import streamlit as st from cryptography.fernet import Fernet import time import pandas as pd import io from transformers import pipeline from streamlit_extras.stylable_container import stylable_container import json import nltk import plotly.express as px from PyPDF2 import PdfReader import docx import zipfile from gliner import GLiNER st.subheader("Named Entity Recognition (NER)", divider="red") # generate Fernet key if 'fernet_key' not in st.session_state: st.session_state.fernet_key = Fernet.generate_key() key = st.session_state.fernet_key # function for generating and validating fernet key def generate_fernet_token(key, data): fernet = Fernet(key) token = fernet.encrypt(data.encode()) return token def validate_fernet_token(key, token, ttl_seconds): fernet = Fernet(key) try: decrypted_data = fernet.decrypt(token, ttl=ttl_seconds).decode() return decrypted_data, None except Exception as e: return None, f"Expired token: {e}" # sidebar with st.sidebar: with stylable_container( key="test_button", css_styles=""" button { background-color: yellow; border: 1px solid black; padding: 5px; color: black; } """, ): st.button("DEMO APP") expander = st.expander("**Important notes on the Demo Named Entity Recognition (NER) App**") expander.write(''' **Supported File Formats** This app accepts files in .pdf and .docx formats. **How to Use** Upload your file first. Then, click the 'Results' button. **Usage Limits** You can request results up to 5 times. **Subscription Management** This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own Named Entity Recognition (NER) Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app within five business days. If you wish to delete your Account with us, please contact us at info@nlpblogs.com **Authorization** For security purposes, your authorization access expires hourly. To restore access, click the "Request Authorization" button. **Customization** To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts. **File Handling and Errors** The app may display an error message if your file is corrupt, or has other errors. For any errors or inquiries, please contact us at info@nlpblogs.com ''') # count attempts based on file upload if 'file_upload_attempts' not in st.session_state: st.session_state['file_upload_attempts'] = 0 max_attempts = 5 # upload file upload_file = st.file_uploader("Upload your file. Accepted file formats include: .pdf, .docx", type=['pdf', 'docx']) text = None df = None if upload_file is not None: file_extension = upload_file.name.split('.')[-1].lower() if file_extension == 'pdf': try: pdf_reader = PdfReader(upload_file) text = "" for page in pdf_reader.pages: text += page.extract_text() st.write(text) except Exception as e: st.error(f"An error occurred while reading PDF: {e}") elif file_extension == 'docx': try: doc = docx.Document(upload_file) text = "\n".join([para.text for para in doc.paragraphs]) st.write(text) except Exception as e: st.error(f"An error occurred while reading docx: {e}") else: st.warning("Unsupported file type.") st.stop() # generate and validate Fernet token for the current file if 'fernet_token' not in st.session_state: if text is not None: st.session_state.fernet_token = generate_fernet_token(key, text) else: st.stop() decrypted_data_streamlit, error_streamlit = validate_fernet_token(key, st.session_state.fernet_token, ttl_seconds=3600) if error_streamlit: if text is not None: st.warning("Please press Request Authorization.") if st.button("Request Authorization"): st.session_state.fernet_token = generate_fernet_token(key, text) st.success("Authorization granted") decrypted_data_streamlit, error_streamlit = validate_fernet_token(key, st.session_state.fernet_token, ttl_seconds=3600) if error_streamlit: st.error(f"Your authorization has expired: {error_streamlit}") st.stop() st.divider() #retrieve answer if st.button("Results"): if st.session_state['file_upload_attempts'] >= max_attempts: st.error(f"You have requested results {max_attempts} times. You have reached your daily request limit.") st.stop() st.session_state['file_upload_attempts'] += 1 if error_streamlit: st.warning("Please upload a file before retrieving the results.") else: with st.spinner('Wait for it...'): time.sleep(2) model = GLiNER.from_pretrained("xomad/gliner-model-merge-large-v1.0") labels = ["person", "location", "country", "city", "organization", "time", "date", "product", "event name", "money", "affiliation", "ordinal value", "percent value", "position"] entities = model.predict_entities(text, labels) df = pd.DataFrame(entities) properties = {"border": "2px solid gray", "color": "blue", "font-size": "16px"} df_styled = df.style.set_properties(**properties) st.dataframe(df_styled) if df is not None: fig = px.treemap(df, path=[px.Constant("all"), 'text', 'label'], values='score', color='label') fig.update_layout(margin = dict(t=50, l=25, r=25, b=25)) st.plotly_chart(fig) dfa = pd.DataFrame( data={ 'text': ['entity extracted from file'], 'score': ['accuracy score'], 'label': ['label assigned to the extracted entity'], 'start': ['index of the start of the corresponding entity'], 'end': ['index of the end of the corresponding entity'], }) buf = io.BytesIO() with zipfile.ZipFile(buf, "w") as myzip: myzip.writestr("Summary of the results.csv", df.to_csv(index=False)) myzip.writestr("Glossary of labels.csv", dfa.to_csv(index=False)) with stylable_container( key="download_button", css_styles="""button { background-color: yellow; border: 1px solid black; padding: 5px; color: black; }""", ): st.download_button( label="Download zip file", data=buf.getvalue(), file_name="zip file.zip", mime="application/zip", ) st.divider() st.write(f"Number of times you requested results: {st.session_state['file_upload_attempts']}/{max_attempts}")