serving/typed_decisions.py

"""One context, three typed questions using Pivot's bundled runtime."""
import torch
from transformers import AutoModel, AutoTokenizer

repo = "Q1z/Pivot"
tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModel.from_pretrained(repo, trust_remote_code=True, dtype=torch.float32).eval()
response = model.decide(
    tokenizer,
    "Customer dispute: invoice 120 vs PO 100, age=3d, region=US",
    [
        {"id": "route", "primitive": "choice",
         "options": ["billing", "tech", "sales"]},
        {"id": "approve", "primitive": "noul",
         "options": ["true", "false"]},
        {"id": "severity", "primitive": "score",
         "options": ["0", "1", "2", "3"]},
    ],
)
print(response)