Skip to content

Latest commit

 

History

History
84 lines (57 loc) · 2.47 KB

README.MD

File metadata and controls

84 lines (57 loc) · 2.47 KB
Raw

Chatbot with OpenAI Assistants API & Function Calling

This project showcases a chatbot integrated with the OpenAI Assistants API, capable of engaging in conversations and executing specific actions based on user requests. One notable feature is its ability to send a webhook containing user details, such as name and phone number, when requested by the user. This functionality demonstrates the chatbot's potential in real-world applications, particularly in customer service and support scenarios where collecting user information is crucial.

The chatbot is built using Node.js and Express, with the OpenAI API providing the intelligence for natural language understanding and response generation. The webhook functionality is implemented using the fetch API, allowing the chatbot to communicate with external services. An OpenAI API key. You can get one by signing up at OpenAI.

Setting Up Your Project:

git clone https://github.com/RaheesAhmed/assistant_with_function_calling.git

GO to the Directory:

cd assistant_with_function_calling

Install Packages:

npm install

Create a .env file in the root of your project directory and add your OpenAI API key:

OPENAI_API_KEY=your_api_key_here

Replace your_api_key_here with your actual OpenAI API key.

The get_webhook.js File This file contains the function to send a webhook with user details.

The index.js File This file contains the main logic of the chatbot and the OpenAI assistant.

Endpoint The main endpoint for interacting with the chatbot is /chat.

Request Method POST Request URL yourdomain.com/chat Request Body The request body should be a JSON object containing the following fields:

question: The question to ask the chatbot. userDetails: An object containing user details. For example, { "name": "John Doe", "phoneNumber": "1234567890","date":"2022/12/31" }.

Example request body:

{"question":"I need human help","userDetails":{"name":"John Doe","phoneNumber":"1234567890"}}

Response The response will be a JSON object containing the following field:

response: The response from the chatbot. Example response:

{
  "response": "Please provide your name and phone number so we can assist you further."
}

Error Handling If an error occurs, the API will return a JSON object with an error field containing the error message.

Example error response:

{
  "error": "An error occurred while processing your request."
}

Google Calander:https://console.cloud.google.com/