add inference client

utils/oneclick.py

@@ -5,9 +5,16 @@ from .responseparser import PatientDataExtractor
 from .pdfutils import PDFGenerator
 import logging
 import json
+from huggingface_hub import InferenceClient
 
 logger = logging.getLogger(__name__)
 
+HF_TOKEN = os.getenv("HF_TOKEN")
+if not HF_TOKEN:
+    raise ValueError("HF_TOKEN environment variable not set.")
+client = InferenceClient(api_key=HF_TOKEN)
+MODEL_NAME = "meta-llama/Llama-3.3-70B-Instruct"
+
 def generate_ai_discharge_summary(patient_dict: Dict[str, str], client) -> Optional[str]:
     """Generate a discharge summary using AI based on extracted patient data."""
     try:
@@ -27,7 +34,7 @@ def generate_ai_discharge_summary(patient_dict: Dict[str, str], client) -> Optio
         ]
 
         stream = client.chat.completions.create(
-            model="grok-3",
+            model=MODEL_NAME,
             messages=messages,
             temperature=0.4,
             max_tokens=3584,