import streamlit as st import pandas as pd import plotly.express as px from datetime import datetime import json import os from pathlib import Path import logging from typing import List, Dict, Any from openai import OpenAI from dotenv import load_dotenv #from llm_job_assistant import LLMJobAssistant # Our previous class class JobAssistantUI: def __init__(self): self.setup_streamlit() self.load_dotenv() self.assistant = LLMJobAssistant() def setup_streamlit(self): """Configure Streamlit page settings""" st.set_page_config( page_title="AI Job Search Assistant", page_icon="🔍", layout="wide", initial_sidebar_state="expanded" ) def load_dotenv(self): """Load environment variables""" os.environ['PATH'] += f':{os.path.expanduser("~/.cargo/bin")}' load_dotenv() if not os.getenv('OPENAI_API_KEY'): st.sidebar.error("OpenAI API key not found. Please set it in .env file") def render_sidebar(self): """Render sidebar controls""" with st.sidebar: st.title("Search Settings") # Job Search Settings st.subheader("Job Search Criteria") keywords = st.text_area( "Search Keywords (one per line)", value="\n".join(self.assistant.config['keywords']) ) self.assistant.config['keywords'] = [k.strip() for k in keywords.split("\n") if k.strip()] # Location Settings location_type = st.radio( "Location Type", ["Remote Only", "Hybrid", "All Locations"] ) # Experience Level experience_level = st.multiselect( "Experience Level", ["Entry Level", "Mid Level", "Senior", "Lead"], default=["Entry Level", "Mid Level"] ) # Salary Range min_salary = st.slider( "Minimum Salary (USD)", 0, 200000, self.assistant.config['minimum_salary'], step=5000 ) # Save Settings if st.button("Save Settings"): self.assistant.config['minimum_salary'] = min_salary self.assistant.save_config() st.success("Settings saved!") def render_job_search_tab(self): """Render job search tab""" st.header("Job Search") col1, col2 = st.columns([2, 1]) with col1: if st.button("Start New Job Search", type="primary"): with st.spinner("Searching for jobs..."): jobs_df = self.assistant.run_enhanced_job_search() st.session_state['jobs_df'] = jobs_df st.success(f"Found {len(jobs_df)} matching jobs!") with col2: if st.button("Load Previous Results"): try: jobs_df = pd.read_pickle('enhanced_jobs.pkl') st.session_state['jobs_df'] = jobs_df st.success("Previous results loaded!") except FileNotFoundError: st.error("No previous results found") if 'jobs_df' in st.session_state: self.display_job_results(st.session_state['jobs_df']) def display_job_results(self, df: pd.DataFrame): """Display job search results""" st.subheader("Search Results") # Filters col1, col2, col3 = st.columns(3) with col1: companies = st.multiselect( "Filter by Company", options=sorted(df['company'].unique()) ) with col2: min_match = st.slider( "Minimum Match Score", 0, 100, 50 ) with col3: sort_by = st.selectbox( "Sort by", ["Match Score", "Company", "Date Posted"] ) # Filter DataFrame filtered_df = df.copy() if companies: filtered_df = filtered_df[filtered_df['company'].isin(companies)] filtered_df = filtered_df[filtered_df['analysis.match_score'] >= min_match] # Sort DataFrame if sort_by == "Match Score": filtered_df = filtered_df.sort_values('analysis.match_score', ascending=False) elif sort_by == "Company": filtered_df = filtered_df.sort_values('company') else: filtered_df = filtered_df.sort_values('date_scraped', ascending=False) # Display results for _, job in filtered_df.iterrows(): with st.expander(f"{job['title']} at {job['company']} - Match: {job['analysis']['match_score']}%"): col1, col2 = st.columns([2, 1]) with col1: st.write("**Job Description:**") st.write(job['full_description']) st.write("**Required Skills:**") for skill in job['analysis']['required_skills']: st.markdown(f"- {skill}") with col2: st.write("**Salary Range:**") st.write(job['analysis']['estimated_salary_range']) st.write("**Experience Required:**") st.write(job['analysis']['required_experience']) if st.button("Generate Application Materials", key=job['url']): with st.spinner("Generating materials..."): cover_letter = self.assistant.generate_custom_cover_letter( job['analysis'], job['company'] ) resume_suggestions = self.assistant.tailor_resume(job['analysis']) st.download_button( "Download Cover Letter", cover_letter, file_name=f"cover_letter_{job['company']}.txt" ) st.download_button( "Download Resume Suggestions", resume_suggestions, file_name=f"resume_suggestions_{job['company']}.txt" ) def render_analytics_tab(self): """Render analytics tab""" st.header("Job Search Analytics") if 'jobs_df' in st.session_state: df = st.session_state['jobs_df'] col1, col2 = st.columns(2) with col1: # Match Score Distribution fig = px.histogram( df, x='analysis.match_score', title='Distribution of Match Scores', labels={'analysis.match_score': 'Match Score'} ) st.plotly_chart(fig) with col2: # Company Distribution company_counts = df['company'].value_counts().head(10) fig = px.bar( company_counts, title='Top Companies', labels={'value': 'Number of Jobs', 'index': 'Company'} ) st.plotly_chart(fig) # Salary Distribution fig = px.box( df, y='analysis.estimated_salary_range', title='Salary Distribution' ) st.plotly_chart(fig) def render_settings_tab(self): """Render settings tab""" st.header("Application Settings") # Resume Upload st.subheader("Resume") resume_file = st.file_uploader("Upload your resume (TXT format)", type=['txt']) if resume_file: resume_text = resume_file.read().decode() with open('templates/base_resume.txt', 'w') as f: f.write(resume_text) st.success("Resume uploaded successfully!") # API Settings st.subheader("API Settings") api_key = st.text_input( "OpenAI API Key", value=os.getenv('OPENAI_API_KEY', ''), type="password" ) if st.button("Save API Key"): with open('.env', 'w') as f: f.write(f"OPENAI_API_KEY={api_key}") st.success("API key saved!") def run(self): """Run the Streamlit application""" st.title("AI Job Search Assistant") # Render sidebar self.render_sidebar() # Main content tabs tab1, tab2, tab3 = st.tabs(["Job Search", "Analytics", "Settings"]) with tab1: self.render_job_search_tab() with tab2: self.render_analytics_tab() with tab3: self.render_settings_tab() def main(): app = JobAssistantUI() app.run() if __name__ == "__main__": main()