README.md

AI-task-manager

This project is an example of a LangChain agent for task management. The agent can add tasks, search for tasks based on their status, and delete tasks. This example does not use a real database, only simulated data for demonstration purposes.

Setup

1. Clone the repository.
2. Create a .env file in the root directory with your OpenAI API key:

   OPENAI_API_KEY=your_openai_api_key_here
   

3. Install the required dependencies:

   pip install -r requirements.txt
   

4. Run the FastAPI server:

   uvicorn main:app --reload
   

Usage

The agent provides three main functions:

• add_task: Adds a new task with a description and due date.
• search_tasks: Searches for tasks with a specified status (e.g., pending, completed).
• delete_task: Deletes a task.

Interacting with the Agent

Interaction with the agent is done through the /chat route. Send a POST request to this route with the following body:

{
  "text": "Request content here"
}

Example Request with curl

To add a new task, you can send:

curl -X POST "http://localhost:8000/chat" -H "Content-Type: application/json" -d '{"text": "I need to buy bread tomorrow"}'

The agent will invoke a function that will create the task and return a response like this:

{
  "status": "success",
  "operation": "add",
  "task_description": "buy bread",
  "due_date": "2024-07-15"
}

The agent will then return a natural language response to the user, such as:

{
  "response": "I have added your task to buy bread tomorrow. If there is anything else I can help with, please let me know."
}

Interaction Example

You can interact with the agent informally. For example, to add a task, you can send a text like:

{
  "text": "I need to buy bread tomorrow"
}

Or to search for pending tasks, you can send:

{
  "text": "What are my pending tasks?"
}

And to delete a task, you can send:

{
  "text": "Delete the task to buy bread"
}

The agent will process the request and return the appropriate response in natural language.