AI configuration
Last updated
Was this helpful?
Last updated
Was this helpful?
Some commands, such as assertWithAI and assertNoDiffWithAI, use generative AI models, which are not built directly in Maestro CLI. Therefore, to use such commands, additional configuration is required.
The default model is the latest GPT-4o.
Support for more models and providers is tracked in this issue.
To use these features, you must have an account on Robin, the official Maestro cloud platform. Make sure to create an account and retrieve your API key to set it up correctly by following this link:
To use this command, an API key for the LLM is required. With the latest changes, we have migrated hard-coded API calls and prompts to our cloud backend, allowing us to enhance these features dynamically without requiring new CLI releases. To set it, export the MAESTRO_CLOUD_API_KEY env var.