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

# Stream chat

Endpoint: `POST /v2/stream/`

This endpoint allows for real-time or streamed interaction with an agent. It is designed for continuous dialogue where the agent's responses are streamed back to the user incrementally, enhancing the real-time interaction experience.

#### Parameters

<ParamField path="user_id " type="string" required>
  The unique identifier of the user interacting with the agent.
</ParamField>

<ParamField path="agent_id " type="string" required>
  The unique identifier of the agent handling the chat.
</ParamField>

<ParamField path="session_id " type="string" required>
  The session ID to maintain context across multiple interactions.
</ParamField>

<ParamField path="message " type="string" required>
  The user's message or query to the agent.
</ParamField>

<CodeGroup>
  <RequestExample>
    ```bash Curl theme={null}
    curl -X POST "https://agent.api.lyzr.app/v2/stream/" \
     -H "accept: application/json"\
     -H "content-type: application/json"\
     -H "x-api-key: your_Lyzr_API_Key_Here" \
         -d '{
               "user_id": "user123",
               "agent_id": "60d0fe4f5311236168a109ca",
               "session_id": "session123",
               "message": "Can you stream your response?"
             }'

    ```

    ```python Python theme={null}
    import requests

    url = "https://agent.api.lyzr.app/v2/stream/"

    data = {
        "user_id": "user123",  # Replace with actual user ID
        "agent_id": "60d0fe4f5311236168a109ca",  # Replace with actual agent ID
        "session_id": "session123",  # Replace with actual session ID
        "message": "Can you stream your response?"
    }

    headers = {
        "Content-Type": "application/json",
        "x-api-key": "your_Lyzr_API_Key_Here"
    }

    response = requests.post(url, headers=headers, json=data, stream=True)

    # Handle the streamed response
    if response.status_code == 200:
        for chunk in response.iter_content(chunk_size=128):
            print(chunk.decode("utf-8"))
    else:
        print(f"Error: {response.status_code} - {response.text}")
    ```
  </RequestExample>
</CodeGroup>

<ResponseExample>
  ```json 200 theme={null}
  LYZR_AGENT: To improve productivity, you can focus on time management, set clear goals, and minimize distractions.
  ```
</ResponseExample>

#### Response Parameters

<ParamField path="response" type="string">
  The agent’s response sent back incrementally.
</ParamField>