Update main.py

main.py

@@ -11,6 +11,7 @@ import socket
 import time
 from enum import Enum
 import random
+import asyncio
 
 #--------------------------------------------------- Definizione Server FAST API ------------------------------------------------------
 app = FastAPI()
@@ -35,7 +36,8 @@ class PostSpazio(BaseModel):
     nomeSpazio: str
     input: str = '' 
     api_name: str = "/chat"
-    
+
+
 #--------------------------------------------------- Generazione TESTO ------------------------------------------------------
 @app.post("/Genera")
 def read_root(request: Request, input_data: InputData):
@@ -74,6 +76,36 @@ def format_prompt(message, history):
     prompt += f"[{now}] [INST] {message} [/INST]"
     return prompt
 
+#--------------------------------------------------- Generazione TESTO Asincrono  ------------------------------------------------------
+@app.post("/GeneraAsincrono")
+def read_root_async(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 = [] 
+    async with aiohttp.ClientSession() as session:
+        tasks = [generate_async(input_data.input, history, input_data.temperature, input_data.max_new_tokens, input_data.top_p, input_data.repetition_penalty) for _ in range(10)]
+        responses = await asyncio.gather(*tasks)
+    return {"responses": responses}
+
+async def generate_async(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)
+    output = client.text_generation(formatted_prompt, **generate_kwargs, stream=False, details=False)
+    return output
     
 #--------------------------------------------------- Generazione IMMAGINE ------------------------------------------------------
 style_image = {