some changes

backend/src/inference.py

@@ -1,4 +1,5 @@
 import threading
+import ollama
 from stream import Stream
 
 
@@ -18,13 +19,15 @@ class Models:
     qwen3_8b = "lucataco/qwen3-vl-8b-instruct:39e893666996acf464cff75688ad49ac95ef54e9f1c688fbc677330acc478e11"
     qwen3_235b = "qwen/qwen3-235b-a22b-instruct-2507"
 
-async def ollama_chat_completion(app, messages, model, opts={}):
-    from ollama import AsyncClient
+async def ollama_list(app, messages, model, opts={}):
+    # TODO: test the output, and use this
+    return ollama.list()
 
+async def ollama_chat_completion(app, messages, model, opts={}):
     content_stream = Stream(app)
 
     print("START OLLAMA INFERENCE")
-    stream_response = await AsyncClient().chat(
+    stream_response = await ollama.AsyncClient().chat(
         model=model,
         messages=[{'role': msg.role, 'content': msg.content} for msg in messages],
         stream=True,