Update app.py

app.py

@@ -1,15 +1,22 @@
+# Imports
 import streamlit as st
-from dotenv import load_dotenv
 from PyPDF2 import PdfReader
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.chat_models import ChatOpenAI
-from langchain.memory import ConversationBufferMemory
-from langchain.chains import ConversationalRetrievalChain
-from htmlTemplates import css, bot_template, user_template
-from langchain.llms import HuggingFaceHub
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import os
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+import google.generativeai as genai
+from langchain_community.vectorstores import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()  
+os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))  # Configure Google Generative AI
 
+# Extracts text from all pages of provided PDF documents
 def get_pdf_text(pdf_docs):
     text = ""
     for pdf in pdf_docs:
@@ -18,87 +25,84 @@ def get_pdf_text(pdf_docs):
             text += page.extract_text()
     return text
 
-
+# Splits text into chunks of 10,000 characters with 1,000 character overlap
 def get_text_chunks(text):
-    text_splitter = CharacterTextSplitter(
-        separator="\n",
-        chunk_size=1000,
-        chunk_overlap=200,
-        length_function=len
-    )
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
     chunks = text_splitter.split_text(text)
     return chunks
 
-
-def get_vectorstore(text_chunks):
-    embeddings = OpenAIEmbeddings()
-    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
-    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
-    return vectorstore
-
-
-def get_conversation_chain(vectorstore):
-    llm = ChatOpenAI()
-    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
-
-    memory = ConversationBufferMemory(
-        memory_key='chat_history', return_messages=True)
-    conversation_chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        retriever=vectorstore.as_retriever(),
-        memory=memory
+# Creates and saves a FAISS vector store from text chunks
+def get_vector_store(text_chunks):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    vector_store.save_local("faiss_index")
+
+# Creates and returns a conversational chain for question answering
+def get_conversational_chain():
+    prompt_template = """
+Answer the question concisely, focusing on the most relevant and important details from the PDF context. 
+Refrain from mentioning any mathematical equations, even if they are present in provided context. 
+Focus on the textual information available. Please provide direct quotations or references from PDF
+to back up your response. If the answer is not found within the PDF, 
+please state "answer is not available in the context."\n\n
+Context:\n {context}?\n
+Question: \n{question}\n
+Example response format:
+Overview: 
+(brief summary or introduction)
+Key points: 
+(point 1: paragraph for key details)
+(point 2: paragraph for key details)
+...
+Use a mix of paragraphs and points to effectively convey the information.
+"""
+
+# Adjust temperature parameter to lower value to: 
+# reduce model creativity & focus on factual accuracy
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.2)
+
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+
+    return chain
+
+# Processes user question and provides a response
+def user_input(user_question):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+
+    new_db = FAISS.load_local("faiss_index", embeddings)
+    docs = new_db.similarity_search(user_question)
+
+    chain = get_conversational_chain()
+
+    response = chain.invoke(
+        {"input_documents": docs, "question": user_question},
+        return_only_outputs=True
     )
-    return conversation_chain
 
+    st.write("Reply: ", response["output_text"],"")  
 
-def handle_userinput(user_question):
-    response = st.session_state.conversation({'question': user_question})
-    st.session_state.chat_history = response['chat_history']
-
-    for i, message in enumerate(st.session_state.chat_history):
-        if i % 2 == 0:
-            st.write(user_template.replace(
-                "{{MSG}}", message.content), unsafe_allow_html=True)
-        else:
-            st.write(bot_template.replace(
-                "{{MSG}}", message.content), unsafe_allow_html=True)
+# Streamlit UI
+def main():
+    st.set_page_config(page_title="Chat with PDFs", page_icon="")
+    st.header("Chat with multiple PDFs using AI 💬")
 
+    user_question = st.text_input("Ask a Question from PDF file(s)")  
 
-def main():
-    load_dotenv()
-    st.set_page_config(page_title="Chat with multiple PDFs",
-                       page_icon=":books:")
-    st.write(css, unsafe_allow_html=True)
-
-    if "conversation" not in st.session_state:
-        st.session_state.conversation = None
-    if "chat_history" not in st.session_state:
-        st.session_state.chat_history = None
-
-    st.header("Chat with multiple PDFs :books:")
-    user_question = st.text_input("Ask a question about your documents:")
     if user_question:
-        handle_userinput(user_question)
+        user_input(user_question)
 
     with st.sidebar:
-        st.subheader("Your documents")
-        pdf_docs = st.file_uploader(
-            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
-        if st.button("Process"):
-            with st.spinner("Processing"):
-                # get pdf text
-                raw_text = get_pdf_text(pdf_docs)
+        st.title("Menu ✨")
+        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button ",
+                                     accept_multiple_files=True)
 
-                # get the text chunks
+        if st.button("Submit & Process"): 
+            with st.spinner("Processing..."):
+                raw_text = get_pdf_text(pdf_docs)
                 text_chunks = get_text_chunks(raw_text)
+                get_vector_store(text_chunks)
+                st.success("Done ✨")
 
-                # create vector store
-                vectorstore = get_vectorstore(text_chunks)
-
-                # create conversation chain
-                st.session_state.conversation = get_conversation_chain(
-                    vectorstore)
-
-
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()