Train
trainTrain a new version of the model. Two steps: the first call changes nothing and returns what the run will use from the workspace's allowance plus a confirmation code; show that to the user, and only after they explicitly agree call again with that exact code. The user's yes is not the code. A code works once, for this model and these arguments, for 10 minutes.
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": {
"model_id": "<model_id>",
"model_type": "<model_type>"
},
"name": "train"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model_id | Yes | The model id, from list_models. | |
| model_type | Yes | classifier: Classifier Model (words only). ai_classifier: AI Classifier Model (reads meaning; for pictures, the AI Image Classifier Model). dedicated: Dedicated AI Model trained on the user's examples on a GPU (for pictures, the Dedicated AI Image Model); a model last trained in the workspace's own Amazon Bedrock retrains there, on the same connection and base model. byom: Your AI Model (bring your own model), the workspace's own AI platform asked with the user's examples, nothing trained (text only); retrains with the AI platform, model and settings of its last Your AI Model run, which is first chosen in the app. | |
| confirmation | No | The code from the first call, sent only after the user said yes. |