Update app.py

app.py

@@ -32,12 +32,11 @@ def get_similarity_score(model, data, query, corpus_embeddings):
     result.sort_values(by=['score', 'Last Day'], ascending=[False, True], inplace=True)
     return result
 
-@st.cache(ttl=24*3600)
+@st.cache(ttl=4*3600)
 def create_embedding(model: SentenceTransformer, data: pd.DataFrame, key: str) -> Tuple[list, list]:
     """Create vector embeddings from the dataset"""
     corpus_sentences = data[key].astype(str).tolist()
     corpus_embeddings = model.encode(sentences=corpus_sentences,
-                                     show_progress_bar=True,
                                      convert_to_tensor=True,
                                      normalize_embeddings=True)
     return corpus_embeddings
@@ -51,6 +50,14 @@ def load_dataset(columns: List) -> pd.DataFrame:
     data  = data.iloc[: , :7]
     data.columns = columns
     data.insert(0, 'ID', range(len(data)))
+    data['Full Name'] = data['Full Name'].str.title()
+    data['LinkedIn Profile'] = data['LinkedIn Profile'].str.lower()
+    data['LinkedIn Profile'] = np.where(data['LinkedIn Profile'].str.startswith('www.linkedin.com'),
+                                        "https://" + data['LinkedIn Profile'],
+                                        data['LinkedIn Profile'])
+    data['LinkedIn Profile'] = np.where(data['LinkedIn Profile'].str.startswith('linkedin.com'),
+                                        "https://www." + data['LinkedIn Profile'],
+                                        data['LinkedIn Profile'])
     return data
 
 def show_aggrid_table(result: pd.DataFrame):
@@ -78,8 +85,8 @@ def show_aggrid_table(result: pd.DataFrame):
         allow_unsafe_jscode=True,
     )
 
-def main():
-    """Main Function"""
+def show_heading():
+    """Show heading made using streamlit"""
     st.title('@ecommurz Talent Search Engine')
     st.markdown('''
         <div align="left">
@@ -92,32 +99,26 @@ def main():
     ''', unsafe_allow_html=True)
     st.write('This app lets you search and sort talent by job title or relevant job descriptions from ecommurz talent list in real-time.')
 
+def main():
+    """Main Function"""
+    show_heading()
+
     columns = ['Timestamp', 'Full Name', 'Company', 'Previous Role',
                'Experience (months)', 'Last Day', 'LinkedIn Profile']
     data = load_dataset(columns)
 
-    # Preprocess Data
-    data['Full Name'] = data['Full Name'].str.title()
-    data['LinkedIn Profile'] = data['LinkedIn Profile'].str.lower()
-    data['LinkedIn Profile'] = np.where(data['LinkedIn Profile'].str.startswith('www.linkedin.com'),
-                                        "https://" + data['LinkedIn Profile'],
-                                        data['LinkedIn Profile'])
-    data['LinkedIn Profile'] = np.where(data['LinkedIn Profile'].str.startswith('linkedin.com'),
-                                        "https://www." + data['LinkedIn Profile'],
-                                        data['LinkedIn Profile'])
-
-
-    # model = load_model()
-    # corpus_embeddings = create_embedding(model, data, 'Previous Role')
+    # Inference
+    model = load_model()
+    corpus_embeddings = create_embedding(model, data, 'Previous Role')
 
-    # job_title = st.text_input('Insert the job title below:', '')
-    # submitted = st.button('Submit')
+    job_title = st.text_input('Insert the job title below:', '')
+    submitted = st.button('Submit')
 
-    # if submitted:
-    #     st.info(f'Showing results for {job_title}')
-    #     result = get_similarity_score(model, data, job_title, corpus_embeddings)
-    #     result = result[columns]
-    #     show_aggrid_table(result)
+    if submitted:
+        st.info(f'Showing results for {job_title}')
+        result = get_similarity_score(model, data, job_title, corpus_embeddings)
+        result = result[columns]
+        show_aggrid_table(result)
 
 if __name__ == '__main__':
     main()