Update main.py

main.py

@@ -15,6 +15,7 @@ llm = Llama(
 class Validation(BaseModel):
     user_prompt: str  # User's input prompt
     system_prompt: str  # System's guiding prompt
+    max_tokens: int
 
 # FastAPI application initialization
 app = FastAPI()
@@ -28,7 +29,7 @@ async def generate_response(item: Validation):
 { item.user_prompt }<|eot_id|> \n <|start_header_id|>assistant<|end_header_id|>"""
     
     # Call the Llama model to generate a response
-    output = llm(prompt, echo=True)  # Update parameters as needed
+    output = llm(prompt, max_tokens = item.max_tokens,echo=True)  # Update parameters as needed
     
     # Extract and return the text from the response
     return output['choices'][0]['text']