Update LLM Provider

Before You Begin

🔗 Use the GraphQL Playground to execute the mutations in this guide.

➡️ New to GraphQL? Learn how to navigate the Playground with our Playground Basics Guide.

Prerequisites

1. Authentication: Use a Service Account token.
2. Permissions: You must have permissions to manage AI providers in the organization.
3. Organization UUID: The UUID of the organization where the provider exists.
4. LLM Provider ID: The ID of the provider configuration you wish to update. You can get this ID from the llmProvidersByOrganization query.

Step 1: Execute the Mutation

This mutation allows you to modify an existing LLM provider's details, such as its name or its configuration settings.

mutation {
  updateLlmProvider(
    input: {
      id: "27"
      organizationUuid: "org-uuid-example"
      name: "OpenAI GPT-4o (Updated)"
      configuration: {
        provider: "openai"
        openai_api_key: "sk-your-new-secret-key"
        model_name: "gpt-4o"
      }
    }
  ) {
    llmProvider {
      id
      name
      configuration
    }
  }
}

Arguments

• id (ID, required): The ID of the LLM provider configuration to update.
• organizationUuid (String, required): The UUID of the target organization.
• configuration (JSON, required): An object containing the provider's new settings. All required configuration keys must be provided.
• name (String, optional): The new descriptive name for the provider configuration.

Response Fields

• llmProvider: The updated LLM provider object, containing:
  • id: The unique ID of the provider configuration.
  • name: The newly updated name.
  • configuration: The updated configuration details.

Example Response

{
  "data": {
    "updateLlmProvider": {
      "llmProvider": {
        "id": "27",
        "name": "OpenAI GPT-4o (Updated)",
        "configuration": {
          "provider": "openai",
          "model_name": "gpt-4o"
        }
      }
    }
  }
}

Additional Notes

• If the mutation fails due to an invalid id, incorrect organizationUuid, or lack of permissions, an error will be returned.
• When updating the configuration, the entire configuration object must be passed. The system does not perform a partial merge.
• For security, sensitive fields like openai_api_key are accepted in the input but will not be returned in the response.

This mutation provides a straightforward way to modify and maintain your LLM provider configurations.