Update app.py

app.py

@@ -100,12 +100,58 @@
 #     demo.launch()
 
 
+# import os
+# import gradio as gr
+# from langchain_openai import ChatOpenAI
+# from langchain.prompts import PromptTemplate
+# from langchain.memory import ConversationBufferMemory
+# from langchain.chains import LLMChain
+
+# # Set OpenAI API Key
+# OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
+
+# # Define the template for the chatbot's response
+# template = """You are a helpful assistant to answer all user queries.
+# {chat_history}
+# User: {user_message}
+# Chatbot:"""
+
+# # Define the prompt template
+# prompt = PromptTemplate(
+#     input_variables=["chat_history", "user_message"], 
+#     template=template
+# )
+
+# # Initialize conversation memory
+# memory = ConversationBufferMemory(memory_key="chat_history")
+
+# # Define the LLM (language model) and chain
+# llm = ChatOpenAI(temperature=0.5, model="gpt-3.5-turbo")
+# llm_chain = LLMChain(
+#     llm=llm,
+#     prompt=prompt,
+#     verbose=True,
+#     memory=memory,
+# )
+
+# # Function to get chatbot response
+# def get_text_response(user_message, history):
+#     response = llm_chain.predict(user_message=user_message)
+#     return response
+
+# # Create a Gradio chat interface
+# demo = gr.Interface(fn=get_text_response, inputs="text", outputs="text")
+
+# if __name__ == "__main__":
+#     demo.launch()
+
 import os
 import gradio as gr
 from langchain_openai import ChatOpenAI
 from langchain.prompts import PromptTemplate
 from langchain.memory import ConversationBufferMemory
-from langchain.chains import LLMChain
+from langchain.schema import AIMessage, HumanMessage
+from langchain.chains import RunnableSequence
 
 # Set OpenAI API Key
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
@@ -122,21 +168,23 @@ prompt = PromptTemplate(
     template=template
 )
 
-# Initialize conversation memory
-memory = ConversationBufferMemory(memory_key="chat_history")
+# Initialize conversation memory (following migration guide)
+memory = ConversationBufferMemory(return_messages=True)  # Use return_messages=True for updated usage
 
-# Define the LLM (language model) and chain
+# Define the LLM (language model)
 llm = ChatOpenAI(temperature=0.5, model="gpt-3.5-turbo")
-llm_chain = LLMChain(
-    llm=llm,
-    prompt=prompt,
-    verbose=True,
-    memory=memory,
-)
+
+# Create the RunnableSequence instead of LLMChain
+llm_sequence = prompt | llm  # This pipelines the prompt into the language model
 
 # Function to get chatbot response
 def get_text_response(user_message, history):
-    response = llm_chain.predict(user_message=user_message)
+    # Prepare the conversation history
+    chat_history = [HumanMessage(content=user_message)]
+    
+    # Pass the prompt and history to the language model sequence
+    response = llm_sequence.invoke({"chat_history": history, "user_message": user_message})
+    
     return response
 
 # Create a Gradio chat interface
@@ -146,3 +194,4 @@ if __name__ == "__main__":
     demo.launch()
 
 
+