codeGPT / app.py
red1xe's picture
PDF to text
f4781ea
raw
history blame
441 Bytes
import streamlit as st
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from pdfminer.high_level import extract_text
st.title("Embedding Creation for Langchain")
st.header("File Upload")
files = st.file_uploader("Upload your files", accept_multiple_files=True, type="pdf")
if files:
st.header("PDFs to Text")
for file in files:
text = extract_text(file)
st.write(text)