Example Usage
Note
Before exploring example usage in the notebooks/
directory, ensure you have specified the necessary API tokens in your environment.
-
Log in to your OpenAI account at the OpenAI Platform website. If you don't have an account, you'll need to create one first.
-
Navigate to the API keys section. You can find this by clicking on your profile icon in the top-right corner and selecting "API keys."
-
Click the + Create new secret key button.
-
Give your key a descriptive name (e.g., "ChemGraph").
-
Click Create secret key. A new key will be generated.
-
Copy the key and save it in a secure location. You will not be able to see it again after this step.
-
Set the key in your environment using the command provided in the instructions:
- Restart your terminal or IDE to ensure the environment variable is loaded.
-
Sign up or log in to your Anthropic account at the Anthropic console.
-
In the left-hand navigation menu, select API Keys.
-
Click on the option to create a new API key.
-
Provide a name for your API key (e.g., "ChemGraph").
-
Click Create Key again.
-
Copy the generated key and store it securely, as you may not be able to view it again.
-
Set the key in your environment using the command provided in the instructions:
- Restart your terminal or IDE to ensure the environment variable is loaded.
-
Go to the Google AI Studio website at Google AI Studio and sign in with your Google account.
-
In the left-hand menu, select Get API key.
-
Click the Create API key in new project button. A new key will be instantly generated.
-
Copy the API key by clicking the copy icon next to it.
-
Set the key as an environment variable:
- Restart your terminal or IDE to ensure the environment variable is loaded.
Explore Example Notebooks
Navigate to the notebooks/
directory to explore various example notebooks demonstrating different capabilities of ChemGraph.
-
Single-Agent System with MACE: This notebook demonstrates how a single agent can utilize multiple tools with MACE/xTB support.
-
Single-Agent System with UMA: This notebook demonstrates how a single agent can utilize multiple tools with UMA support.
-
Multi-Agent System: This notebook demonstrates a multi-agent setup where different agents (Planner, Executor and Aggregator) handle various tasks exemplifying the collaborative potential of ChemGraph.
-
Single-Agent System with gRASPA: This notebook provides a sample guide on executing a gRASPA simulation using a single agent. For gRASPA-related installation instructions, visit the gRASPA GitHub repository. The notebook's functionality has been validated on a single compute node at ALCF Polaris.