Update app.py

app.py

@@ -11,7 +11,7 @@ model.eval()
 with open('../system.prompt', 'r', encoding='utf-8') as f:
     prompt = f.read()
 
-@app.post("/echo")
+@app.post("/request")
 async def echo():
     data = await request.get_json()
     if data.get("max_tokens") != None and data.get("max_tokens") > 500: data['max_tokens'] = 500
@@ -23,4 +23,8 @@ async def echo():
         do_sample=random.choice([True, False]), temperature=float(random.randint(7,20)) / 10.0,
         max_new_tokens=data.get("max_tokens") or random.randomint(200,500), 
         eos_token_id=tokenizer.eos_token_id, return_full_text = False)
-    return {"output": tokenizer.decode(output_ids[0], skip_special_tokens=True)}
+    return {"output": tokenizer.decode(output_ids[0], skip_special_tokens=True)}
+
+@app.get("/")
+async def get():
+    return "better to run it on own container"