app.py

import streamlit as st
import os
from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings, ChatNVIDIA
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.embeddings import OllamaEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain.chains import create_retrieval_chain
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFDirectoryLoader
import time
import tempfile


from dotenv import load_dotenv
load_dotenv()

## load the Groq API key
os.environ['NVIDIA_API_KEY']=os.getenv("NVIDIA_API_KEY")

def vector_embedding(loader):

    if "vectors" not in st.session_state:

        st.session_state.embeddings=NVIDIAEmbeddings()
        st.session_state.loader=loader ## Data Ingestion
        st.session_state.docs=st.session_state.loader.load() ## Document Loading
        st.session_state.text_splitter=RecursiveCharacterTextSplitter(chunk_size=700,chunk_overlap=50) ## Chunk Creation
        st.session_state.final_documents=st.session_state.text_splitter.split_documents(st.session_state.docs[:30]) #splitting
        st.session_state.vectors=FAISS.from_documents(st.session_state.final_documents,st.session_state.embeddings) #vector OpenAI embeddings


st.title("Nvidia NIM Demo")
llm = ChatNVIDIA(model="mistralai/mixtral-8x7b-instruct-v0.1")


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}

"""
)

uploaded_files = st.file_uploader("Upload PDF",type="pdf", accept_multiple_files=True)

# Check if files were uploaded
if st.button("Documents Embedding") and uploaded_files:
    # Create a temporary directory to save the uploaded PDFs
    with tempfile.TemporaryDirectory() as temp_dir:
        for uploaded_file in uploaded_files:
            # Save each uploaded file to the temporary directory
            with open(os.path.join(temp_dir, uploaded_file.name), "wb") as f:
                f.write(uploaded_file.getbuffer())

        # Initialize PyPDFDirectoryLoader with the path to the temporary directory
        loader = PyPDFDirectoryLoader(temp_dir)
        vector_embedding(loader)
        st.write("Vector Store DB Is Ready")

        
prompt1=st.text_input("Enter Your Question From Documents")


#if st.button("Documents Embedding"):
#    vector_embedding()
#    st.write("Vector Store DB Is Ready")





if prompt1:
    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':prompt1})
    print("Response time :",time.process_time()-start)
    st.write(response['answer'])

    # With a streamlit expander
    with st.expander("Document Similarity Search"):
        # Find the relevant chunks
        for i, doc in enumerate(response["context"]):
            st.write(doc.page_content)
            st.write("--------------------------------")