Skip to content

README.md

Latest commit

 

History

History
87 lines (63 loc) · 2.73 KB

README.md

File metadata and controls

87 lines (63 loc) · 2.73 KB

Google Agent Development Kit (ADK) Example

Complexity: 🟢 Beginner

A minimal example using Agent Development Kit showcasing a simple weather and time agent that can call multiple tools.

Installation and Setup

If you have not already done so, follow the instructions in the Install Guide to create the development environment and install NeMo Agent Toolkit.

Install this Workflow

From the root directory of the NeMo Agent Toolkit repository, run the following command:

uv pip install -e examples/frameworks/adk_demo

Set up API keys

If you have not already done so, follow the Obtaining API Keys instructions to obtain an NVIDIA API key. You need to set your NVIDIA API key as an environment variable to access NVIDIA AI services:

export NVIDIA_API_KEY=<YOUR_API_KEY>

Optionally, if you would prefer to run with an OpenAI Key:

export OPENAI_API_KEY=<YOUR_API_KEY>

Run the Workflow

Run the workflow with the nat run command:

nat run --config_file examples/frameworks/adk_demo/configs/config.yml --input "What is the weather and time in New York today?"

Optionally if you would prefer to run with an OpenAI model:

nat run --config_file examples/frameworks/adk_demo/configs/config_oai.yml --input "What is the weather and time in New York today?"

Expected Output

<snipped for brevity>

Configuration Summary:
--------------------
Workflow Type: adk
Number of Functions: 2
Number of Function Groups: 0
Number of LLMs: 1
Number of Embedders: 0
Number of Memory: 0
Number of Object Stores: 0
Number of Retrievers: 0
Number of TTC Strategies: 0
Number of Authentication Providers: 0

<snipped for brevity>

--------------------------------------------------
Workflow Result:
['Here’s the latest for New York:\n- Weather: Sunny, around 25°C (77°F)\n- Time: 2025-09-25 12:27:26 EDT (UTC-4)']
--------------------------------------------------