Update generate endpoint

main.py

@@ -11,48 +11,33 @@ app = FastAPI()
 
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-class Item(BaseModel):
-    prompt: str
-    history: list
-    system_prompt: str
-    temperature: float = 0.0
-    max_new_tokens: int = 1048
-    top_p: float = 0.15
-    repetition_penalty: float = 1.0
 
 class EchoMessage(BaseModel):
     message: str
 
-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
+class Item(BaseModel):
+    prompt: str
+
 
 def generate(item: Item):
-    temperature = float(item.temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(item.top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=item.max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=item.repetition_penalty,
-        do_sample=True,
-        seed=42,
+    generator = pipeline("text-generation", model=model_name)
+
+    # Your input prompt
+    prompt = item.prompt
+
+    # Generate text
+    generated_texts = generator(
+        prompt,
+        max_length=50,  # Maximum length of the generated text
+        num_return_sequences=1,  # Number of different sequences to generate
+        temperature=0.8,  # Controls the randomness of the output
+        top_k=50,        # Limits the number of top tokens to consider
+        top_p=0.95,      # Nucleus sampling parameter
+        do_sample=True   # Enable sampling for non-deterministic output
     )
 
-    formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}", item.history)
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
+    return generated_texts
 
-    for response in stream:
-        output += response.token.text
-    return output
 
 @app.post("/generate/")
 async def generate_text(item: Item):