Triton AI Docs
Endpoints

Classify private text

Run Privacy Filter as token classification. Returns token scores; redacted text requires a separate decoding step.

For the workflow and examples, read the guide.

POST/vllm/pooling

Authorization

bearerAuth
AuthorizationBearer <token>

Your Triton AI Developer API key.

In: header

Request Body

application/json

Response Body

application/json

import jsonimport osfrom urllib.request import Request, urlopenrequest = Request(    "https://tritonai-api.ucsd.edu/vllm/pooling",    headers={        "Authorization": f"Bearer {os.environ['TRITONAI_API_KEY']}",        "Content-Type": "application/json",    },    data=json.dumps({        "model": "openai-privacy-filter",        "input": "Contact Jamie Example at jamie@example.com or 202-555-0142.",        "task": "token_classify",    }).encode("utf-8"),)with urlopen(request, timeout=60) as response:    result = json.load(response)scores = result["data"][0]["data"]print(f"Tokens: {len(scores)}")print(f"Classes per token: {len(scores[0])}")