Update main.py

main.py

@@ -36,12 +36,7 @@ class InputData(BaseModel):
     top_p: float = 0.95
     repetition_penalty: float = 1.0
 
-class InputDataAsync(BaseModel):
-    input: str
-    temperature: float = 0.7
-    max_new_tokens: int = 30000
-    top_p: float = 0.95
-    repetition_penalty: float = 1.0
+class InputDataAsync(InputData):
     NumeroGenerazioni: int = 1
     StringaSplit: str = '********'
     
@@ -58,26 +53,25 @@ def read_root(request: Request, input_data: InputData):
     top_p = input_data.top_p
     repetition_penalty = input_data.repetition_penalty
     history = [] 
-    input_text = = f'''
-        {{
-            "input": {{
-                "role": "system",
-                "content": "{input_data.systemRole}", 
-                "style": "{input_data.systemStyle}", 
-                
+    input_text = f'''
+    {{
+        "input": {{
+            "role": "system",
+            "content": "{input_data.systemRole}", 
+            "style": "{input_data.systemStyle}"
+        }},
+        "messages": [
+            {{
+                "role": "instructions",
+                "content": {input_data.instruction}
             }},
-            "messages": [
-                {{
-                    "role": "instructions",
-                    "content": {input_data.instruction}
-                }},
-                {{
-                    "role": "user",
-                    "content": "{input_data.input}"
-                }}
-            ]
-        }}
-        '''    
+            {{
+                "role": "user",
+                "content": "{input_data.input}"
+            }}
+        ]
+    }}
+    '''
     generated_response = generate(input_text, history, temperature, max_new_tokens, top_p, repetition_penalty)
     return {"response": generated_response}