deploy_tmp/test_token.py

import os
from dotenv import load_dotenv
from huggingface_hub import InferenceClient, whoami

# Load .env explicitly
load_dotenv()
token = os.getenv("HUGGINGFACE_TOKEN")

print(f"Token from environment: {token}")

if not token:
    print("❌ No token found!")
    exit(1)

# 1. Check whoami (verifies validity)
try:
    user_info = whoami(token=token)
    print(f"✅ Token is valid for user: {user_info['name']}")
    print(f"   Org: {user_info.get('orgs', 'None')}")
except Exception as e:
    print(f"❌ Token validation failed (whoami): {e}")

# 2. Try simple inference with a generic model
client = InferenceClient(token=token)
model = "HuggingFaceH4/zephyr-7b-beta"

print(f"\nTesting Inference on {model}...")
try:
    messages = [{"role": "user", "content": "Hello!"}]
    response = client.chat_completion(messages=messages, model=model, max_tokens=10)
    print(f"✅ Inference success: {response.choices[0].message.content}")
except Exception as e:
    print(f"❌ Inference failed: {e}")