app_archive.py

import streamlit as st
from PyPDF2 import PdfReader
from llama_index.llms import HuggingFaceInferenceAPI
from llama_index import VectorStoreIndex
from llama_index.embeddings import HuggingFaceEmbedding
from llama_index import ServiceContext
from llama_index.schema import Document


def read_pdf(uploaded_file):
    pdf_reader = PdfReader(uploaded_file)
    text = ""
    for page_num in range(len(pdf_reader.pages)):
        text += pdf_reader.pages[page_num].extract_text()
    return text



st.title("PdfQuerier using LLAMA by Rahul Bhoyar")
hf_token = st.text_input("Enter your Hugging Face token:")
llm = HuggingFaceInferenceAPI(model_name="HuggingFaceH4/zephyr-7b-alpha", token=hf_token)
st.markdown("Query your pdf file data with using this chatbot.")
uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])

# Creation of Embedding model
embed_model_uae = HuggingFaceEmbedding(model_name="WhereIsAI/UAE-Large-V1")
service_context = ServiceContext.from_defaults(llm=llm, chunk_size=800, chunk_overlap=20, embed_model=embed_model_uae)

if uploaded_file is not None:
    file_contents = read_pdf(uploaded_file)
    documents = Document(text=file_contents)
    documents = [documents]
    st.success("Documents loaded successfully!")

# Indexing the documents
progress_container = st.empty()
progress_container.text("Creating VectorStoreIndex...")
    # Code to create VectorStoreIndex
index = VectorStoreIndex.from_documents(documents, service_context=service_context, show_progress=True)
# Persist Storage Context
index.storage_context.persist()
st.success("VectorStoreIndex created successfully!")
# Create Query Engine
query = st.text_input("Ask a question:")
query_engine = index.as_query_engine()

if query:
    # Run Query
    progress_container.text("Fetching the response...")
    response = query_engine.query(query)
    st.markdown(f"**Response:** {response}")