Update app.py

app.py

@@ -7,8 +7,9 @@ nest_asyncio.apply()
 
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
 
+# Fixed client initialization without proxies
 client = OpenAI(
-    base_url="https://api-inference.huggingface.co/v1/",
+    base_url="https://api-inference.huggingface.co/models/NousResearch/Hermes-3-Llama-3.1-8B/",
     api_key=ACCESS_TOKEN,
 )
 
@@ -25,7 +26,6 @@ def respond(
     ]
     
     try:
-        print("Making request to API...")
         response = client.chat.completions.create(
             model="NousResearch/Hermes-3-Llama-3.1-8B",
             messages=messages,
@@ -35,10 +35,9 @@ def respond(
         )
         return response.choices[0].message.content
     except Exception as e:
-        print(f"Error: {str(e)}")
         return f"Error: {str(e)}"
 
-# Create simple Gradio interface without chat memory
+# Gradio interface
 iface = gr.Interface(
     fn=respond,
     inputs=[
@@ -49,7 +48,7 @@ iface = gr.Interface(
         gr.Slider(minimum=0, maximum=1, value=0.9, label="Top P")
     ],
     outputs="text",
-    title="Vendor Contract Parser"
+    title="Hermes-3-Llama Chat"
 )
 
 if __name__ == "__main__":