Update app.py

app.py

@@ -51,55 +51,55 @@ 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
-
-        with gr.Blocks() as chat_interface:
-            chatbot = gr.Chatbot()
-            msg = gr.Textbox()
-            submit = gr.Button("Submit")
-            clear = gr.Button("Clear")
-
-            def user(user_message, history):
-                return "", history + [[user_message, None]]
-
-            def clear_chat(*args):
-                return []  # Returning an empty list to signify clearing the chat, adjust as per Gradio's capabilities
-
-            submit.click(
-                fn=get_response,
-                inputs=[msg, chatbot],
-                outputs=chatbot
-            )
-
-            clear.click(
-                fn=clear_chat,
-                inputs=None,
-                outputs=chatbot
-            )
-            
-        chat_interface.queue()
-        chat_interface.launch()
+        #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()
+        #    msg = gr.Textbox()
+        #    submit = gr.Button("Submit")
+        #    clear = gr.Button("Clear")
+#
+        #    def user(user_message, history):
+        #        return "", history + [[user_message, None]]
+#
+        #    def clear_chat(*args):
+        #        return []  # Returning an empty list to signify clearing the chat, adjust as per Gradio's capabilities
+#
+        #    submit.click(
+        #        fn=get_response,
+        #        inputs=[msg, chatbot],
+        #        outputs=chatbot
+        #    )
+#
+        #    clear.click(
+        #        fn=clear_chat,
+        #        inputs=None,
+        #        outputs=chatbot
+        #    )
+        #    
+        #chat_interface.queue()
+        #chat_interface.launch()
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         with gr.TabItem("🏆 LLM Leadeboard", elem_id="llm-benchmark-table", id=0):