app.py

import streamlit as st
from langchain_groq import ChatGroq
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFLoader

import os
from dotenv import load_dotenv
import tempfile
import time

load_dotenv()

## Langsmith Tracking
os.environ['LANGCHAIN_API_KEY'] = os.getenv('LANGCHAIN_API_KEY')
os.environ['LANGCHAIN_TRACING_V2'] = 'true'
os.environ['LANGCHAIN_PROJECT'] = "Simple Q&A Chatbot With OpenAI"
os.environ['GROQ_API_KEY'] = os.getenv('GROQ_API_KEY')
os.environ["HF_TOKEN"] = os.getenv('HF_TOKEN')
os.environ["TOKENIZERS_PARALLELISM"] = "false"

llm = ChatGroq(model="llama-3.1-70b-Versatile")

prompt = ChatPromptTemplate.from_template(
    """
    Answer the question based on provided context only.
    Please provide the most accurate response based on the question
    <context>
    {context}
    </context>
    Question: {input}
    """
)

def create_vector_embeddings(pdf_file_path):
    st.session_state.embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
    st.session_state.loader = PyPDFLoader(pdf_file_path)
    st.session_state.docs = st.session_state.loader.load()
    st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs)
    st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings)

uploaded_file = st.file_uploader("Upload a PDF", type="pdf", key="pdf_uploader")

user_prompt = st.text_input("Enter your Query about PDF here:")

if st.button("Document Embedding") and uploaded_file is not None:
    with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
        tmp_file.write(uploaded_file.getvalue())
        tmp_file_path = tmp_file.name
    create_vector_embeddings(tmp_file_path)
    st.write("Vector Database is ready")

if user_prompt and "vectors" in st.session_state:
    document_chain = create_stuff_documents_chain(llm, prompt)
    retriever = st.session_state.vectors.as_retriever()
    retrieval_chain = create_retrieval_chain(retriever, document_chain)
    
    start = time.process_time()
    response = retrieval_chain.invoke({"input": user_prompt})
    st.write(f"Response Time: {time.process_time() - start}")
    
    st.write(response["answer"])
    
    with st.expander("Document Similarity Search"):
        for i, doc in enumerate(response["context"]):
            st.write(doc.page_content)
            st.write("---------------------------------------")