Update app.py

app.py

@@ -1,21 +1,40 @@
 import os
-import openai
 import gradio as gr
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+from langchain.memory import ConversationBufferMemory
 
 # Set OpenAI API Key
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
-openai.api_key = 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 chain with the ChatOpenAI model and conversation memory
+llm_chain = LLMChain(
+    llm=ChatOpenAI(temperature=0.5, model="gpt-3.5-turbo"),  # Use 'model' instead of 'model_name'
+    prompt=prompt,
+    verbose=True,
+    memory=memory,
+)
+
+# Function to get chatbot response
 def get_text_response(user_message, history):
-    # Call OpenAI GPT model
-    response = openai.ChatCompletion.create(
-        model="gpt-3.5-turbo",
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": user_message},
-        ]
-    )
-    return response['choices'][0]['message']['content']
+    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")