basic.py

from langchain_groq import ChatGroq
from langchain_openai import OpenAIEmbeddings 
from langchain.text_splitter 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 PyPDFDirectoryLoader
from langchain_google_genai import GoogleGenerativeAIEmbeddings

import streamlit as st
import os
import time
from dotenv import load_dotenv

load_dotenv()

# os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')
groq_api_key = os.getenv('GROQ_API_KEY')
os.environ['GOOGLE_API_KEY'] = os.getenv('GOOGLE_API_KEY')

st.title('Talk to your PDF')

llm = ChatGroq(groq_api_key = groq_api_key,
               model_name = 'llama3-8b-8192')

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

def vector_embedding():
    
    if 'vectors' not in st.session_state:
        st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model = 'models/embedding-001')
        st.session_state.loader = PyPDFDirectoryLoader('./us_census') #data ingestion
        st.session_state.docs = st.session_state.loader.load() #document loading
        st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200) #chunk creation
        st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs[:20]) #splitting
        st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings) #vector embeddings


prompt1 = st.text_input('Ask a question')

if st.button('Create Vector Store'):
    vector_embedding() 
    st.write('Vector Store DB is ready!') #vector db is available in st.session_state


if prompt1:
    document_chain = create_stuff_documents_chain(llm, prompt)
    retriever = st.session_state.vectors.as_retriever()
    retriever_chain = create_retrieval_chain(retriever, document_chain)
    start = time.process_time()
    response = retriever_chain.invoke({'input': prompt1})
    print('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("-------------------------------")