An AI-driven resume screening system that leverages multi-agent collaboration to evaluate candidate resumes against job descriptions with high precision.

• Smart PDF Parsing: Extracts text from complex resume layouts using specialized parsers.
• Multi-Agent Evaluation:
  • Resume Extractor: Identifies key skills, experience, and education from candidate profiles.
  • JD Extractor: Analyzes core requirements and expectations from job descriptions.
  • Candidate Evaluator: Scores the candidate and provides actionable feedback and suggestions.
• Dual Interface:
  • Streamlit UI: A sleek, user-friendly web interface for manual resume uploads and visualization.
  • FastAPI Backend: A robust API endpoint for programmatic resume screening integration.

• AI Models: Groq (Llama-3/Mixtral)
• Frontend: Streamlit
• Backend: FastAPI
• Libraries: PyPDF2, python-dotenv, requests, uvicorn

1. Clone the repository:

   git clone <your-repo-url>
   cd AGENTIC_RESUME_SCREENING

2. Create and activate a virtual environment:

   python -m venv venv
   # On Windows:
   venv\Scripts\activate
   # On macOS/Linux:
   source venv/bin/activate

3. Install dependencies:

   pip install -r requirements.txt

4. Set up environment variables: Create a .env file in the root directory and add your Groq API key:

   GROQ_API_KEY=your_api_key_here

5. Run the application:

   • Streamlit UI:

     streamlit run ui.py

   • FastAPI Backend:

     uvicorn app.main:app --reload

If something here caught your attention—a project, an idea, or even the way I structure my ML pipelines—I’d love to talk.

Open to:

• Internships
• Collaboration
• AI/ML discussions
• Interesting tech problems

📩 Reach out via LinkedIn or email — I respond faster than most APIs.

• LinkedIn: linkedin.com/in/kokila-m-ai-ds/
• Email: kokilakoki3376@gmail.com
• GitHub: github.com/kokilamariyayi