import os
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

# Safe writable cache dirs in Hugging Face Spaces
os.environ["TRANSFORMERS_CACHE"] = "/tmp/hf_cache"
os.environ["HF_HOME"] = "/tmp/hf_home"
os.environ["HF_HUB_CACHE"] = "/tmp/hf_hub"



HF_TOKEN = os.getenv("HF_TOKEN")
MODEL_ID = "TypicaAI/magbert-ner"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, token=HF_TOKEN)
model = AutoModelForTokenClassification.from_pretrained(MODEL_ID, token=HF_TOKEN)


ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="first")