​
Features

  • LlamaIndex Integration: Built using LlamaIndex’s powerful agent framework
  • Custom Tools: Example implementation of custom function tools
  • ReAct Agent: Demonstrates LlamaIndex’s ReAct agent pattern
  • Practical Example: Task management assistant with real-world use cases
  • Easy to Extend: Well-structured code for adding your own tools and functionality

​
References and Acknowledgements

​
Tech Stack

  • Agno framework for AI agent development
  • Nebius AI’s for running LLMs. We are using Qwen/Qwen3-30B-A3B reasoning model
  • HackerNews Tool from Agno

​
Prerequisites

​
Setup

  1. Get the code: 
    git   clone    https://github.com/nebius/ai-studio-cookbook/
cd    agents/llamaindex-task-timer
  2. Install dependencies:
    using uv:     
    # create a venv and install dependencies
uv  sync
    or install using python pip: 
    pip install -r requirements.txt
  3. Create .env file in the project root and add your Nebius API key: 
    cp env.example .env

    NEBIUS_API_KEY=your_api_key_here

​
Running the Agent

Using uv: 
uv  sync
uv  run   python agent.py
Using python pip: 
python agent.py
The agent will start with a welcome message and show available capabilities. You can interact with it by typing your questions or commands.

​
Example Implementation

This starter implements a Task Management Assistant with the following capabilities:
  • Duration Analysis: Calculate time durations between tasks
  • Task Estimation: Estimate completion times for multiple tasks
  • Productivity Tracking: Calculate and analyze productivity rates
Example queries:
  • “If I worked from 09:00 to 17:00 and completed 8 tasks, what was my productivity rate?”
  • “How long will it take to complete 3 tasks that each take 45 minutes?”
  • “Calculate the duration between 09:00 and 17:00”

​
Extending the Agent

To add your own functionality:
  1. Create new function tools using FunctionTool.from_defaults()
  2. Add your tools to the agent’s tool list
  3. Implement your custom logic in the functions