOfMemoryError.
     * For large files, use streaming APIs instead.
     * </p>
     *
     * @param file
     *            The file. Must not be {@literal null}.
     * @return A byte array containing the contents of the file.

When needing to mix blocking and async code, see Asyncer in [the other tools reference](references/other-tools.md).

## Streaming (JSON Lines, SSE, bytes)

See [the streaming reference](references/streaming.md) for JSON Lines, Server-Sent Events (`EventSourceResponse`, `ServerSentEvent`), and byte streaming (`StreamingResponse`) patterns.

## Tooling

# Custom Response Classes - File, HTML, Redirect, Streaming, etc.

There are several custom response classes you can use to create an instance and return them directly from your *path operations*.

Read more about it in the [FastAPI docs for Custom Response - HTML, Stream, File, others](https://fastapi.tiangolo.com/advanced/custom-response/).

You can import them directly from `fastapi.responses`:

```python
from fastapi.responses import (
    FileResponse,

{* ../../docs_src/stream_data/tutorial001_py310.py ln[26:29] hl[27] *}

### No Annotation { #no-annotation }

You don't really need to declare the return type annotation for streaming binary data.

As FastAPI will not try to convert the data to JSON with Pydantic or serialize it in any way, in this case, the type annotation is only for your editor and tools to use, it won't be used by FastAPI.

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);