Back to Home

AI Resume Analyser

An intelligent tool that analyzes resumes using AI to provide personalized feedback and insights

AI Resume Analyser Interface

Project Overview

The AI Resume Analyser is an intelligent ATS (Applicant Tracking System) tool that uses Google's Gemini AI to analyze resumes against job descriptions. It helps job seekers understand how well their resume matches specific job requirements and provides detailed feedback for improvement.

This Streamlit-based application processes PDF resumes, converts them to images for analysis, and uses advanced AI prompts to evaluate resume content against job descriptions. It provides percentage match scores, identifies missing keywords, and offers professional HR-level feedback on candidate alignment with role requirements.

Key Features

Resume Analysis Features

  • PDF resume upload and processing
  • Job description comparison analysis
  • Percentage match calculation
  • Missing keyword identification
  • Professional HR-level evaluation

AI-Powered Feedback

  • Strengths and weaknesses analysis
  • Candidate profile alignment assessment
  • Technical HR manager perspective
  • ATS scanner functionality
  • Detailed improvement recommendations

User Experience

Streamlit Interface

Clean, intuitive web interface for easy resume upload and analysis

Real-time Analysis

Instant feedback and percentage match calculations

PDF Processing

Automatic PDF to image conversion for AI analysis

Technical Architecture

The AI Resume Analyser is built using Python and Streamlit, leveraging Google's Gemini AI for intelligent resume analysis. The application focuses on simplicity and effectiveness in processing PDF resumes and providing actionable feedback.

Core Technologies

  • Python - Core programming language
  • Streamlit - Web application framework
  • Google Gemini AI - AI model for analysis
  • python-dotenv - Environment variable management

Processing Libraries

  • PDF2Image - PDF to image conversion
  • PIL (Pillow) - Image processing
  • Base64 - Image encoding for AI processing
  • IO - Byte stream handling

Google Gemini AI Integration

The application leverages Google's Gemini AI model to provide intelligent resume analysis and professional HR-level feedback. The AI processes both text and image data to deliver comprehensive resume evaluation.

Gemini 2.5 Flash Model

Uses Google's advanced Gemini 2.5 Flash model for fast and accurate analysis of resume content against job descriptions, providing professional HR-level insights.

Multimodal Processing

Processes both PDF images and text content for comprehensive analysis

Specialized AI Prompts

Custom-engineered prompts that simulate experienced Technical HR Managers and skilled ATS scanners to provide accurate percentage matches and detailed feedback.

Professional Evaluation

AI acts as an experienced HR professional providing detailed candidate assessment

Analysis Capabilities

Resume Evaluation

Professional assessment of resume against job requirements

Percentage Matching

Accurate calculation of resume-job description alignment

Keyword Analysis

Identification of missing keywords and skills

Data Processing Flow

The Resume Analyser follows a streamlined processing pipeline that converts PDF resumes to images and uses AI to provide professional analysis and feedback.

PDF Processing

  1. User uploads PDF resume through Streamlit interface
  2. PDF is converted to JPEG images using PDF2Image
  3. First page is extracted and converted to bytes
  4. Image is encoded to Base64 for AI processing
  5. Processed data is prepared for Gemini AI analysis

AI Analysis & Feedback

  1. Job description and resume are sent to Gemini AI
  2. AI analyzes resume against job requirements
  3. Professional HR-level evaluation is generated
  4. Percentage match and missing keywords are identified
  5. Detailed feedback and recommendations are provided

This efficient approach leverages Google's Gemini AI to provide professional-grade resume analysis that helps job seekers understand their alignment with specific roles and improve their application success rate.

Explore the Code

Check out the source code and documentation on GitHub

View on GitHub