Update app.py

app.py

@@ -1,18 +1,16 @@
 import openai
 import gradio as gr
-from langchain.chains import ConversationalChain
+from langchain.chains import RetrievalQA
 from langchain.llms import OpenAI
 from langchain.document_loaders import PyPDFLoader
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.chat_models import ChatOpenAI
-from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
 from PyPDF2 import PdfReader
-import os
 
 # Function to load and process the PDF document
 def load_pdf(file):
-    # Load the PDF using PyPDF2 or LangChain's built-in loader
+    # Load the PDF using LangChain's PyPDFLoader
     loader = PyPDFLoader(file.name)
     documents = loader.load()
     return documents
@@ -22,6 +20,7 @@ def summarize_pdf(file, openai_api_key):
     # Set the API key dynamically
     openai.api_key = openai_api_key
 
+    # Load and process the PDF
     documents = load_pdf(file)
 
     # Create embeddings for the documents
@@ -30,16 +29,16 @@ def summarize_pdf(file, openai_api_key):
     # Use LangChain's FAISS Vector Store to store and search the embeddings
     vector_store = FAISS.from_documents(documents, embeddings)
 
-    # Create a conversational chain that allows us to query the document
+    # Create a RetrievalQA chain for summarization
     llm = ChatOpenAI(model="gpt-4")  # Using GPT-4 as the LLM
-    conversational_chain = ConversationalChain(
-        llm=llm, 
-        vectorstore=vector_store,
-        verbose=True
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=vector_store.as_retriever()
     )
 
-    # Query the model for a summary
-    response = conversational_chain.run("Summarize the content of the research paper.")
+    # Query the model for a summary of the document
+    response = qa_chain.run("Summarize the content of the research paper.")
     return response
 
 # Function to handle user queries and provide answers from the document
@@ -47,6 +46,7 @@ def query_pdf(file, user_query, openai_api_key):
     # Set the API key dynamically
     openai.api_key = openai_api_key
 
+    # Load and process the PDF
     documents = load_pdf(file)
 
     # Create embeddings for the documents
@@ -55,16 +55,16 @@ def query_pdf(file, user_query, openai_api_key):
     # Use LangChain's FAISS Vector Store to store and search the embeddings
     vector_store = FAISS.from_documents(documents, embeddings)
 
-    # Create a conversational chain that allows us to query the document
-    llm = ChatOpenAI(model="gpt-4o")  # Using GPT-4 as the LLM
-    conversational_chain = ConversationalChain(
+    # Create a RetrievalQA chain for querying the document
+    llm = ChatOpenAI(model="gpt-4")  # Using GPT-4 as the LLM
+    qa_chain = RetrievalQA.from_chain_type(
         llm=llm,
-        vectorstore=vector_store,
-        verbose=True
+        chain_type="stuff",
+        retriever=vector_store.as_retriever()
     )
 
     # Query the model for the user query
-    response = conversational_chain.run(user_query)
+    response = qa_chain.run(user_query)
     return response
 
 # Define Gradio interface for the summarization