This project provides an intelligent AI-powered platform for resume analysis, mock interviews, and knowledge base RAG, targeting job seekers, HR professionals, and training institutions. It offers automated resume evaluation, personalized interview practice, and efficient knowledge retrieval, streamlining recruitment and skill development processes.

How It Works

The system leverages a modern stack including Spring Boot, Java 21, and Spring AI, integrating PostgreSQL with the pgvector extension for efficient vector storage and retrieval. Core functionalities like resume analysis and knowledge base vectorization are handled asynchronously via Redis Streams, decoupling these intensive tasks from the main request flow and allowing for independent scaling. Retrieval Augmented Generation (RAG) is employed for intelligent Q&A over the knowledge base, providing contextual and accurate responses.

Quick Start & Requirements

• Prerequisites: JDK 21+, Node.js 18+, PostgreSQL 14+ (with pgvector extension), Redis 6+, S3-compatible object storage (e.g., MinIO), and an AI API key (e.g., Alibaba DashScope).
• Local Setup: Clone the repository, configure database connection details and AI API keys in application.yml and environment variables, then run the backend with ./gradlew bootRun and the frontend using cd frontend && pnpm install && pnpm dev.
• Docker Deployment: A docker-compose.yml is provided for a one-click setup of all services (frontend, backend, PostgreSQL, Redis, MinIO). Requires Docker and Docker Compose installed, and AI API keys configured in a .env file.
• Documentation: API documentation is available via Swagger at http://localhost:8080.

Highlighted Details

• AI-Driven Features: Offers automated resume analysis across multiple formats (PDF, DOCX, DOC, TXT), personalized mock interviews with feedback, and RAG-powered knowledge base Q&A with streaming responses.
• Asynchronous Task Processing: Utilizes Redis Stream for background jobs like document vectorization and report generation, enhancing system responsiveness and scalability.
• Vector Database Integration: Employs PostgreSQL with pgvector for robust semantic search capabilities, crucial for RAG and resume content analysis.
• Comprehensive Document Handling: Supports various document types for both resume uploads and knowledge base content.

Maintenance & Community

The project welcomes contributions via Issues and Pull Requests. Specific details regarding core maintainers, active development, or community channels (like Discord/Slack) are not detailed in the README.

Licensing & Compatibility

The project is licensed under the AGPL-3.0 License. This strong copyleft license requires that any derivative works or services provided over a network that incorporate or are based on this software must also be made available under the AGPL-3.0 license, potentially restricting its use in closed-source commercial applications accessed via a network.

Limitations & Caveats

Key features like API rate limiting, advanced interview follow-up questions, and frontend performance optimizations are marked as TODOs. Careful management of JPA's ddl-auto setting is crucial during setup to prevent data loss. The system relies on external AI API keys, and the AGPL-3.0 license imposes significant obligations for network-based service deployments.