Sigo o tutorial do Azure sobre como ajustar o GPT. Sigo a fase de implantação.
Código:
# Deploy fine-tuned model
import json
import requests
token = '[redacted]'
subscription = '[redacted]'
resource_group = "[redacted]"
resource_name = "[redacted]"
model_deployment_name = "gpt-4o-mini-2024-07-18-ft" # Custom deployment name you chose for your fine-tuning model
deploy_params = {'api-version': "2023-05-01"}
deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}
deploy_data = {
"sku": {"name": "standard", "capacity": 1},
"properties": {
"model": {
"format": "OpenAI",
"name": "gpt-4o-mini-2024-07-18.ft-[redacted]", #retrieve this value from the previous call, it will look like gpt-4o-mini-2024-07-18.ft-[redacted]
"version": "1"
}
}
}
deploy_data = json.dumps(deploy_data)
request_url = f'https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}'
print('Creating a new deployment...')
r = requests.put(request_url, params=deploy_params, headers=deploy_headers, data=deploy_data)
print(r)
print(r.reason)
print(r.json())
Isso funciona bem, mas o token expira rapidamente. Isso me incomoda. Como posso implantar um modelo GPT ajustado no Azure via Python sem usar um token (por exemplo, usando uma chave de endpoint)?