How hunterdii/smart-ai-resume-analyzer works
Project Type & Purpose
• This is a full-stack, AI-powered web application built with Streamlit that helps users analyze their resumes, receive job-specific recommendations, generate ATS-optimized resumes, and even scrape job listings.
• The project integrates user interfaces (front end), backend intelligence (machine learning and NLP modules), and persistent data storage (SQLite databases). It even includes external libraries (e.g., Poppler for PDF processing) and APIs (e.g., Google Gemini).
Analyzing the File Structure
• Key top-level files and directories:
• app.py and run_app.py: Main entry points for launching the application.
• config: Contains configurations (course recommendations, database parameters, job roles) used to drive functionality.
• dashboard: Implements UI components for displaying analytical insights.
• feedback: Manages user feedback including its database and schema.
• jobs: Consists of modules for scraping and aggregating job listings (e.g., from LinkedIn and other portals).
• resume_analytics: Likely contains core analysis logic focused on resume optimization.
• utils: Includes helper functions for various tasks, such as AI analysis (ai_resume_analyzer.py), resume parsing and building (resume_builder.py, resume_parser.py), database interactions, and Excel management.
• poppler (and poppler.zip): Provides PDF processing tools supporting resume document handling.
• Other supporting files include style resources, scripts for startup and deployment (Dockerfile, startup.sh), and a detailed README that further explains the tech stack and module roles.
Main Components
a. Frontend/UI Layer:
• Streamlit-based interactive web interface that renders pages for resume analysis, resume builder templates, job search, dashboards, and feedback.
• UI elements and static assets (HTML, CSS, JS, and style components).
b. Backend/Application Logic Layer:
• Core application logic in app.py and run_app.py that orchestrates functionalities.
• Business logic modules such as those in the “resume_analytics” and “utils” directories, including resume analysis, PDF extraction (with Poppler), CSV/Excel export, and resume parsing.
• Job scraping modules in the “jobs” folder that interface with external job portals and data sources.
• Dashboard components that aggregate analysis results and present dynamic insights.
c. Configuration & Integration Layer:
• “config” directory that holds course recommendations, database settings, and job role configurations.
• Environment setup (via .env in utils) for API keys (Google Gemini API) required by the AI optimization engine.
d. Data Storage/Database Layer:
• SQLite databases (resume_data.db, feedback.db) that store resumes, feedback, and possibly user or session data.
• Additional file-based data such as resume_data_export.xlsx facilitates data export.
e. External Libraries & Tools:
• Poppler library for PDF processing.
• Third-party modules used in the project (spaCy, scikit-learn, Plotly, Python-docx, PyPDF2, etc.) that tie into the resume analysis and UI enhancement.
Relationships & Data Flow
• The user interacts through the Streamlit UI (frontend), which sends requests to the backend (app.py, run_app.py) and passes inputs to the analysis modules.
• The backend makes use of configuration settings and utilities to process resume documents, perform AI-driven analysis, scrape job data, and update dashboards.
• Data persists through SQLite databases and is, in some cases, exported as Excel files for further processing.
• Integration with external APIs (e.g., Gemini API via environment variables) further enriches the analysis with advanced AI capabilities.
• Feedback data is separately managed in its own module and database to offer continuous improvement and tracking.
Architectural Patterns & Design Principles
• Modular design: Clear separation of concerns is evident with distinct directories handling configuration, user interfaces, job scraping, analysis, and utilities.
• Layered architecture: The system divides responsibilities across UI, business logic, integration, and data storage layers.
• Use of external libraries and APIs to enhance functionality without reinventing the wheel (e.g., PDF extraction using Poppler, NLP with spaCy).
• Emphasis on configuration and environment management (use of .env for sensitive API keys and configuration files) to allow easy adaptability and deployment.
• Since this is a resume analyzer tool, make sure to emphasize:
○ The separation between the interactive web UI (built with Streamlit) and the backend processing logic.
○ The integration with databases for storing resume and feedback data.
○ The AI and NLP modules utilized to extract insights and optimize resumes.
○ The external job scraping functionalities that gather job postings.
○ The configuration management that ties in with external APIs (e.g., Gemini API for advanced text analysis).