Update app.py

app.py

@@ -2,6 +2,9 @@ import gradio as gr
 from langchain_community.chat_models import ChatOpenAI
 from langchain.memory import ConversationBufferMemory, SimpleMemory
 from langchain.agents import initialize_agent, AgentType
+from langchain_community.callbacks import ClearMLCallbackHandler
+from langchain_core.callbacks import StdOutCallbackHandler
+from clearml import Logger, Task
 from dotenv import load_dotenv
 import os
 import agent.planning_agent as planning_agent
@@ -15,6 +18,7 @@ logger = logging.getLogger(__name__)
 llm = None
 chat_memory = None
 query_memory = None
+clearml_callback = None
 
 def initialize_components():
     global llm, chat_memory, query_memory
@@ -40,6 +44,19 @@ def initialize_components():
     )
     query_memory = SimpleMemory()
 
+        # Setup and use the ClearML Callback
+    clearml_callback = ClearMLCallbackHandler(
+    task_type="inference",
+    project_name="langchain_callback_demo",
+    task_name="llm",
+    tags=["test"],
+    # Change the following parameters based on the amount of detail you want tracked
+    visualize=True,
+    complexity_metrics=True,
+    stream_logs=True,)
+    
+    callbacks = [StdOutCallbackHandler(), clearml_callback
+
     # Initialize planning agent with both memories
     planning_agent.initialize_planning_agent(llm, chat_memory, query_memory)
 
@@ -106,6 +123,14 @@ def main():
         app = create_gradio_app()
         app.queue()
         app.launch(server_name="0.0.0.0", server_port=7860, share=True)
+        a_task = Task.get_task(project_name='langchain_callback_demo', task_name='llm')
+        loer = a_task.get_logger()
+        report_logs(loer)
+          # report text as debug example
+        report_debug_text(loer)
+        # report graphs
+        report_table(loer)
+        loer.flush()
     except Exception as e:
         logger.error(f"Error in main: {str(e)}")
         raise