qader-ai 0.1.0

Python SDK for Qader AI services

Qader AI Library

A Python library for interacting with Qader AI services and AI processing utilities.

---

Features

• Python SDK for Qader AI
• Predict API
• Chat API
• Usage API
• Subscription API
• API Key Authentication
• Custom Exceptions
• AI Processing Utilities
• Duplicate Cleaning
• Configurable Settings

---

Requirements

• Python 3.9+
• requests
• pydantic
• pydantic-settings
• openai
• pandas
• numpy
• tqdm
• scikit-learn
• sentence-transformers
• pytest (for testing)
• responses (for testing)

Install the library:

pip install -e .

Install with testing dependencies included:

pip install -e ".[test]"

---

Prerequisites

This library is a client for the Qader backend API — it does not work standalone. Before using it, make sure:

1. The Qader backend is running and reachable (defaults to http://127.0.0.1:8000).
2. You have a valid API key. Create one via the backend's POST /api-keys/create endpoint (see the backend's /docs page for details).
3. That API key has an active subscription and remaining usage, otherwise calls will raise SubscriptionExpiredError or UsageLimitExceededError.

---

Project Structure

Qader-AI-Library/
│
├── src/
│   └── qader_ai/
│       ├── __init__.py
│       ├── sdk.py
│       ├── config.py
│       ├── exceptions.py
│       ├── clients.py
│       ├── duplicate_cleaner.py
│       ├── ai_processing/
│       │   ├── __init__.py
│       │   ├── ...
│       │
│       └── enums/
│           ├── __init__.py
│           ├── ...
│
├── tests/
│   ├── test_sdk_unit.py          # mocked, no backend needed
│   └── test_sdk_integration.py   # requires the backend running
│
├── README.md
├── pyproject.toml
└── requirements.txt

---

Installation

Clone the repository

git clone <repository-url>

Move to the project

cd Qader-AI-Library

Install the package

pip install -e .

---

Configuration

Configuration is managed through config.py, using environment variables (or a .env file in the project root).

Available SDK settings:

Setting	Default	Description
base_url	http://127.0.0.1:8000	The Qader backend's base URL
timeout	30	Request timeout in seconds

Example .env file:

base_url=http://127.0.0.1:8000
timeout=30

Additional AI processing settings are also available inside the same configuration file.

---

Quick Start

from qader_ai import QaderAI

client = QaderAI(
    api_key="YOUR_API_KEY"
)

---

Predict

result = client.predict(
    question="What is Artificial Intelligence?"
)

print(result)

---

Chat

result = client.chat(
    message="Hello!"
)

print(result)

---

Usage

result = client.usage(
    api_key_id=1
)

print(result)

---

Subscription

result = client.subscription(
    user_id=1
)

print(result)

---

Exception Handling

The library provides the following exceptions:

• QaderAIError — base exception for all library errors
• InvalidAPIKeyError — raised when the API key is missing, invalid, or inactive (HTTP 401)
• SubscriptionExpiredError — raised when the subscription is expired or inactive (HTTP 403)
• NotFoundError — raised when a requested usage or subscription record doesn't exist (HTTP 404)
• ValidationError — raised when the request data is invalid (HTTP 422)
• UsageLimitExceededError — raised when the API key has hit its usage limit (HTTP 429)
• RateLimitExceededError — raised when too many requests are sent in a short time window (HTTP 429)
• ServerError — raised for backend server errors (HTTP 500+)

Example:

from qader_ai.exceptions import InvalidAPIKeyError

try:
    client.predict("Hello")
except InvalidAPIKeyError:
    print("Invalid API Key")

---

Running Tests

Unit tests (mocked, no backend required):

pytest tests/test_sdk_unit.py -v

Integration tests (requires the Qader backend running locally):

pytest tests/test_sdk_integration.py -v

Run everything:

pytest -v

---

License

This project is intended for educational and internal use.