Update app.py

app.py

@@ -1,9 +1,7 @@
 import gradio as gr
-from gradio_webrtc import WebRTC, ReplyOnStopWords, AdditionalOutputs, audio_to_bytes, get_twilio_turn_credentials
+from gradio_webrtc import WebRTC, ReplyOnStopWords, AdditionalOutputs, audio_to_bytes
 import numpy as np
-import os
 import base64
-import openai
 import re
 from groq import Groq
 
@@ -12,7 +10,7 @@ load_dotenv()
 
 spinner_html = open("spinner.html").read()
 
-rtc_configuration = get_twilio_turn_credentials()
+rtc_configuration = None
 
 print("rtc_configuration", rtc_configuration)
 
@@ -33,14 +31,9 @@ logger = logging.getLogger("gradio_webrtc")
 logger.setLevel(logging.DEBUG)
 logger.addHandler(console_handler)
 
-client = openai.OpenAI(
-    api_key=os.environ.get("SAMBANOVA_API_KEY"),
-    base_url="https://api.sambanova.ai/v1",
-)
 
 groq_client = Groq()
 
-
 system_prompt = "You are an AI coding assistant. Your task is to write single-file HTML applications based on a user's request. Only return the necessary code. Include all necessary imports and styles. You may also be asked to edit your original response."
 user_prompt = "Please write a single-file HTML application to fulfill the following request.\nThe message:{user_message}\nCurrent code you have written:{code}"
 
@@ -75,12 +68,16 @@ def generate(user_message: tuple[int, np.ndarray],
     user_msg_formatted = user_prompt.format(user_message=text, code=code)
     history.append({"role": "user", "content": user_msg_formatted})
     
-    response = client.chat.completions.create(
-        model='Meta-Llama-3.1-70B-Instruct',
+    print("generating response")
+    response = groq_client.chat.completions.create(
+        model="llama-3.3-70b-versatile",
         messages=history,
-        temperature =  0.1,
-        top_p = 0.1
+        temperature=1,
+        max_tokens=1024,
+        top_p=1,
+        stream=False,
     )
+    print("finished generating response")
     
     output = response.choices[0].message.content
     html_code = extract_html_content(output)