create_integration
Set up connections to AI providers like OpenAI, Anthropic, Azure OpenAI, or AWS Bedrock by configuring API keys and provider-specific settings.
Instructions
Create a new integration with an AI provider (e.g., OpenAI, Anthropic, Azure OpenAI, AWS Bedrock)
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Human-readable name for the integration | |
| ai_provider_id | Yes | ID of the AI provider (e.g., 'openai', 'anthropic', 'azure-openai', 'aws-bedrock', 'vertex-ai') | |
| slug | No | URL-friendly identifier (auto-generated from name if not provided) | |
| key | No | API key for the provider (if required) | |
| description | No | Optional description of the integration | |
| workspace_id | No | Workspace ID for workspace-scoped integrations | |
| api_version | No | API version (for Azure OpenAI) | |
| resource_name | No | Resource name (for Azure OpenAI) | |
| deployment_name | No | Deployment name (for Azure OpenAI) | |
| aws_region | No | AWS region (for AWS Bedrock) | |
| aws_access_key_id | No | AWS access key ID (for AWS Bedrock) | |
| aws_secret_access_key | No | AWS secret access key (for AWS Bedrock) | |
| vertex_project_id | No | GCP project ID (for Vertex AI) | |
| vertex_region | No | GCP region (for Vertex AI) | |
| custom_host | No | Custom base URL for the provider |