Metadata-Version: 2.4
Name: noveum-sdk
Version: 1.1.0
Summary: Official Python SDK for the Noveum.ai API - AI/ML evaluation and testing platform
Author-email: Noveum Team <team@noveum.ai>
License: Apache-2.0
Project-URL: Homepage, https://noveum.ai
Project-URL: Repository, https://github.com/Noveum/noveum-sdk-python
Project-URL: Documentation, https://noveum.ai/docs
Project-URL: Bug Tracker, https://github.com/Noveum/noveum-sdk-python/issues
Project-URL: Changelog, https://github.com/Noveum/noveum-sdk-python/blob/main/CHANGELOG.md
Keywords: noveum,ai,ml,evaluation,testing,api,sdk,observability,llm,tracing
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: httpx<0.29.0,>=0.23.0
Requires-Dist: attrs>=22.2.0
Requires-Dist: python-dateutil>=2.8.0
Provides-Extra: dev
Requires-Dist: pytest>=9.0.0; extra == "dev"
Requires-Dist: pytest-cov>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=1.3.0; extra == "dev"
Requires-Dist: black>=24.0.0; extra == "dev"
Requires-Dist: isort>=5.0.0; extra == "dev"
Requires-Dist: ruff>=0.14.0; extra == "dev"
Requires-Dist: mypy>=1.5.0; extra == "dev"
Requires-Dist: types-python-dateutil>=2.8.0; extra == "dev"
Requires-Dist: bandit>=1.7.5; extra == "dev"
Requires-Dist: safety>=3.7.0; extra == "dev"
Requires-Dist: python-dotenv>=1.0.0; extra == "dev"

# Noveum SDK - Python Client

[![CI](https://github.com/Noveum/noveum-sdk-python/actions/workflows/ci.yml/badge.svg)](https://github.com/Noveum/noveum-sdk-python/actions/workflows/ci.yml)
[![Release](https://github.com/Noveum/noveum-sdk-python/actions/workflows/release.yml/badge.svg)](https://github.com/Noveum/noveum-sdk-python/actions/workflows/release.yml)
[![codecov](https://codecov.io/gh/Noveum/noveum-sdk-python/branch/main/graph/badge.svg)](https://codecov.io/gh/Noveum/noveum-sdk-python)
[![PyPI version](https://badge.fury.io/py/noveum-sdk-python.svg)](https://badge.fury.io/py/noveum-sdk-python)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)

[![Noveum Platform](https://img.shields.io/badge/Noveum-Platform-blue?style=flat&logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMjQiIGhlaWdodD0iMjQiIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj48cGF0aCBkPSJNMTIgMkw0IDdWMTdMMTIgMjJMMjAgMTdWN0wxMiAyWiIgZmlsbD0id2hpdGUiLz48L3N2Zz4=)](https://noveum.ai/)
[![noveum-trace](https://img.shields.io/pypi/v/noveum-trace.svg?label=noveum-trace&color=green)](https://pypi.org/project/noveum-trace/)
[![AI Observability](https://img.shields.io/badge/AI-Observability-orange?style=flat)](https://noveum.ai/)
[![LLM Evaluation](https://img.shields.io/badge/LLM-Evaluation-purple?style=flat)](https://noveum.ai/)

A professional Python SDK for the [Noveum.ai](https://noveum.ai) API. Provides both high-level convenience methods and low-level access to core API endpoints for AI/ML evaluation, testing, and observability.

## Features

- **Core API Coverage** - Essential endpoints for datasets, traces, scorers, projects, and ETL jobs
- **Full IDE Support** - Complete type hints, autocomplete, and docstrings
- **Async & Sync** - Both async/await and synchronous support
- **Secure** - API key authentication, HTTPS only, proper error handling
- **Well-Documented** - Comprehensive guides, examples, and inline documentation
- **Production-Ready** - Extensive test suite with integration and unit tests
- **Easy to Use** - High-level wrapper for common operations

## Quick Start

### Installation

#### From PyPI (Recommended)

```bash
pip install noveum-sdk-python
```

#### From Source

```bash
# Clone the repository
git clone https://github.com/Noveum/noveum-sdk-python.git
cd noveum-sdk-python

# Upgrade pip and setuptools (required for PEP 621)
pip install --upgrade pip setuptools wheel

# Install in development mode
pip install -e .

# Or install with dev dependencies for development
pip install -e ".[dev]"
```

### Basic Usage (High-Level Client)

```python
import os
from noveum_api_client import NoveumClient

# Get API key from environment
api_key = os.getenv("NOVEUM_API_KEY")

# Initialize client
client = NoveumClient(api_key=api_key)

# List datasets
datasets = client.list_datasets(limit=10)
print(f"Found {len(datasets['data'])} datasets")

# Get dataset items
items = client.get_dataset_items("my-dataset", limit=50)
for item in items["data"]:
    print(f"Item: {item}")

# Get evaluation results
results = client.get_results(dataset_slug="my-dataset")
print(f"Results: {results['data']}")
```

### Setting Your API Key

**Option 1: Environment Variable (Recommended)**
```bash
export NOVEUM_API_KEY="nv_your_api_key_here"
```

Then use it in code:
```python
import os
from noveum_api_client import NoveumClient

api_key = os.getenv("NOVEUM_API_KEY")
client = NoveumClient(api_key=api_key)
```

**Option 2: Direct Initialization**
```python
from noveum_api_client import NoveumClient

client = NoveumClient(api_key="nv_your_api_key_here")
```

**Option 3: .env File**
```bash
# Create .env file
echo "NOVEUM_API_KEY=nv_your_api_key_here" > .env
```

Then load it:
```python
import os
from dotenv import load_dotenv
from noveum_api_client import NoveumClient

load_dotenv()
api_key = os.getenv("NOVEUM_API_KEY")
client = NoveumClient(api_key=api_key)
```

## API Reference

### High-Level Client (NoveumClient)

The `NoveumClient` class provides convenient methods for common operations. Use this for most use cases.

#### Methods

**`list_datasets(limit=20, offset=0)`**

List all datasets in your organization.

```python
response = client.list_datasets(limit=10)
print(f"Status: {response['status_code']}")
print(f"Datasets: {response['data']}")
```

**Parameters:**
- `limit` (int): Number of datasets to return (default: 20)
- `offset` (int): Pagination offset (default: 0)

**Returns:** Dictionary with `status_code`, `data`, and `headers`

---

**`get_dataset_items(dataset_slug, limit=20, offset=0)`**

Get items from a specific dataset.

```python
items = client.get_dataset_items("my-dataset", limit=100)
for item in items["data"]:
    print(f"Item ID: {item['id']}, Input: {item['input']}")
```

**Parameters:**
- `dataset_slug` (str): The dataset slug (required)
- `limit` (int): Number of items to return (default: 20)
- `offset` (int): Pagination offset (default: 0)

**Returns:** Dictionary with `status_code`, `data`, and `headers`

---

**`get_results(dataset_slug=None, item_id=None, scorer_id=None, limit=100, offset=0)`**

Get evaluation results with optional filtering.

```python
# Get all results
results = client.get_results()

# Filter by dataset
results = client.get_results(dataset_slug="my-dataset")

# Filter by item
results = client.get_results(item_id="item-123")

# Filter by scorer
results = client.get_results(scorer_id="factuality_scorer")
```

**Parameters:**
- `dataset_slug` (str): Filter by dataset slug (optional)
- `item_id` (str): Filter by item ID (optional)
- `scorer_id` (str): Filter by scorer ID (optional)
- `limit` (int): Number of results to return (default: 100)
- `offset` (int): Pagination offset (default: 0)

**Returns:** Dictionary with `status_code`, `data`, and `headers`

---

### Low-Level Client (Client)

For advanced use cases, access the generated API directly with full control.

```python
from noveum_api_client import Client
from noveum_api_client.api.datasets import get_api_v1_datasets

# Create low-level client
client = Client(
    base_url="https://api.noveum.ai",
    headers={"Authorization": f"Bearer {api_key}"}
)

# Call API directly
response = get_api_v1_datasets.sync_detailed(
    client=client,
    limit=20,
    offset=0
)

print(f"Status: {response.status_code}")
print(f"Data: {response.parsed}")
```

## Available API Endpoints

The SDK provides access to the following API categories:

| Category | Description |
|----------|-------------|
| `health/` | Health check endpoint |
| `status/` | API status endpoint |
| `datasets/` | Dataset CRUD operations |
| `traces/` | Trace management and querying |
| `scorers/` | Scorer definitions and management |
| `scorer_results/` | Evaluation results |
| `projects/` | Project management |
| `etl_jobs/` | ETL job operations |

### Example: Using Traces API

```python
from noveum_api_client import Client
from noveum_api_client.api.traces import get_api_v1_traces, post_api_v1_traces

client = Client(
    base_url="https://api.noveum.ai",
    headers={"Authorization": f"Bearer {api_key}"}
)

# List traces
response = get_api_v1_traces.sync_detailed(client=client)
print(f"Traces: {response.parsed}")
```

### Example: Using Scorers API

```python
from noveum_api_client.api.scorers import get_api_v1_scorers

# List scorers
response = get_api_v1_scorers.sync_detailed(client=client)
print(f"Scorers: {response.parsed}")
```

### Example: Using ETL Jobs API

```python
from noveum_api_client.api.etl_jobs import get_api_v1_etl_jobs

# List ETL jobs
response = get_api_v1_etl_jobs.sync_detailed(client=client)
print(f"ETL Jobs: {response.parsed}")
```

## Common Use Cases

### Use Case 1: CI/CD Regression Testing

Test your model/agent quality in CI/CD pipelines:

```python
from noveum_api_client import NoveumClient

def test_agent_quality():
    client = NoveumClient(api_key="nv_...")
    
    # Get test dataset
    items = client.get_dataset_items("regression-tests")
    
    # Evaluate each item
    failed = 0
    for item in items["data"]:
        # Run your agent/model
        output = my_agent.run(item["input"])
        
        # Get evaluation results
        results = client.get_results(item_id=item["id"])
        
        # Check quality
        for result in results["data"]:
            if result.get("score", 0) < 0.8:
                print(f"Item {item['id']} failed: {result['score']}")
                failed += 1
    
    # Assert
    assert failed == 0, f"{failed} items failed quality check"
    print("All items passed quality check")

# Run test
test_agent_quality()
```

### Use Case 2: Batch Processing

Process all items in a dataset:

```python
from noveum_api_client import NoveumClient

client = NoveumClient(api_key="nv_...")

# Get all items (with pagination)
offset = 0
while True:
    items = client.get_dataset_items("my-dataset", limit=100, offset=offset)
    
    if not items["data"]:
        break
    
    # Process each item
    for item in items["data"]:
        print(f"Processing item {item['id']}")
        # Your processing logic here
    
    offset += 100
```

### Use Case 3: Result Analysis

Analyze evaluation results:

```python
from noveum_api_client import NoveumClient

client = NoveumClient(api_key="nv_...")

# Get all results
results = client.get_results(limit=1000)

# Analyze
total = len(results["data"])
passed = sum(1 for r in results["data"] if r.get("passed"))
avg_score = sum(r.get("score", 0) for r in results["data"]) / total if total > 0 else 0

print(f"Total: {total}")
print(f"Passed: {passed} ({passed/total*100:.1f}%)")
print(f"Average Score: {avg_score:.2f}")
```

### Use Case 4: Async Operations

Use async for concurrent operations:

```python
import asyncio
from noveum_api_client import Client
from noveum_api_client.api.datasets import get_api_v1_datasets

async def main():
    api_key = "nv_..."
    client = Client(
        base_url="https://api.noveum.ai",
        headers={"Authorization": f"Bearer {api_key}"}
    )
    
    # Async call
    response = await get_api_v1_datasets.asyncio_detailed(client=client)
    print(f"Status: {response.status_code}")
    print(f"Datasets: {response.parsed}")

# Run
asyncio.run(main())
```

## Configuration

### Custom Base URL

```python
client = NoveumClient(
    api_key="nv_...",
    base_url="https://custom.api.noveum.ai"
)
```

### Custom Timeout

```python
import httpx
from noveum_api_client import Client

client = Client(
    base_url="https://api.noveum.ai",
    timeout=httpx.Timeout(30.0)  # 30 second timeout
)
```

### Context Manager

```python
from noveum_api_client import NoveumClient

# Automatically closes connection
with NoveumClient(api_key="nv_...") as client:
    datasets = client.list_datasets()
    # Connection automatically closed
```

## Response Format

All high-level client methods return a dictionary with:

```python
{
    "status_code": 200,           # HTTP status code
    "data": {...},                # Response data (parsed JSON)
    "headers": {...}              # Response headers
}
```

Check `status_code` to verify success:

```python
response = client.list_datasets()

if response["status_code"] == 200:
    print(f"Success: {response['data']}")
else:
    print(f"Error: {response['status_code']}")
```

## Error Handling

### Handle API Errors

```python
from noveum_api_client import NoveumClient

client = NoveumClient(api_key="nv_...")

try:
    response = client.list_datasets()
    
    if response["status_code"] != 200:
        print(f"API Error: {response['status_code']}")
        print(f"Response: {response['data']}")
    else:
        print(f"Success: {response['data']}")
        
except Exception as e:
    print(f"Error: {e}")
```

### Handle Network Errors

```python
import httpx
from noveum_api_client import NoveumClient

client = NoveumClient(api_key="nv_...")

try:
    response = client.list_datasets()
except httpx.ConnectError:
    print("Connection error - check your internet connection")
except httpx.TimeoutException:
    print("Request timeout - API is slow or unreachable")
except Exception as e:
    print(f"Unexpected error: {e}")
```

## Testing

For detailed testing instructions, see [TESTING.md](TESTING.md).

### Quick Start

```bash
# Install with dev dependencies
pip install -e ".[dev]"

# Run unit tests (fast, no API key needed)
pytest tests/unit/ -v

# Run integration tests (requires API key)
export NOVEUM_API_KEY="nv_your_api_key"
pytest tests/integration/ -v

# Run all tests with coverage
pytest tests/ -v --cov=noveum_api_client --cov-report=term-missing
```

## Architecture

### Project Structure

```
noveum-sdk-python/
├── noveum_api_client/           # Main package
│   ├── __init__.py              # Public API exports
│   ├── client.py                # Generated base client
│   ├── noveum_client.py         # High-level wrapper
│   ├── errors.py                # Error definitions
│   ├── types.py                 # Type definitions
│   ├── py.typed                 # PEP 561 type marker
│   ├── api/                     # Generated API endpoints
│   │   ├── datasets/            # Dataset operations
│   │   ├── etl_jobs/            # ETL job management
│   │   ├── health/              # Health check
│   │   ├── projects/            # Project operations
│   │   ├── scorers/             # Scorer operations
│   │   ├── scorer_results/      # Evaluation results
│   │   ├── status/              # Status endpoint
│   │   └── traces/              # Trace operations
│   └── models/                  # Data models
├── tests/                       # Test suite
│   ├── integration/             # Integration tests with live API
│   │   ├── test_datasets.py     # Dataset tests
│   │   ├── test_etl_jobs.py     # ETL job tests
│   │   ├── test_projects.py     # Project tests
│   │   ├── test_scorers.py      # Scorer tests
│   │   ├── test_scorer_results.py # Scorer results tests
│   │   └── test_traces.py       # Trace tests
│   └── unit/                    # Unit tests (mocked)
├── doc/                         # Documentation
├── README.md                    # This file
├── CHANGELOG.md                 # Version history
├── CONTRIBUTING.md              # Contribution guidelines
└── pyproject.toml               # Project configuration
```

### Two-Layer Architecture

**Layer 1: Generated API Client**
- Auto-generated from OpenAPI schema
- Low-level access to all endpoints
- Full control over parameters
- Both sync and async support

**Layer 2: High-Level Wrapper (NoveumClient)**
- Convenient methods for common operations
- Simplified API for typical use cases
- Automatic error handling
- Better developer experience

## Related Packages

The Noveum ecosystem includes multiple specialized packages:

- **[noveum-trace](https://pypi.org/project/noveum-trace/)** - Lightweight tracing SDK for LLM applications and multi-agent systems with decorator-based API
- **[noveum-sdk-python](https://pypi.org/project/noveum-sdk-python/)** - This package - comprehensive API client for evaluation, datasets, and platform management

## Support

- **Platform**: https://noveum.ai/
- **PyPI Package**: https://pypi.org/project/noveum-sdk-python/
- **API Documentation**: https://noveum.ai/docs
- **GitHub Repository**: https://github.com/Noveum/noveum-sdk-python
- **GitHub Issues**: https://github.com/Noveum/noveum-sdk-python/issues
- **Email**: support@noveum.ai

## License

Apache 2.0 License - See LICENSE file for details

## Contributing

Contributions welcome! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.

## Changelog

See [CHANGELOG.md](CHANGELOG.md) for version history and updates.

---

**Status**: Production Ready  
**Last Updated**: January 16, 2026  
**Version**: 1.0.3
