Update app.py

app.py

@@ -11,7 +11,7 @@ from auditqa.sample_questions import QUESTIONS
 from auditqa.reports import files, report_list, new_files, new_report_list
 from auditqa.process_chunks import load_chunks, getconfig, get_local_qdrant, load_new_chunks
 from auditqa.retriever import get_context
-from auditqa.reader import nvidia_client, dedicated_endpoint
+from auditqa.reader import nvidia_client, dedicated_endpoint, serverless_api
 from auditqa.utils import make_html_source, parse_output_llm_with_sources, save_logs, get_message_template, get_client_location, get_client_ip, get_platform_info
 from dotenv import load_dotenv
 load_dotenv()
@@ -242,7 +242,7 @@ async def chat(query,history,sources,reports,subtype,year, client_ip=None, sessi
     #        yield update
 
     else:
-        chat_model = dedicated_endpoint() # TESTING: ADAPTED FOR HF INFERENCE API (needs to be reverted for production version)
+        chat_model = serverless_api() # TESTING: ADAPTED FOR HF INFERENCE API (needs to be reverted for production version)
         async def process_stream():
             nonlocal answer_yet
             try: