Update app.py

app.py

@@ -51,28 +51,28 @@ with demo:
         #chat_model_selection = chat_model_dropdown.value
         chat_model_selection = 'Intel/neural-chat-7b-v1-1'
         
-        #def call_api_and_stream_response(query, chat_model):
-        #    """
-        #    Call the API endpoint and yield characters as they are received.
-        #    This function simulates streaming by yielding characters one by one.
-        #    """
-        #    url = inference_endpoint_url
-        #    params = {"query": query, "selected_model": chat_model}
-        #    with requests.get(url, json=params, stream=True) as r:  # Use params for query parameters
-        #        for chunk in r.iter_content(chunk_size=1):
-        #            if chunk:
-        #                yield chunk.decode()
-#
-        #def get_response(query, history):
-        #    """
-        #    Wrapper function to call the streaming API and compile the response.
-        #    """
-        #    response = ''
-        #    for char in call_api_and_stream_response(query, chat_model=chat_model_selection):
-        #        if char == '<':  # This seems to be your stopping condition; adjust as needed.
-        #            break
-        #        response += char
-        #        yield [(f"🤖 Response from LLM: {chat_model_selection}", response)]  # Correct format for Gradio Chatbot
+        def call_api_and_stream_response(query, chat_model):
+            """
+            Call the API endpoint and yield characters as they are received.
+            This function simulates streaming by yielding characters one by one.
+            """
+            url = inference_endpoint_url
+            params = {"query": query, "selected_model": chat_model}
+            with requests.get(url, json=params, stream=True) as r:  # Use params for query parameters
+                for chunk in r.iter_content(chunk_size=1):
+                    if chunk:
+                        yield chunk.decode()
+
+        def get_response(query, history):
+            """
+            Wrapper function to call the streaming API and compile the response.
+            """
+            response = ''
+            for char in call_api_and_stream_response(query, chat_model=chat_model_selection):
+                if char == '<':  # This seems to be your stopping condition; adjust as needed.
+                    break
+                response += char
+                yield [(f"🤖 Response from LLM: {chat_model_selection}", response)]  # Correct format for Gradio Chatbot
 #
         #with gr.Blocks() as chat_interface:
         #    chatbot = gr.Chatbot()