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

# Streaming Response With Custom Settings

> In this guide, we will walk through the process of obtaining a streaming response from the ChatFly API with the custom your settings.

### API Endpoint

The API endpoint for obtaining a streaming response with custom setting is:

```text theme={null}
https://backend.chatfly.co/api/chat/get-streaming-response-with-custom-settings
```

To get a streaming response, you need to send a POST request to the API endpoint with a Params and JSON request.
Here's an example Params request:

```params theme={null}
{
    "type_qa": "String"
}
```

* type\_qa (string): type of question message.

And here's an example JSON request:

```json theme={null}
{
  "bot_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "message": "Hi",
  "chat_history": [
      {
        "sender_type": "user",
        "content": "Hi"
      },
      {
        "sender_type": "assistant",
        "content": "Hello! How can I assist you today?"
      }],
  "custom_prompt": "I want you to act as an assistant to a customer support agent by writing email responses...",
  "gpt_model_name": "gpt-3.5-turbo-16k",
  "temperature": 0,
  "rules": []
}
```

### Example Request

Here are example commands to obtain a streaming response with custom settings using the ChatFly API:

<CodeGroup>
  ```json curl theme={null}
  curl -X 'POST' \
    'https://backend.chatfly.co/api/chat/get-streaming-response-with-custom-settings' \
    -H 'accept: application/json' \
    -H 'Content-Type: application/json' \
    -d '{
    "type_qa": "string",
    "bot_id": "xxxx-xxxx-xxxx-xxxx",
    "message": "Hi",
    "chat_history": [
        {
          "sender_type": "user",
          "content": "Hi"
        },
        {
          "sender_type": "assistant",
          "content": "Hello! How can I assist you today?"
        }],
    "custom_prompt": "I want you to act as an assistant to a customer support agent by writing email responses...",
    "gpt_model_name": "gpt-3.5-turbo-16k",
    "temperature": 0,
    "rules": []
  }'
  ```

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

  url = 'https://backend.chatfly.co/api/chat/get-streaming-response-with-custom-settings'
  headers = {
      'accept': 'application/json',
      'Content-Type': 'application/json'
  }
  params = {
      'type_qa': 'string',
  }
      
  data = {
      'bot_id': 'xxxx-xxxx-xxxx-xxxx',
      'message': 'Hi',
      'chat_history': [
        {
          "sender_type": "user",
          "content": "Hi"
        },
        {
          "sender_type": "assistant",
          "content": "Hello! How can I assist you today?"
        }],
      'custom_prompt': 'I want you to act as an assistant to a customer support agent by writing email responses...',
      'gpt_model_name': 'gpt-3.5-turbo-16k',
      'temperature': 0,
      'rules': []
  }

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

  if response.status_code == 200:
      print("Request successful!")

      # Process the streaming response as needed
      for chunk in response.iter_content(chunk_size=1024):
          if chunk:
              # Process each chunk of the streaming response
              print(chunk.decode('utf-8'), end="", flush=True)
  else:
      print("Request failed with status code:", response.status_code)
      print(response.text)
  ```

  ```json javascript theme={null}
  const axios = require('axios');

  const url = 'https://backend.chatfly.co/api/chat/get-streaming-response-with-custom-settings';
  const headers = {
    'accept': 'application/json',
    'Content-Type': 'application/json'
  };
  const data = {
    'type_qa': 'string',
    'bot_id': 'xxxx-xxxx-xxxx-xxxx',
    'message': 'Hi',
    'chat_history': [
        {
          "sender_type": "user",
          "content": "Hi"
        },
        {
          "sender_type": "assistant",
          "content": "Hello! How can I assist you today?"
        }],
    'custom_prompt': 'I want you to act as an assistant to a customer support agent by writing email responses...',
    'gpt_model_name': 'gpt-3.5-turbo-16k',
    'temperature': 0,
    'rules': []
  };

  axios.post(url, data, { headers })
    .then(response => {
      console.log('Response Status Code:', response.status);
      console.log('Response Content:', response.data);
    })
    .catch(error => {
      console.error('Error:', error);
    });
  ```
</CodeGroup>

### Response Body

The streaming response is as follows:

```
*Answer:* Hello! How can I assist you today? 

*Suggest Questions:*
1. What specific information are you looking for?
2. Is there a particular department or service you need assistance with?
3. Can you provide more details about your inquiry or issue?
4. How can I help make your experience better?
```