create_llm
Creates a new LLM configuration to power AI agents, Knowledge AI, and generative features. Requires a connection with provider credentials. Set dryRun=false to create.
Instructions
Creates a new Cognigy.AI large language model configuration. LLMs power Knowledge AI, AI Agents, and generative features. Requires a connection with provider credentials. MUTATING: Set dryRun=false to create.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"projectId": "<projectId>",
"name": "<name>",
"provider": "<provider>",
"modelType": "<modelType>",
"connectionId": "<connectionId>"
},
"name": "create_llm"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Name for the LLM configuration | |
| dryRun | No | If true (default), validates without creating. Set to false to actually create. | |
| provider | Yes | The LLM provider | |
| isDefault | No | Set as the default LLM for the project | |
| modelType | Yes | The model type (e.g., 'gpt-4o', 'claude-3-opus-20240229', 'gemini-2.0-flash') | |
| projectId | Yes | The project ID to create the LLM in | |
| modelGroup | No | Model group: 'chat' for conversational, 'completion' for text generation, 'embedding' for embeddings | |
| description | No | Description of the LLM's purpose | |
| connectionId | Yes | The connection ID containing the provider credentials | |
| providerConfig | No | Provider-specific configuration (e.g., resourceName, deploymentName for Azure) |