YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
π§ TatvaMind AI Career Engine
AI-Powered Resume Analysis using RAG + LLMs
π¬ Overview
TatvaMind AI Career Engine is a production-oriented AI system that analyzes resumes against job descriptions using Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs).
The system provides:
- π Match Score
- β Missing Skills
- π‘ Actionable Suggestions
Built under TatvaMind Intelligence Lab, this project focuses on combining semantic retrieval with intelligent reasoning.
βοΈ How It Works
The system follows a structured pipeline:
flowchart LR
A[Resume] --> C[Parsing]
B[Job Description] --> C
C --> D[Chunking]
D --> E[Embeddings]
E --> F[ChromaDB]
F --> G[Retrieval]
G --> H[LLM]
H --> I[Scoring]
I --> J[Output]
The pipeline ensures that the LLM receives relevant context, improving accuracy and reliability.
π§ Key Components
πΉ RAG Pipeline
- Context-aware retrieval
- Semantic matching
- Improved LLM reasoning
πΉ Embeddings + Vector DB
- ChromaDB for storage
- Efficient similarity search
πΉ Scoring Engine
- Keyword matching
- Semantic similarity
- Section-wise evaluation
π§© Tech Stack
- Backend: FastAPI
- Frontend: Next.js
- Vector DB: ChromaDB
- AI: LLM APIs + Embeddings
π Features
- Resume parsing (PDF/DOCX)
- Semantic job matching
- Intelligent scoring
- Context-aware suggestions
π Project Structure
backend/
frontend/
deployment/
π Links
- π Website: [Add Link]
- π» GitHub: [Add Link]
- π Article: [Add Link]
π€ Author
Nikhil Ranjan
Founder, TatvaMind Intelligence Lab
π Note
This project represents ongoing work in applied AI systems and RAG-based architectures.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support