Spaces:
Runtime error
Runtime error
File size: 1,816 Bytes
1a0b19c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 | import os
from typing import Any, Dict, List
import requests
HF_TOKEN = os.getenv("HF_TOKEN")
HF_TEXT_MODEL = os.getenv("HF_TEXT_MODEL", "microsoft/Phi-3.5-mini-instruct")
HF_INFERENCE_URL = os.getenv(
"HF_INFERENCE_URL",
f"https://api-inference.huggingface.co/models/{HF_TEXT_MODEL}",
)
if not HF_TOKEN:
raise RuntimeError("HF_TOKEN nao definido.")
def _messages_to_prompt(messages: List[Dict[str, str]]) -> str:
lines: List[str] = []
for m in messages:
role = m.get("role", "user").upper()
content = m.get("content", "")
lines.append(f"[{role}]\n{content}")
lines.append("[ASSISTANT]\n")
return "\n\n".join(lines)
def call_hf(messages: List[Dict[str, str]], max_tokens: int = 500, temperature: float = 0.2) -> str:
prompt = _messages_to_prompt(messages)
headers = {
"Authorization": f"Bearer {HF_TOKEN}",
"Content-Type": "application/json",
}
payload: Dict[str, Any] = {
"inputs": prompt,
"parameters": {
"max_new_tokens": max_tokens,
"temperature": temperature,
"return_full_text": False,
},
}
response = requests.post(HF_INFERENCE_URL, headers=headers, json=payload, timeout=120)
response.raise_for_status()
data = response.json()
# Typical formats from HF Inference API
if isinstance(data, list) and data and isinstance(data[0], dict):
if "generated_text" in data[0]:
return str(data[0]["generated_text"]).strip()
if isinstance(data, dict):
if "generated_text" in data:
return str(data["generated_text"]).strip()
if "error" in data:
raise RuntimeError(f"HF inference error: {data['error']}")
raise RuntimeError(f"HF inference response format unexpected: {data}")
|