Spaces:
Sleeping
Sleeping
File size: 1,627 Bytes
3f4a167 |
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 55 56 57 58 59 |
import streamlit as st
from pdf_to_image import pdf_to_image
from image_to_text import image_to_text
from mirascope_extractor import extractor
import google.generativeai as genai
import pandas as pd
import glob
import os
from dotenv import load_dotenv
import streamlit as st
load_dotenv()
global empty_df
openai_api_key = os.getenv('OPENAI_API_KEY')
genai.configure(api_key=openai_api_key)
st.set_page_config(page_title="Invoice Extractor")
st.title("Gen AI CV Extraction")
uploaded_files = st.file_uploader("Choose PDF files", accept_multiple_files=True, type="pdf")
if uploaded_files:
if st.button('Extract'):
image_bytes = pdf_to_image(uploaded_files)
all_texts = []
for image_byte in image_bytes:
print('This is image_byte: ', image_byte)
combine_text = ''
for image in image_byte:
text = image_to_text(image)
combine_text += text
print('This is the text from single PDF: ', combine_text)
all_texts.append(combine_text)
empty_df = pd.DataFrame()
for text in all_texts:
extracted_text = extractor(text)
task_details_dict = extracted_text.dict()
df = pd.DataFrame([task_details_dict])
empty_df = pd.concat([empty_df, df])
st.write(empty_df)
csv = empty_df.to_csv(index=False)
st.download_button(
label = 'Click to Download CSV',
data = csv,
file_name = 'Extracted_data.csv',
mime='text/csv',
)
|