app.py

import streamlit as st
import os
from langchain_groq import ChatGroq
from langchain.embeddings import HuggingFaceEmbeddings
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 dotenv import load_dotenv
import time

# Load environment variables from .env file
load_dotenv()

# Retrieve the API keys from environment variables
huggingfacehub_api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
groq_api_key = os.getenv("GROQ_API_KEY")

# Check if the keys are retrieved correctly
if huggingfacehub_api_token is None:
    raise ValueError("HUGGINGFACEHUB_API_TOKEN environment variable is not set")
if groq_api_key is None:
    raise ValueError("GROQ_API_KEY environment variable is not set")

# Set environment variables for Hugging Face
os.environ['HUGGINGFACEHUB_API_TOKEN'] = huggingfacehub_api_token

# Initialize the ChatGroq LLM with the retrieved API key
llm = ChatGroq(api_key=groq_api_key, model_name="Llama3-8b-8192")

st.title("DataScience Chatgroq With Llama3")

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 = HuggingFaceEmbeddings()
        st.session_state.loader = PyPDFDirectoryLoader("./Data_Science")  # 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 HuggingFace embeddings

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})
    st.write("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("--------------------------------")