Update app.py

app.py

@@ -40,20 +40,18 @@ with st.sidebar:
 ''')
 
 
-
-             
 txt = st.text_area("Job description", key = "text 1")
 job = pd.Series(txt, name="Text")
-st.dataframe(job)
+
 
 if 'upload_count' not in st.session_state:
     st.session_state['upload_count'] = 0
 
-max_attempts = 2
+max_attempts = 3
 
 if st.session_state['upload_count'] < max_attempts:
     uploaded_files = st.file_uploader(
-        "Choose a PDF file", accept_multiple_files=True, type="pdf", key="candidate_upload"
+        "Choose a PDF file", accept_multiple_files=True, type="pdf", key="candidate 1"
     )
 
 if uploaded_files:
@@ -64,18 +62,17 @@ for uploaded_file in uploaded_files:
     for page in pdf_reader.pages:
         text_data += page.extract_text()
         data = pd.Series(text_data, name = 'Text')
-        st.dataframe(data)
+        
         
         frames = [job, data]
         result = pd.concat(frames)
-        st.dataframe(result)
+        
 
-        model = GLiNER.from_pretrained("xomad/gliner-model-merge-large-v1.0")
-        labels = ["person", "country", "city", "organization", "date", "money", "percent value", "position"]
+        model = GLiNER.from_pretrained("urchade/gliner_base")
+        labels = ["person", "country","organization", "date", "time", "role", "skills", "year"]
         entities = model.predict_entities(text_data, labels)
         df = pd.DataFrame(entities)
-        st.dataframe(entities)
-        st.dataframe(df)
+        
 
         import plotly.express as px
         fig = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
@@ -89,15 +86,13 @@ for uploaded_file in uploaded_files:
         tfidf_matrix = vectorizer.fit_transform(result)
         tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
         st.subheader("TF-IDF Values:")
-        st.dataframe(tfidf_df)
+        
         
         cosine_sim_matrix = cosine_similarity(tfidf_matrix)
         cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
-        st.subheader("Cosine Similarity Matrix:")
-        st.dataframe(cosine_sim_df)
+        
 
-        import plotly.express as px
-        st.subheader("A score closer to 1 means closer match")
+        
         
         fig = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Cosine similarity", y="Text", color="Productivity"),
                         x=['text1', 'Jon Description'],
@@ -114,6 +109,3 @@ else:
 if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
     st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
 
-
-                
-