Update app.py

app.py

@@ -4,6 +4,15 @@ from openai import OpenAI
 from dotenv import load_dotenv
 
 load_dotenv()
+api_key = os.getenv("GROQ_API_KEY")
+if not api_key:
+    raise RuntimeError("GROQ_API_KEY is not set")
+
+client = OpenAI(
+    api_key=api_key,
+    base_url="https://api.groq.com/openai/v1",
+    timeout=120.0
+)
 
 def respond(
     message,
@@ -13,16 +22,7 @@ def respond(
     temperature,
     top_p,
 ):
-    api_key = os.getenv("GROQ_API_KEY")
-    if not api_key:
-        raise RuntimeError("GROQ_API_KEY is not set")
-
-    client = OpenAI(
-        api_key=api_key,
-        base_url="https://api.groq.com/openai/v1",
-        timeout=120.0
-    )
-
+    
     def sanitize_messages(history):
         sanitized = []
         for m in history:
@@ -41,20 +41,23 @@ def respond(
 
     response_text = ""
 
-    stream = client.chat.completions.create(
-        model="qwen/qwen3-32b",
-        messages=messages,
-        max_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
-        stream=True,
-    )
+    try:
+        stream = client.chat.completions.create(
+            model="qwen/qwen3-32b",
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            stream=True,
+        )
 
-    for chunk in stream:
-        if chunk.choices[0].delta.content:
-            response_text += chunk.choices[0].delta.content
-            yield response_text
+        for chunk in stream:
+            if chunk.choices[0].delta.content:
+                response_text += chunk.choices[0].delta.content
+                yield response_text
 
+    except Exception as e:
+        yield f"Error: {str(e)}"
 
 
 chatbot = gr.ChatInterface(
@@ -74,4 +77,4 @@ chatbot = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    chatbot.queue().launch()
+    chatbot.queue(default_concurrency_limit=5).launch()