add streaming

app.py

@@ -61,18 +61,24 @@ def chat(message, history):
         # Add user message
         messages.append({"role": "user", "content": message})
 
-        # Get response from the model
-        completion = client.chat.completions.create(
+        # Get streaming response from the model
+        stream = client.chat.completions.create(
             model="deepseek-ai/DeepSeek-V3-0324",
             messages=messages,
             temperature=0.7,
-            max_tokens=1000
+            max_tokens=1000,
+            stream=True
         )
 
-        return completion.choices[0].message.content
+        # Stream the response
+        partial_message = ""
+        for chunk in stream:
+            if chunk.choices[0].delta.content is not None:
+                partial_message += chunk.choices[0].delta.content
+                yield partial_message
 
     except Exception as e:
-        return f"Error: {str(e)}"
+        yield f"Error: {str(e)}"
 
 # Create Gradio interface
 with gr.Blocks(title="DeepSearch - AI Search Assistant") as demo: