Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,20 +1,16 @@
 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
 
 
 
@@ -97,9 +93,9 @@ if 'file_upload_attempts' not in st.session_state:
 max_attempts = 5
 
 # upload file
-upload_file = st.file_uploader("Upload your file. Accepted file formats include: .pdf, .docx", type=['pdf', 'docx'])
+upload_file_ner = 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:
     
@@ -128,96 +124,51 @@ if upload_file is not None:
 
         
 
-# 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:
+if st.button("Results", key="results_ner"):
+    if st.session_state['file_upload_attempts_ner'] >= 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", "country", "city", "organization", "date", "money", "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:
-                value_counts1 = df['label'].value_counts()
-                
-                df1 = pd.DataFrame(value_counts1)
-                
-                final_df = df1.reset_index().rename(columns={"index": "label"})
-                
-            col1, col2 = st.columns(2)
-            with col1:
-                fig1 = px.pie(final_df, values='count', names='label', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted labels')
-                fig1.update_traces(textposition='inside', textinfo='percent+label')
-                st.plotly_chart(fig1)
-            with col2:
-                fig2 = px.bar(final_df, x="count", y="label", color="label", text_auto=True, title='Occurrences of predicted labels')
-                st.plotly_chart(fig2)
-
-                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.session_state['file_upload_attempts_ner'] += 1
+    if upload_file_ner:
+        with st.spinner('Translating...'):  # More informative spinner text
+            try:
+                pipe_ner = get_translation_pipeline_en_el()
+                text_ner = pipe_ner(upload_file_ner)
+                if text_ner:
+                    translated_text_ner = text_ner[0]['translation_text']
+                    st.session_state.fernet_token_ner = generate_fernet_token(key_ner, translated_text_ner)
+                    st.write("**Translated text**: ", translated_text_ner)
                     st.download_button(
-                        label="Download zip file",
-                        data=buf.getvalue(),
-                        file_name="zip file.zip",
-                        mime="application/zip",
-                )
-                    
-
-
-
-
-
-            
-
+                        label="Download text",
+                        data=translated_text_ner,
+                        file_name="translation.txt",
+                        mime="text/plain",  # Specify the mime type
+                        on_click=None,
+                        type="primary",
+                        use_container_width=True, # Makes the button wider
+                        disabled=not translated_text_ner # Disable if no translation
+                    )
+            except IndexError:
+                st.error("The input text is too long. Please try a shorter text (up to 250 words).")
+            except Exception as e:
+                st.error(f"An unexpected error occurred during translation: {e}")
+elif 'fernet_token_ner' in st.session_state:
+    del st.session_state['fernet_token_ner']
+
+decrypted_data_streamlit_ner, error_streamlit_ner = validate_fernet_token(key_ner, st.session_state.fernet_token_ner if 'fernet_token_ner' in st.session_state else None, ttl_seconds=3600)
+if error_streamlit_ner:
+    if 'translated_text_ner' in locals():
+        st.warning("Please press Request Authorization.")
+        if st.button("Request Authorization", key="request_auth_ner"):
+            st.session_state.fernet_token_ner = generate_fernet_token(key_ner, translated_text_ner)
+            st.success("Authorization granted")
+            decrypted_data_streamlit_ner, error_streamlit_ner = validate_fernet_token(key_ner, st.session_state.fernet_token_ner, ttl=3600)
+        if error_streamlit_ner:
+            st.error(f"Your authorization has expired: {error_streamlit_ner}")
+            st.stop()
+        st.divider()
 
 st.divider()
-st.write(f"Number of times you requested results: {st.session_state['file_upload_attempts']}/{max_attempts}")
+st.write(f"Number of times you requested results: {st.session_state['file_upload_attempts_ner']}/{max_attempts}")
+st.divider()