Update app.py

app.py

@@ -1,12 +1,13 @@
 import gradio as gr
 from groq import Groq
+from transformers import TextStreamer
 
-
+# Initialize the Groq client with your API key
 client = Groq(
     api_key=("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"),
 )
 
-
+# Define the function that will generate responses
 def generate_response(input_text):
     chat_completion = client.chat.completions.create(
         messages=[
@@ -17,14 +18,26 @@ def generate_response(input_text):
         ],
         model="llama3-8b-8192",
     )
-    return chat_completion.choices[0].message.content
+    
+    # Set up TextStreamer for streaming the response
+    streamer = TextStreamer(client=client)
+
+    # Stream the assistant's response
+    response = ""
+    for chunk in chat_completion.choices[0].message.content:
+        response += chunk
+        streamer.write(response)  # Stream each chunk of text
+
+    return response
 
+# Create the Gradio interface
 iface = gr.Interface(
     fn=generate_response,
     inputs="text",
     outputs="text",
-    title="Parviz Chatbot",
-    description="ye chi bepors",
+    title="Fast Language Model Chatbot with Streaming",
+    description="Ask any question and receive a response from the Groq API using the llama3-8b-8192 model, streamed in real-time.",
 )
 
+# Launch the interface
 iface.launch()