Synentra Intent Classification Model - Community edition

This repository contains code and resources for training, evaluating, and deploying an intent classification model. The system is designed to classify user intents from natural language input, enabling downstream policy enforcement and decision-making in the Synentra ecosystem.

Overview

The project provides:

• A pipeline for generating synthetic and curated training data\
• Model training and evaluation scripts\
• Export to optimized runtime formats (e.g., ONNX)\
• Integration-ready inference components

Typical use cases include:

• AI agent action classification\
• API intent detection\
• Security and policy enforcement triggers

Getting Started

Prerequisites

• Python 3.8 or higher\
• pip or compatible package manager\
• (Optional) GPU support for faster training

Install dependencies:

pip install -r requirements.txt

Installation

Clone the repository:

git clone <repository-url>
cd <repository-directory>

Usage

1. Generate Training Data

python src/generate_training_data.py

2. Train the Model

python src/train_intent_classifier.py

Model Deployment

• ONNX: src/intent_model_onnx/

License

Apache 2.0