Update main.py

main.py

@@ -1,7 +1,44 @@
 from fastapi import FastAPI
+from huggingface_hub import InferenceClient
 
 app = FastAPI()
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
+
+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.get("/")
 def read_root():
-    return {"Hello": "World!"}
+    user_input = "Come Stai?"  # Puoi passare l'input desiderato da qui
+    history = []  # Puoi definire la history se necessario
+    generated_response = next(generate(user_input, history))  # Ottieni la risposta generata
+    return {"response": generated_response}  # Restituisci la risposta generata come JSON
+
+def generate(prompt, history, temperature=0.2, max_new_tokens=30000, top_p=0.95, repetition_penalty=1.0):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+    formatted_prompt = format_prompt(prompt, history)
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        yield output
+    return output
+