> ## 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.

# Start Chatting with Bot

> Learn how to initiate a conversation with your ChatFly bot using streaming responses from the ChatFly API.

### API Endpoint

The API endpoint for obtaining a streaming response is:

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

### Request Body

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

```json theme={null}
{
  "bot_id": "xxxx-xxxx-xxxx-xxxx",
  "message": "string",
  "session_id": "xxxx-xxxx-xxxx-xxxx"
}
```

* bot\_id (string): ID of your bot.
* message (string): Message from the user.
* session\_id (string): ID of the session.

### Example Request

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

<CodeGroup>
  ```json curl theme={null}
  curl -N -X POST "https://backend.chatfly.co/api/chat/get-streaming-response" \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "bot_id": "xxxx-xxxx-xxxx-xxxx",
    "message": "string",
    "session_id": "xxxx-xxxx-xxxx-xxxx"
  }'
  ```

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

  url = "https://backend.chatfly.co/api/chat/get-streaming-response"
  headers = {
      'Content-Type': 'application/json',
  }

  data = {
    "bot_id": "xxxx-xxxx-xxxx-xxxx",
    "message": "string",
    "session_id": "xxxx-xxxx-xxxx-xxxx",
  }

  response = requests.post(url, headers=headers, json=data, 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 fetch/javascript theme={null}
  const url = "https://backend.chatfly.co/api/chat/get-streaming-response";
  const headers = {
      "Content-Type": "application/json"
  };

  const data = {
      bot_id: "xxxx-xxxx-xxxx-xxxx",
      message: "string",
      session_id: "xxxx-xxxx-xxxx-xxxx",
      user_id: "xxxx-xxxx-xxxx-xxxx",
      sender: "xxxx-xxxx-xxxx-xxxx"
  };

  const decoder = new TextDecoder('utf-8');

  fetch(url, {
      method: 'POST',
      headers: headers,
      body: JSON.stringify(data),
  })
      .then(response => {
          // Check for error response
          if (!response.ok) {
              return response.text().then(errorText => {
                  throw new Error(`Request failed with status code:: ${response.status} - ${errorText}`);
          });
          }

          console.log("Request successful!");

          // Otherwise, return the streaming response body
          return response.body;
      })
      .then(stream => {
          // Create a reader to read the stream
          const reader = stream.getReader();

          // Define the function that will handle the stream
          function read() {
              reader.read().then(({ done, value }) => {
                  // Check to see if we're done with the stream
                  if (done) {
                      return;
                  }

                  // Convert the value (a Uint8Array) to a string
                  const text = decoder.decode(value);

                  process.stdout.write(text);

                  // Read some more, and call this function again
                  read();
              });
          }

          // Start reading the stream
          read();
      })
      .catch(error => {
          console.error(`An error occurred: ${error}`);
      });
  ```
</CodeGroup>

### Response Body

The streaming response is as follows:

```text theme={null}
ChatFly is an AI-powered platform that specializes in building chatbots. It offers a range of products and services to empower businesses in various sectors, including teaching, education, knowledge management, and customer support. With ChatFly, you can create your own chatbot using your data, without the need for coding. Our AI technology enables faster response times, reducing resolution times by an average of 37%. Additionally, ChatFly can act as tier 1 support, answering 39% of inquiries on its own. Implementation is quick and easy, taking only 57 seconds to install. We offer flexible pricing based on usage, with no annual contracts or price per user. Our chatbot seamlessly integrates with your favorite tools, making it effortless for teams and visitors to interact with it.
```

* string (string): A string of the response.

Result with Python, equivalent to JavaScript and Curl:

<img src="https://mintcdn.com/chatfly/68HzF9gC0Zu9PgZd/images/streaming-response.gif?s=e9cbe16ecc752b112eea65a011fcf193" alt="response streaming" width="1408" height="298" data-path="images/streaming-response.gif" />