Create app.py

app.py

@@ -0,0 +1,123 @@
+import streamlit as st
+import os
+import tempfile
+from pathlib import Path
+import time
+from typing import List, Dict
+import pandas as pd
+
+# Initialize Streamlit app
+st.set_page_config(
+    page_title="IntraTalent Resume Processor",
+    page_icon="📄",
+    layout="wide"
+)
+
+def save_uploaded_file(uploaded_file) -> str:
+    """Save uploaded file to temporary directory and return path."""
+    try:
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp_file:
+            tmp_file.write(uploaded_file.getvalue())
+            return tmp_file.name
+    except Exception as e:
+        st.error(f"Error saving file: {e}")
+        return None
+
+def process_resumes(uploaded_files: List[st.UploadedFile]) -> Dict:
+    """Process multiple resumes and return results."""
+    results = {}
+    progress_bar = st.progress(0)
+    
+    for idx, file in enumerate(uploaded_files):
+        if file.type != "application/pdf":
+            st.warning(f"Skipping {file.name}: Not a PDF file")
+            continue
+            
+        temp_path = save_uploaded_file(file)
+        if temp_path:
+            try:
+                name, projects = parse_resume(temp_path)
+                results[file.name] = {
+                    "name": name,
+                    "projects": projects
+                }
+                # Update progress
+                progress_bar.progress((idx + 1) / len(uploaded_files))
+            except Exception as e:
+                st.error(f"Error processing {file.name}: {e}")
+            finally:
+                # Clean up temporary file
+                os.unlink(temp_path)
+                
+    return results
+
+def display_results(results: Dict):
+    """Display processed resume results in an organized manner."""
+    if not results:
+        return
+        
+    st.subheader("Processed Resumes")
+    
+    for filename, data in results.items():
+        with st.expander(f"📄 {data['name']} ({filename})"):
+            if data['projects']:
+                df = pd.DataFrame(data['projects'])
+                st.dataframe(
+                    df,
+                    column_config={
+                        "name": "Project Name",
+                        "description": "Description"
+                    },
+                    hide_index=True
+                )
+            else:
+                st.info("No projects found in this resume")
+
+def main():
+    st.title("IntraTalent Resume Processor")
+    
+    # File uploader section
+    st.header("Upload Resumes")
+    uploaded_files = st.file_uploader(
+        "Upload up to 10 resumes (PDF only)",
+        type=['pdf'],
+        accept_multiple_files=True,
+        key="resume_uploader"
+    )
+    
+    # Validate number of files
+    if len(uploaded_files) > 10:
+        st.error("Maximum 10 files allowed. Please remove some files.")
+        return
+        
+    # Process button
+    if uploaded_files and st.button("Process Resumes"):
+        with st.spinner("Processing resumes..."):
+            results = process_resumes(uploaded_files)
+            st.session_state['processed_results'] = results
+            display_results(results)
+    
+    # Query section
+    st.header("Search Projects")
+    query = st.text_area(
+        "Enter your project requirements",
+        placeholder="Example: Looking for team members with experience in machine learning and computer vision...",
+        height=100
+    )
+    
+    if query and st.button("Search"):
+        if 'processed_results' not in st.session_state:
+            st.warning("Please process some resumes first!")
+            return
+            
+        with st.spinner("Searching for matches..."):
+            # Here you would implement the embedding and similarity search
+            # Using the code from your original script
+            st.success("Search completed!")
+            # Display results in a nice format
+            st.subheader("Top Matches")
+            # Placeholder for search results
+            st.info("Feature coming soon: Will display matching projects and candidates based on similarity search")
+
+if __name__ == "__main__":
+    main()