Update app.py

app.py

@@ -17,7 +17,15 @@ class GenModel(BaseModel):
     mirostat_mode: int=2
     mirostat_tau: float=4.0
     mirostat_eta: float=1.1
-    
+
+class ChatModel(BaseModel):
+    question: list
+    system: str = "You are a helpful medical AI chat assistant. Help as much as you can.Also continuously ask for possible symptoms in order to atat a conclusive ailment or sickness and possible solutions.Remember, response in English."
+    temperature: float = 0.8
+    seed: int = 101
+    mirostat_mode: int=2
+    mirostat_tau: float=4.0
+    mirostat_eta: float=1.1
 llm_chat = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
@@ -66,15 +74,15 @@ def health():
     
 # Chat Completion API
 @app.post("/chat/")
-async def chat(gen:GenModel):
+async def chat(chatm:ChatModel):
     try:
         messages=[
-                {"role": "assistant", "content": gen.system},
-            **gen.question
+                {"role": "assistant", "content": chatm.system},
+            **chatm.question
             ]
         st = time()
         
-        messages.append({"role": "user", "content": gen.question})
+        messages.append({"role": "user", "content": chatm.question})
         output = llm_chat.create_chat_completion(
             messages = messages,
             temperature=gen.temperature,