Skip to main content

Create and Deploy Agent

Once you Test your Agent configuration and validate it, you can proceed to deploy the agent. The deployment process involves creating an agent using the YAML configuration file and deploying it to your Organization or Agent Store.

With this SVAHNAR API, you can create and deploy agents using the YAML configuration file. The API provides a simple and efficient way to manage your agents, allowing you to focus on building and deploying them without worrying about the underlying infrastructure.

The API supports various features, including agent creation, deployment, and validation. You can easily create agents with different configurations and deploy them to your Organization or Agent Store.

Validate Agent Configuration​

Before you upload please validate the Agent configuration using the validate API. This will help you identify any potential issues in the agent's configuration and provide feedback on what needs to be corrected. Additionally, you can refer to the Validate Agent Configuration documentation for more details on the validation process.

Deploy Agent​

To deploy an agent, you need to provide the YAML configuration file. The API will handle the deployment process and ensure that your agent is up and running. You can also specify the deployment type, such as organization or agent_store, to control where the agent will be deployed.

YAML Configuration File​

To start creating YAML configuration file, you can refer to the Agent Configuration documentation for more details on the configuration options available.

Here's a simple example to deploy an agent:​

Python
from svahnar import Svahnar
from pathlib import Path

client = Svahnar()

agent = client.agents.create(
    name="Agent Name",
    description="Description",
    deploy_to="organization", # "Organization" or "AgentStore"
    yaml_file=Path("agent.yaml"),
)
    
print(agent)

Parameters​

  • name: The name of the agent you want to create.
  • description: A brief description of the agent's purpose or functionality.
  • deploy_to: The deployment type, either Organization or AgentStore. This determines where the agent will be hosted.
    • Organization: The agent will be deployed to your organization, making it accessible to your team members.
    • AgentStore: The agent will be deployed to the agent store, making it publicly available for others to use.
  • yaml_file: The path to the YAML configuration file that defines the agent's behavior and settings.

You will receive a response containing the details of the deployed agent, including its ID, and any other relevant information.

Response​

This response will help you verify that the agent has been successfully deployed and is ready for use.

json
{
    "message": "Your agent 'Agent Name' has been successfully created and hosted. You can access it with the ID - 8bd57aa1-a982-49ba-b6f5-91e84e5dfe9c."
}

Please store this Agent ID securely, as it will be required for future interactions with the agent. You can use this Agent ID to run and manage the agent, including updating its configuration or deleting it if necessary.