Update app.py

app.py

@@ -1,7 +1,7 @@
-from langchain_openai import ChatOpenAI
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_core.output_parsers import StrOutputParser
-from langchain_community.llms import Ollama
+from langchain import LLMChain
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate
+from langchain.output_parsers import StrOutputParser
 import streamlit as st
 import os
 from dotenv import load_dotenv
@@ -13,29 +13,30 @@ load_dotenv()
 os.environ["LANGCHAIN_TRACING_V2"] = "true"
 os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_API_KEY")
 
+# Initialize the LLM (e.g., using OpenAI or Hugging Face)
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", openai_api_key=os.getenv("OPENAI_API_KEY"))
+
 # Prompt Template
 prompt = ChatPromptTemplate.from_messages(
     [
-        ("system", "You are a helpful assistant. Please respond to the user queries"),
+        ("system", "You are a helpful assistant. Please respond to the user queries."),
         ("user", "Question: {question}")
     ]
 )
 
+# Create LLM Chain
+chain = LLMChain(llm=llm, prompt=prompt, output_key="response")
+
 # Streamlit app setup
-st.title('Langchain Demo With LLAMA2 API')
+st.title('Langchain Demo with Hugging Face API')
 
 # User input
 input_text = st.text_input("Search the topic you want")
 
-# Ollama LLM (ensure the model is available, or access it through Hugging Face API)
-llm = Ollama(model="llama2")
-output_parser = StrOutputParser()
-chain = prompt | llm | output_parser
-
 # Display result when user inputs text
 if input_text:
     try:
-        response = chain.invoke({"question": input_text})
+        response = chain.run({"question": input_text})
         st.write(response)
     except Exception as e:
         st.error(f"Error: {e}")