Update memory for new chat session

.gitignore

@@ -1,3 +1,4 @@
+.ipynb_checkpoints
 .venv
 .idea
 __pycache__

app.py

@@ -1,9 +1,10 @@
+import chainlit as cl
 from langchain.prompts import ChatPromptTemplate
 from langchain.schema import StrOutputParser
 from langchain.schema.runnable import Runnable
 from langchain.schema.runnable.config import RunnableConfig
-from react_agent_v2 import agent_executor
-import chainlit as cl
+from react_agent_v2 import get_react_agent
+from langchain.memory import ConversationBufferMemory
 from langchain_community.chat_message_histories import ChatMessageHistory
 from langchain_core.chat_history import BaseChatMessageHistory
 from langchain_core.runnables.history import RunnableWithMessageHistory
@@ -12,8 +13,18 @@ from langchain_core.runnables.history import RunnableWithMessageHistory
 
 @cl.on_chat_start
 async def on_chat_start():
+    message_history = ChatMessageHistory()
+    memory = ConversationBufferMemory(
+        memory_key = "chat_history",
+        output_key = "output",
+        chat_memory = message_history,
+        return_message = True
+    )
+    
+    agent_executor = get_react_agent(memory)
     cl.user_session.set("runnable", agent_executor)
 
+    
 @cl.on_message
 async def on_message(message: cl.Message):
     # runnable = cl.user_session.get("runnable")  # type: Runnable
@@ -39,8 +50,8 @@ async def on_message(message: cl.Message):
 
     llm_chain = cl.user_session.get("runnable")
 
-    response = llm_chain.invoke(
-        {"input": message.content}, callbacks = [cl.LangchainCallbackHandler()]
+    response = await llm_chain.ainvoke(
+        {"input": message.content}, callbacks = [cl.AsyncLangchainCallbackHandler()]
     )
 
     await cl.Message(response["output"].replace("`", "")).send()

react_agent_v2.py

@@ -1,9 +1,8 @@
 from langchain.agents import Tool, AgentType, initialize_agent
 from langchain.memory import ConversationBufferMemory
-# from langchain.utilities import DuckDuckGoSearchAPIWrapper
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.agents import AgentExecutor
-from langchain import hub
+
 from langchain.agents.format_scratchpad import format_log_to_str
 from langchain.agents.output_parsers import ReActSingleInputOutputParser
 from langchain.tools.render import render_text_description
@@ -20,12 +19,6 @@ llm = ChatGoogleGenerativeAI(
     temperature = 0
 )
 
-# search = DuckDuckGoSearchAPIWrapper()
-#
-# search_tool = Tool(name="Current Search",
-#                    func=search.run,
-#                    description="Useful when you need to answer questions about detail jobs information or search a job."
-#                    )
 
 kg_query = Tool(
     name = 'Query Knowledge Graph',
@@ -88,6 +81,17 @@ agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=me
 # result = agent_executor.invoke(question)
 # print(result)
 
+def get_react_agent(memory):
+    agent_executor = AgentExecutor(
+        agent = agent,
+        tools = tools,
+        verbose = True,
+        memory = memory
+    )
+    
+    return agent_executor
+
+
 if __name__ == "__main__":
     while True:
         try: