Update app.py

app.py

@@ -7,7 +7,7 @@ import asyncio
 import os
 import json
 
-ENDPOINT_URL = "https://xzup8268xrmmxcma.us-east-1.aws.endpoints.huggingface.cloud"
+ENDPOINT_URL = "https://xzup8268xrmmxcma.us-east-1.aws.endpoints.huggingface.cloud/invocations"
 hf_token = os.getenv("HF_TOKEN")
 
 asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
@@ -33,21 +33,17 @@ def generate(prompt, history, temperature=0.1, max_new_tokens=2048):
     
     formatted_prompt = format_prompt(prompt, history)
     
-    headers = {
-        "Authorization": f"Bearer {hf_token}",
-        "Content-Type": "application/json"
-    }
-    
+    headers = {"Authorization": f"Bearer {hf_token}", "Content-Type": "application/json"}
     payload = {
-        "model": "meta-llama/Llama-3.1-8B-Instruct",
-        "messages": [{"role": "user", "content": formatted_prompt}],
-        "temperature": temperature,
-        "max_tokens": max_new_tokens,
-        "stream": False
+        "inputs": prompt,
+        "parameters": {
+            "temperature": temperature,
+            "max_new_tokens": max_new_tokens
+        }
     }
 
     try:
-        response = requests.post(f"{ENDPOINT_URL}/v1/chat/completions", headers=headers, json=payload)
+        response = requests.post(ENDPOINT_URL, headers=headers, json=payload)
         
         if response.status_code == 200:
             result = response.json()