Update app.py

app.py

@@ -6,6 +6,12 @@ import time
 #import pandas as pd 
 global Modelfile  # Declare Modelfile as a global variable
 
+from llama_cpp import Llama
+
+llm = Llama.from_pretrained(
+	repo_id="alibidaran/LLAMA3.2-Virtual_doctor_GGUF",
+	filename="unsloth.Q8_0.gguf",
+)
 
 #def Generate_report(history,model_flags):
    # data={'steps':model_flags,
@@ -18,14 +24,13 @@ def user(user_message,history):
     return "", history+[{'role': 'user', 'content':user_message}]
 def respond(history):
     text=f"<s> ###Human: {history[-1]['content']} ###Asistant: "
-    response=ollama.generate(
-    model='hf.co/alibidaran/LLAMA3.2-Virtual_doctor_GGUF:latest',
-    prompt=text,
-    stream=False,
-)
-    print(response['response'])
+    response=llm(text,
+                max_tokens=512,
+            	echo=True)
+    response=response['choice'][0]['text']
+    print(response)
     history.append({'role':'assistant','content':""})
-    for character in response['response']:
+    for character in response:
         history[-1]['content']+=character
         time.sleep(0.02)
         yield history