Spaces:
Paused
Paused
File size: 1,891 Bytes
8225db2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
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}")
|