> ## 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.

# Create Bot

> In this guide, we will walk through the process of manage a chatbot using an API

## Prerequisites

Before you begin, make sure you have the following:

1. ChatFly account to get access token.
2. A development environment or tool for making HTTP requests, such as Curl or a programming language like Python.

## Create Bot

### API Endpoint

The API endpoint for creating a chatbot is:

```text theme={null}
https://backend.chatfly.co/api/bot
```

### Request Body

To create a chatbot, you need to send a POST request to the API endpoint with a JSON request body. Here’s an example request body:

```json theme={null}
{
  "user_id": "User_id of Your Account",
  "bot_name": "Your Chatbot's Name",
  "case_study": "Your Case Study",
  "is_visibility": true,
  "domain": [
    "Your domain"
  ],
  "collect_customer_info": {},
  "rules": [
    "Your rules"
  ],
  "gpt_model_name": "gpt-3.5-turbo",
  "temperature": 0,
  "custom_prompt": "A sample prompt for your chatbot.",
  "bot_tone_type": 0,
  "custom_error_message": "Your custom error message"
}
```

* bot\_name (string): Your Chatbot's Name

* case\_study (string, optional): Your Case Study.

  Options available: `Customer Support`, `Knowledge Management`, `Teaching Education`, `Lecture Assistant`, `Toeic Learner Assistant`.

* is\_visibility (string, optional): Set the visibility of your chatbot.

  Options available: `private`, `public`.

* domain (list(string)): website domain where you want to embed the bot.

* collect\_customer\_info (list(string)): The information you want to collect from users.

* rules (list(string)): The rule you want the bot to express when responding to messages.

* gpt\_model\_name (string, optional): Specify the model you want to use. In this example, we’re using `gpt-3.5-turbo`.

  Options available `gpt-3.5-turbo`, `gpt-3.5-turbo-16k`, `gpt-4`

* temperature (float, optional): You can adjust the temperature parameter for response randomness. A value of `0` makes responses deterministic, while higher values increase randomness.

  Options are values as a float between `0` and `1`

* custom\_prompt (string, optional): You can provide an initial prompt for your chatbot.

* bot\_tone\_type (int): Bot tone type.

* custom\_error\_message (string): Your custom error message.

### Example Request

Here’re example command sto create a chatbot using the ChatFly API:

<Warning>
  Replace `token` with your token access.
</Warning>

<CodeGroup>
  ```json curl theme={null}
  curl -X POST "https://backend.chatfly.co/api/bot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer token" \
  -d '{
    "user_id": "xxxx-xxxx-xxxx-xxxx",
    "bot_name": "ChatbotName",
    "case_study": "CaseStudy",
    "is_visibility": true,
    "domain": [
      "Your domain"
    ],
    "collect_customer_info": {},
    "rules": [
      "Your rules"
    ],
    "gpt_model_name": "gpt-3.5-turbo",
    "temperature": 0,
    "custom_prompt": "A sample prompt for your chatbot.",
    "bot_tone_type": 0,
    "custom_error_message": "Your custom error message"
  }'
  ```

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

  url = 'https://backend.chatfly.co/api/bot'
  headers = {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer token'
  }

  data = {
    "user_id": "xxxx-xxxx-xxxx-xxxx",
    "bot_name": "ChatbotName",
    "case_study": "CaseStudy",
    "is_visibility": true,
    "domain": [
      "Your domain"
    ],
    "collect_customer_info": {},
    "rules": [
      "Your rules"
    ],
    "gpt_model_name": "gpt-3.5-turbo",
    "temperature": 0,
    "custom_prompt": "A sample prompt for your chatbot.",
    "bot_tone_type": 0,
    "custom_error_message": "Your custom error message"
  }

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

  if response.status_code == 200:
      print("Request successful!")
      print(response.json())
  else:
      print("Request failed with status code:", response.status_code)
      print(response.text)
  ```

  ```json javascript theme={null}
  const url = 'https://backend.chatfly.co/api/bot';
  const headers = {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer your_actual_token_here'
  };

  const data = {
      "user_id": "xxxx-xxxx-xxxx-xxxx",
      "bot_name": "ChatbotName",
      "case_study": "CaseStudy",
      "is_visibility": true,
      "domain": [
          "Your domain"
      ],
      "collect_customer_info": {},
      "rules": [
          "Your rules"
      ],
      "gpt_model_name": "gpt-3.5-turbo",
      "temperature": 0,
      "custom_prompt": "A sample prompt for your chatbot.",
      "bot_tone_type": 0,
      "custom_error_message": "Your custom error message"
  };

  fetch(url, {
      method: 'POST',
      headers: headers,
      body: JSON.stringify(data)
  })
      .then(response => {
          if (response.status === 200) {
              return response.json();
          } else {
              throw new Error(`Request failed with status code: ${response.status}`);
          }
      })
      .then(data => {
          console.log("Request successful!");
          console.log(data);
      })
      .catch(error => {
          console.error(error);
      });
  ```
</CodeGroup>

## Bot Information

### API Endpoint

The API endpoint for get bot information is:

```text theme={null}
https://backend.chatfly.co/api/bot/information
```

### Request Body

To get bot information, you need to send a Get request to the API endpoint with a Params request. Here’s an example params request:

```json theme={null}
{
  "bot_id": "xxxx-xxxx-xxxx-xxxx"
}
```

* bot\_id (string): id of your bot.

### Example Request

Here’re example command sto get bot information using the ChatFly API:

<Warning>
  Replace `token` with your token access.
</Warning>

<CodeGroup>
  ```json curl theme={null}
  curl -X GET "https://backend.chatfly.co/api/bot/information?bot_id=xxxx-xxxx-xxxx-xxxx"
  -H "Authorization: Bearer token"
  -H "Content-Type: application/json"

  ```

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

  url = 'https://backend.chatfly.co/api/bot/information'
  headers = {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer token'
  }

  data = {
     "bot_id": "xxxx-xxxx-xxxx-xxxx"
  }

  response = requests.get(url, headers=headers, params=data)

  if response.status_code == 200:
      print("Request successful!")
      print(response.json())
  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/bot/information';
  const headers = {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer token'
  };

  const params = {
      bot_id: 'xxxx-xxxx-xxxx-xxxx'
  };

  axios.get(url, { headers, params })
      .then(response => {
          if (response.status === 200) {
              console.log('Request successful!');
              console.log(response.data);
          } else {
              console.log('Request failed with status code:', response.status);
              console.log(response.data);
          }
      })
      .catch(error => {
          console.error('An error occurred:', error);
      });

  ```
</CodeGroup>

### Response Body

The bot's information is responded:

```json theme={null}
{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "bot_name": "Your Chatbot's Name",
  "case_study": "Your Case Study",
  "is_visibility": true,
  "domain": [
    "Your domain"
  ],
  "collect_customer_info": {},
  "rules": [
    "Your rules"
  ],
  "gpt_model_name": "gpt-3.5-turbo",
  "temperature": 0,
  "custom_prompt": "A sample prompt for your chatbot.",
  "bot_tone_type": 0,
  "custom_error_message": "Your custom error message",
  "num_message_left": 0,
  "created_at": "YYYY-MM-DD",
  "updated_at": "YYYY-MM-DD"
}
```

Information about response params in `Request Body (Create bot)`.