GitHub - cmakafui/batchwizard: A CLI tool for managing OpenAI batch processing jobs with ease.

BatchWizard

BatchWizard is a powerful CLI tool for managing OpenAI batch processing jobs with ease. It provides functionalities to upload files, create batch jobs, check their status, and download the results. The tool uses asynchronous processing to efficiently handle multiple jobs concurrently.

Table of Contents

• Installation
• Usage
• Configuration
• Commands
• Features
• Contributing
• License

Installation

You can install BatchWizard using pipx for an isolated environment or directly via pip.

Using pipx (recommended)

Using pip

Ensure you have pipx or pip installed on your system. For pipx, you can follow the installation instructions here.

Usage

BatchWizard provides a command-line interface (CLI) for managing batch jobs. Here are some example commands:

Process Batch Jobs

To process input files or directories:

batchwizard process <input_paths>... [--output-directory OUTPUT_DIR] [--max-concurrent-jobs NUM] [--check-interval SECONDS]

You can provide multiple input paths, which can be individual JSONL files or directories containing JSONL files.

Example with Sample Input

Let's say you have a file named batchinput.jsonl with the following content:

{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-4o-mini", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-4o-mini", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}

To process this file using BatchWizard:

1. First, ensure your OpenAI API key is set:

   batchwizard configure --set-key YOUR_API_KEY

2. Then, run the process command:

   batchwizard process /path/to/batchinput.jsonl --output-directory /path/to/output

   This command will:
   • Upload the batchinput.jsonl file to OpenAI
   • Create a batch job
   • Monitor the job status
   • Download the results to the specified output directory when complete

You can also process multiple files or directories:

batchwizard process /path/to/file1.jsonl /path/to/directory_with_jsonl_files /path/to/file2.jsonl

List Recent Jobs

To list recent batch jobs:

batchwizard list-jobs [--limit NUM] [--all]

Cancel a Job

To cancel a specific batch job:

batchwizard cancel <job_id>

Download Job Results

To download results for a completed batch job:

batchwizard download <job_id> [--output-file FILE_PATH]

Configuration

Setting up the OpenAI API Key

To set the OpenAI API key:

batchwizard configure --set-key YOUR_API_KEY

Show Current Configuration

To show the current configuration:

batchwizard configure --show

Reset Configuration

To reset the configuration to default values:

batchwizard configure --reset

Commands

BatchWizard supports the following commands:

• process: Process batch jobs from input files or directories.
• configure: Manage BatchWizard configuration.
• list-jobs: List recent batch jobs.
• cancel: Cancel a specific batch job.
• download: Download results for a completed batch job.

For detailed information on each command, use the --help option:

batchwizard <command> --help

Features

• Flexible Input: Process individual JSONL files or entire directories containing JSONL files.
• Asynchronous Processing: Efficiently handle multiple batch jobs concurrently.
• Rich UI: Display progress and job status using a rich, interactive interface.
• Flexible Configuration: Easily manage API keys and other settings.
• Job Management: List, cancel, and download results for batch jobs.
• Error Handling: Robust error handling and informative error messages.

Contributing

We welcome contributions to BatchWizard! To contribute, follow these steps:

1. Fork the repository.
2. Create a new branch: git checkout -b feature/your-feature-name.
3. Make your changes and commit them: git commit -m 'Add some feature'.
4. Push to the branch: git push origin feature/your-feature-name.
5. Open a pull request.

Running Tests

To run tests, use pytest:

pytest --cov=batchwizard tests/

Ensure your code passes all tests and meets the coding standards before opening a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

For any questions or feedback, feel free to open an issue on the GitHub repository.