younessshr/xxrec-ai-matching

How younessshr/xxrec-ai-matching works

XXREC is an AI-assisted candidate–job matching service. Its primary workflow accepts a base64 PDF CV, extracts and redacts text, parses a structured profile, computes candidate–requisition features, and returns a LightGBM match score. Separate endpoints provide SHAP-backed explanations and personalized technical tests. The repository also contains an offline synthetic-data and model-training workflow. README_SETUP.md and DEPLOYMENT_GUIDE.md are present in the tree, but no README content or excerpts documenting additional capabilities were provided; connections below rely on the shown source and SOURCE INDEX.

Main entry points: main.py FastAPI endpoints · ai_pipeline.py Gemini pipeline · model_lgbm.pkl LightGBM model artifact · build_features.py Dataset feature engineering

Components 13

Matching API

FastAPI endpoints api/main.py
PDF text extraction api/main.py
Live feature computation api/main.py
SHAP explainer api/main.py

LLM features

PII redaction src/llm/redact.py
Gemini pipeline src/llm/ai_pipeline.py

Model workflow

Synthetic data generation src/ml/generate_dataset.py
Dataset feature engineering src/ml/build_features.py
Model training and ranking evaluation src/ml/train_model.py
Offline SHAP analysis src/ml/explain_model.py

Model artifacts

LightGBM model artifact data/model_lgbm.pkl

Other components

API client
Google Gemini

Connections 15

API client → FastAPI endpoints: sends requests api/main.py
FastAPI endpoints → PDF text extraction: extracts PDF text api/main.py
FastAPI endpoints → Gemini pipeline: parses CV api/main.py
Gemini pipeline → PII redaction: redacts text src/llm/ai_pipeline.py
Gemini pipeline → Google Gemini: requests generation src/llm/ai_pipeline.py
FastAPI endpoints → Live feature computation: computes features api/main.py
FastAPI endpoints → LightGBM model artifact: predicts scores api/main.py
FastAPI endpoints → SHAP explainer: computes contributions api/main.py
FastAPI endpoints → Gemini pipeline: generates explanations api/main.py
FastAPI endpoints → Gemini pipeline: generates tests api/main.py
Synthetic data generation → Dataset feature engineering: writes matching dataset src/ml/generate_dataset.py
Dataset feature engineering → Model training and ranking evaluation: writes feature dataset src/ml/build_features.py
Model training and ranking evaluation → LightGBM model artifact: saves model src/ml/train_model.py
Offline SHAP analysis → LightGBM model artifact: loads model src/ml/explain_model.py
FastAPI endpoints → API client: returns results api/main.py

Drawn by GitDiagram on November 10, 2026 from the repository's file tree, README and source files. Read as Markdown ·