Download the PHP package marcino0o/openai without Composer
On this page you can find all versions of the php package marcino0o/openai. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
FAQ
Example:
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
- Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
- To use Composer is sometimes complicated. Especially for beginners.
- Composer needs much resources. Sometimes they are not available on a simple webspace.
- If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
- Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.
Informations about the package openai
OpenAI PHP SDK (by @marcino0o)
A lightweight, modern PHP (≥ 8.4) wrapper for the OpenAI API. Focused on simplicity and rapid integration for Chat Completions, with growing support for other endpoints.
Table of Contents
- Requirements
- Installation
- Quick Start
- Configuration
-
Usage
- Chat Completions – Basics
- System Role / Messages
- Model Selection
- Images
- Audio
- Moderations
- Supported Endpoints
- Error Handling
- Retry / Timeout / Streaming
- Logging & Telemetry
- Testing
- Contributing
- Versioning
- License
- FAQ
Requirements
- PHP 8.4+
- Composer
Installation
From Packagist
Quick Start
Configuration
- API key: via constructor or
OPENAI_API_KEYenv var. - Default model: configurable via
OPENAI_MODELor passed per request. - Timeouts/Retry: basic support (advanced retry middleware planned).
Usage
Chat Completions – Basics
Example response (truncated):
System Role / Messages
Example response (truncated):
Model Selection
Example response metadata:
Chat Completions – Advanced options
Images
Example response (truncated):
Audio
Example response:
Moderations
Example response:
Supported Endpoints
| Endpoint | Status | Notes |
|---|---|---|
| Chat Completions | ✅ Stable | Primary focus |
| Images (generation/edit) | ⚠️ Experimental | API subject to change |
| Audio (STT/TTS) | ⚠️ Experimental | Partial support |
| Embeddings | ⏳ Planned | Not yet implemented |
| Moderations | ⚙️ Beta | Basic support present |
| Files / Fine-tuning | ⏳ Planned | Not yet implemented |
| Assistants / Realtime / Agents | ⏳ Planned | Upcoming |
Error Handling
Wrap calls in try/catch blocks:
Retry / Timeout / Streaming
- Timeouts – configurable via HTTP client.
- Retry – exponential backoff (planned in upcoming release).
- Streaming – future
stream()API for live token events.
Logging & Telemetry
- Optional PSR-3 logger.
- Mask sensitive info (e.g., API keys, full prompts).
Testing
Run quality checks locally:
Note: Integration tests use mocked HTTP responses and do not require a live OpenAI API request.
Contributing
Contributions welcome!
- Documentation, examples, FAQ.
- Tests (SSE parsing, error mapping, retries).
- Embeddings/Moderations refinements.
- Retry middleware with exponential backoff.
Workflow:
- Fork → feature branch → PR with examples.
- CI (GitHub Actions) runs PHPUnit on PHP 8.4.
Versioning
- Semantic Versioning (SemVer).
- Breaking changes possible until
v1.0.0. - See
CHANGELOG.mdafter first release.
License
MIT
FAQ
Does it support streaming?
Streaming API planned (stream() returning partial deltas).
Which models can I use?
Use values from Openai\Model, e.g. gpt-5, gpt-4.1, gpt-4.1-mini, o3, o4-mini, gpt-4o, gpt-4o-mini, omni-moderation-latest, gpt-4o-mini-transcribe.
Is it production-ready? Yes for small/medium workloads. For heavy production, enable retry logic, monitoring, and pin a stable release.
