wurun 0.2.1

Async OpenAI API wrapper for Jupyter notebooks

Wurun

Async OpenAI API wrapper optimized for Jupyter notebooks with connection pooling, retry logic, and batch processing.

Features

• HTTP/2 Connection Pooling - Shared client for efficient API calls
• Robust Retry Logic - Exponential backoff for rate limits and errors
• Batch Processing - Concurrent API calls with semaphore control
• Jupyter Optimized - Clean notebook output and error handling
• Zero Configuration - Simple setup, works with OpenAI and Azure OpenAI

Installation

# Production use
pip install .

# Development (includes testing tools)
pip install ".[dev]"

Quick Start

from wurun import Wurun

# Setup once per kernel
await Wurun.setup(
    endpoint="https://api.openai.com/v1",
    api_key="your-api-key",
    deployment_name="gpt-3.5-turbo"
)

# Single question
messages = [{"role": "user", "content": "Explain asyncio"}]
answer = await Wurun.ask(messages)
print(answer)

# Custom parameters
answer = await Wurun.ask(messages, max_tokens=512, temperature=0.7)

# Batch processing
questions = [
    [{"role": "user", "content": "What is Python?"}],
    [{"role": "user", "content": "What is JavaScript?"}]
]
answers = await Wurun.run_gather(questions, concurrency=2)

# Cleanup
await Wurun.close()

DataFrame Processing

import pandas as pd
df = pd.DataFrame({
    "id": [1, 2, 3],
    "messages": [
        [{"role": "user", "content": "What is Python?"}],
        [{"role": "user", "content": "What is JavaScript?"}],
        [{"role": "user", "content": "What is Go?"}]
    ]
})
results = await Wurun.run_dataframe(df, "messages", concurrency=2)

🧪 Practical Demo on Kaggle

API Reference

Setup

• Wurun.setup() - Initialize client (call once per kernel)
• Wurun.close() - Clean up resources

Single Calls

• Wurun.ask() - Single API call with retry logic
• return_meta=True - Include latency and retry count
• max_tokens=1024 - Maximum tokens in response (default: 1024)
• temperature=0 - Response randomness (default: 0)

Batch Processing

• Wurun.run_gather() - Preserve input order
• Wurun.run_as_completed() - Process as results finish
• concurrency parameter controls parallel requests
• max_tokens and temperature available on all batch methods

DataFrame Processing

• Wurun.run_dataframe() - Process messages from DataFrame column

Notebook Helpers

• Wurun.print_qna_ordered() - Pretty print Q&A format
• Wurun.print_as_ready() - Print results as they complete

Configuration

await Wurun.setup(
    endpoint="https://api.openai.com/v1",
    api_key="your-key",
    deployment_name="gpt-3.5-turbo",
    timeout=30.0,
    max_connections=32,
    max_keepalive=16,
    http2=True,
    max_retries=2
)

Error Handling

# Custom retry settings
result = await Wurun.ask(
    messages,
    attempts=3,
    initial_backoff=1.0,
    max_backoff=10.0,
    max_tokens=512,
    temperature=0.7
)

# Get metadata
answer, meta = await Wurun.ask(messages, return_meta=True)
print(f"Latency: {meta['latency']:.2f}s, Retries: {meta['retries']}")

Development

# Install dev dependencies
pip install ".[dev]"

# Run tests
pytest test_wurun.py -v

Release Process

1. Create PR: Make changes and create pull request to main
2. Auto Draft: Release Drafter automatically creates/updates draft release
3. Publish Release: Go to GitHub Releases, edit draft, and publish
4. Auto Deploy: Publishing triggers automatic PyPI deployment

Manual Version Update

# Update version in pyproject.toml
python scripts/update_version.py 1.2.3

License

Apache License 2.0