Update app.py

app.py

@@ -18,7 +18,7 @@ OLLAMA_SERVICE_THREAD.start()
 
 print("Giving ollama serve a moment")
 time.sleep(10)
-
+subprocess.run("~/ollama run gemma2", shell=True)
 
 
 import copy
@@ -33,16 +33,6 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL_ID = "google/gemma-2-27b-it"
 MODEL_NAME = MODEL_ID.split("/")[-1]
 
-os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
-
-
-
-llm = Ollama(model="gemma2", request_timeout=60.0)
-
-
-def run_ollama():
-    subprocess.run("~/ollama pull gemma2", shell=True)
-
 TITLE = "<h1><center>Chatbox</center></h1>"
 
 DESCRIPTION = f"""
@@ -82,7 +72,7 @@ def stream_chat(message: str, history: list, temperature: float, context_window:
 
     print(f"Conversation is -\n{conversation}")
 
-
+    llm = Ollama(model="gemma2", request_timeout=60.0)
     resp = llm.chat(
         messages = messages,
         chat_history = conversation,