Update main.py

main.py

@@ -7,20 +7,29 @@ client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 class InputData(BaseModel):
     input: str
+    temperature: float = 0.2
+    max_new_tokens: int = 30000
+    top_p: float = 0.95
+    repetition_penalty: float = 1.0
 
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
-
-@app.post("/Genera/")
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
+
+@app.post("/Genera")
 def read_root(request: Request, input_data: InputData):
     input_text = input_data.input
+    temperature = input_data.temperature
+    max_new_tokens = input_data.max_new_tokens
+    top_p = input_data.top_p
+    repetition_penalty = input_data.repetition_penalty
+
     history = []  # Puoi definire la history se necessario
-    generated_response = generate(input_text, history)
+    generated_response = generate(input_text, history, temperature, max_new_tokens, top_p, repetition_penalty)
     return {"response": generated_response}
 
 @app.get("/")