File size: 3,019 Bytes
7ddeba9 4e6eb1f a9c16f6 7ddeba9 c0c07c7 a813767 2c0d74d 7ddeba9 2c0d74d 7ddeba9 671cbf4 7ddeba9 0997900 c93c025 d0f94b2 c93c025 671cbf4 7ddeba9 671cbf4 7ddeba9 671cbf4 7ddeba9 671cbf4 c93c025 d0f94b2 c93c025 671cbf4 7ddeba9 671cbf4 |
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 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
import streamlit as st
import pytesseract
from tempfile import NamedTemporaryFile
from langchain_community.document_loaders import PyPDFLoader
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain import HuggingFaceHub
from PIL import Image
import os
def main():
st.title("Invoice Entity Extractor 📚")
uploaded_file = st.sidebar.file_uploader("Upload a PDF file", type="pdf")
uploaded_image = st.sidebar.file_uploader("Upload an image", type=["png", "jpg", "jpeg"])
if uploaded_file is not None:
process_pdf(uploaded_file)
elif uploaded_image is not None:
process_image(uploaded_image)
api_token = os.getenv('HF_TOKEN')
def process_pdf(uploaded_file):
# Process the uploaded PDF file
with NamedTemporaryFile(delete=False) as temp_file:
temp_file.write(uploaded_file.read())
temp_file_path = temp_file.name
loader = PyPDFLoader(temp_file_path)
pages = loader.load()
st.write(f"Number of pages: {len(pages)}")
for page in pages:
st.write(page.page_content)
model = "meta-llama/Meta-Llama-3-8B-Instruct"
llm = HuggingFaceHub(
huggingfacehub_api_token = api_token,
repo_id = model,
verbose = False,
model_kwargs = {"temperature":0.01, "max_new_tokens": 128})
template = """Extract invoice number, name of organization, address, date,
Qty, Rate, Tax, Amount {pages}
Output: entity: type
"""
prompt_template = PromptTemplate(input_variables=["pages"], template=template)
chain = LLMChain(llm=llm, prompt=prompt_template)
result = chain.run(pages=pages[0].page_content)
st.write("Extracted entities:")
entities = result.strip().split("\n")
table_data = [line.split(":") for line in entities]
st.table(table_data)
def process_image(uploaded_image):
# Process the uploaded image using OCR
image = Image.open(uploaded_image)
text = pytesseract.image_to_string(image)
st.write("Extracted text from the image:")
st.write(text)
# Apply entity extraction logic to the extracted text
#llm = CTransformers(model="llama-2-7b-chat.ggmlv3.q4_0.bin", model_type="llama",
#config={'max_new_tokens': 128, 'temperature': 0.01})
model = "llama-2-7b-chat.ggmlv3.q4_0.bin"
llm = HuggingFaceHub(
huggingfacehub_api_token = api_token,
repo_id = model,
verbose = False,
model_kwargs = {"temperature":0.01, "max_new_tokens": 128})
template = """Extract invoice number, name of organization, address, date,
Qty, Rate, Tax, Amount {text}
Output: entity: type
"""
prompt_template = PromptTemplate(input_variables=["text"], template=template)
chain = LLMChain(llm=llm, prompt=prompt_template)
result = chain.run(text)
st.write("Extracted entities:")
entities = result.strip().split("\n")
table_data = [line.split(":") for line in entities]
st.table(table_data)
if __name__ == "__main__":
main() |