Update src/streamlit_app.py

src/streamlit_app.py

@@ -20,43 +20,43 @@ st.markdown(
     <style>
     /* Main app background and text color */
     .stApp {
-        background-color: #E0FFFF; /* Light cyan, a very pale blue */
-        color: #000000; /* Black for the text */
+        background-color: #F3E5F5; /* A very light purple */
+        color: #1A0A26; /* Dark purple for the text */
     }
+
     /* Sidebar background color */
     .css-1d36184 {
-        background-color: #ADD8E6; /* Light blue for the sidebar */
-        secondary-background-color: #ADD8E6;
-    }
-        
-    /* Expander background color */
-    .streamlit-expanderContent {
-        background-color: #E0FFFF;
+        background-color: #D1C4E9; /* A medium light purple */
+        secondary-background-color: #D1C4E9;
     }
-    
-    /* Expander header background color */
-    .streamlit-expanderHeader {
-        background-color: #E0FFFF;
+
+    /* Expander background color and header */
+    .streamlit-expanderContent, .streamlit-expanderHeader {
+        background-color: #F3E5F5;
     }
+
     /* Text Area background and text color */
     .stTextArea textarea {
-        background-color: #B0E0E6; /* Powder blue, a light, soft blue */
-        color: #000000; /* Black for text */
+        background-color: #B39DDB; /* A slightly darker medium purple */
+        color: #1A0A26; /* Dark purple for text */
     }
+
     /* Button background and text color */
     .stButton > button {
-        background-color: #B0E0E6;
-        color: #000000;
+        background-color: #B39DDB;
+        color: #1A0A26;
     }
+
     /* Warning box background and text color */
     .stAlert.st-warning {
-        background-color: #87CEEB; /* Sky blue for the warning box */
-        color: #000000;
+        background-color: #9575CD; /* A medium-dark purple for the warning box */
+        color: #1A0A26;
     }
+
     /* Success box background and text color */
     .stAlert.st-success {
-        background-color: #87CEEB; /* Sky blue for the success box */
-        color: #000000;
+        background-color: #9575CD; /* A medium-dark purple for the success box */
+        color: #1A0A26;
     }
     </style>
     """,
@@ -66,22 +66,28 @@ st.markdown(
 
 
 
-
 # --- Page Configuration and UI Elements ---
 st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
-st.subheader("StoryCraft", divider="blue")
+st.subheader("MediaTagger", divider="violet")
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
 expander = st.expander("**Important notes**")
-expander.write("""**Named Entities:** This StoryCraft web app predicts eighteen (18) labels: "Person", "Organization", "Location", "Date", "Time", "Quantity", "Product", "Event", "Title", "Job_title", "Artwork", "Media", "URL", "Website", "Hashtag", "Email", "IP_address", "File_path"
+expander.write("""**Named Entities:** This MediaTagger web app predicts eighteen (18) labels: 'person', 'organization', 'location', 'date', 'time', 'event', 'title', 'product', 'law', 'policy', 'work of art', 'geopolitical entity', 'number', 'cause of death',
+'weapon', 'vehicle', 'facility', 'temporal expression'
+
 Results are presented in easy-to-read tables, visualized in an interactive tree map, pie chart and bar chart, and are available for download along with a Glossary of tags.      
+
 **How to Use:** Type or paste your text into the text area below, then press Ctrl + Enter. Click the 'Results' button to extract and tag entities in your text data.      
+
 **Usage Limits:** You can request results unlimited times for one (1) month.      
+
 **Supported Languages:** English 
+
 **Technical issues:** If your connection times out, please refresh the page or reopen the app's URL. 
+
 For any errors or inquiries, please contact us at info@nlpblogs.com""")
 
 with st.sidebar:
-    st.write("Use the following code to embed the StoryCraft web app on your website. Feel free to adjust the width and height values to fit your page.")
+    st.write("Use the following code to embed the MediaTagger web app on your website. Feel free to adjust the width and height values to fit your page.")
     code = '''
    <iframe
 	src="https://aiecosystem-storycraft.hf.space"
@@ -94,7 +100,7 @@ with st.sidebar:
     st.text("")
     st.text("")
     st.divider()
-    st.subheader("🚀 Ready to build your own NER Web App?", divider="blue")
+    st.subheader("🚀 Ready to build your own NER Web App?", divider="violet")
     st.link_button("NER Builder", "https://nlpblogs.com", type="primary")
 
 # --- Comet ML Setup ---
@@ -149,7 +155,7 @@ category_mapping = {
 def load_ner_model():
     """Loads the GLiNER model and caches it."""
     try:
-        return GLiNER.from_pretrained("gliner-community/gliner_large-v2.5", nested_ner=True, num_gen_sequences=2, gen_constraints= labels)
+        return GLiNER.from_pretrained("EmergentMethods/gliner_large_news-v2.1", nested_ner=True, num_gen_sequences=2, gen_constraints= labels)
     except Exception as e:
         st.error(f"Failed to load NER model. Please check your internet connection or model availability: {e}")
         st.stop()
@@ -189,7 +195,7 @@ if st.button("Results"):
                     experiment.log_parameter("input_text", text)
                     experiment.log_table("predicted_entities", df)
                 
-                st.subheader("Grouped Entities by Category", divider = "blue")
+                st.subheader("Grouped Entities by Category", divider = "violet")
                 
                 # Create tabs for each category
                 category_names = sorted(list(category_mapping.keys()))
@@ -217,9 +223,9 @@ if st.button("Results"):
                 st.divider()
                                 
                 # Tree map
-                st.subheader("Tree map", divider = "blue")
+                st.subheader("Tree map", divider = "violet")
                 fig_treemap = px.treemap(df, path=[px.Constant("all"), 'category', 'label', 'text'], values='score', color='category')
-                fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#E0FFFF', plot_bgcolor='#E0FFFF')
+                fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#F3E5F5', plot_bgcolor='#F3E5F5')
                 st.plotly_chart(fig_treemap)
                 
                 # Pie and Bar charts
@@ -228,12 +234,12 @@ if st.button("Results"):
                 col1, col2 = st.columns(2)
                 
                 with col1:
-                    st.subheader("Pie chart", divider = "blue")
+                    st.subheader("Pie chart", divider = "violet")
                     fig_pie = px.pie(grouped_counts, values='count', names='category', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted categories')
                     fig_pie.update_traces(textposition='inside', textinfo='percent+label')
                     fig_pie.update_layout(
-                        paper_bgcolor='#E0FFFF',
-                        plot_bgcolor='#E0FFFF'
+                        paper_bgcolor='#F3E5F5',
+                        plot_bgcolor='#F3E5F5'
                     )
                     st.plotly_chart(fig_pie)
                 
@@ -241,16 +247,16 @@ if st.button("Results"):
 
 
                 with col2:
-                    st.subheader("Bar chart", divider = "blue")
+                    st.subheader("Bar chart", divider = "violet")
                     fig_bar = px.bar(grouped_counts, x="count", y="category", color="category", text_auto=True, title='Occurrences of predicted categories')
                     fig_bar.update_layout(  # Changed from fig_pie to fig_bar
-                        paper_bgcolor='#E0FFFF',
-                        plot_bgcolor='#E0FFFF'
+                        paper_bgcolor='#F3E5F5',
+                        plot_bgcolor='#F3E5F5'
                     )
                     st.plotly_chart(fig_bar)
                 
                 # Most Frequent Entities
-                st.subheader("Most Frequent Entities", divider="blue")
+                st.subheader("Most Frequent Entities", divider="violet")
                 word_counts = df['text'].value_counts().reset_index()
                 word_counts.columns = ['Entity', 'Count']
                 repeating_entities = word_counts[word_counts['Count'] > 1]
@@ -258,8 +264,8 @@ if st.button("Results"):
                     st.dataframe(repeating_entities, use_container_width=True)
                     fig_repeating_bar = px.bar(repeating_entities, x='Entity', y='Count', color='Entity')
                     fig_repeating_bar.update_layout(xaxis={'categoryorder': 'total descending'},
-                        paper_bgcolor='#E0FFFF',
-                        plot_bgcolor='#E0FFFF')
+                        paper_bgcolor='#F3E5F5',
+                        plot_bgcolor='#F3E5F5')
                     st.plotly_chart(fig_repeating_bar)
                 else:
                     st.warning("No entities were found that occur more than once.")