AI Provider for llama.cpp
| 开发者 | acrosswp |
|---|---|
| 更新时间 | 2026年4月28日 06:32 |
| PHP版本: | 7.4 及以上 |
| WordPress版本: | 7.0 |
| 版权: | GPL-2.0-or-later |
| 版权网址: | 版权信息 |
详情介绍:
This plugin provides llama.cpp integration for the WordPress AI Client. It lets WordPress sites use large language models running via a llama.cpp server for text generation and other AI capabilities.
llama.cpp exposes an OpenAI-compatible API, and this provider uses that API to communicate with any GGUF model loaded into your llama.cpp server.
Features:
- Text generation with any llama.cpp-loaded model
- Automatic model discovery from your llama.cpp server
- Function calling support
- Structured output (JSON mode) support
- Settings page to configure the server URL (default: http://127.0.0.1:8080)
- Works without an API key for local instances
- PHP 7.4 or higher
- WordPress AI Client plugin must be installed and activated
- llama.cpp server running locally or on a remote host
安装:
- Ensure the WordPress AI Client plugin is installed and activated.
- Upload the plugin files to
/wp-content/plugins/ai-provider-for-llamacpp/. - Activate the plugin through the 'Plugins' menu in WordPress.
- Go to Settings > llama.cpp to configure the server URL.
常见问题:
Do I need an API key?
No. For local llama.cpp instances, no API key is needed. The plugin automatically registers an empty key as a fallback.
What is the default server URL?
http://127.0.0.1:8080 -- the default address used by llama-server.
How do I change the server URL?
Go to Settings > llama.cpp and enter your server's base URL in the "Server URL" field.
更新日志:
0.0.3
- Added support for the WordPress AI plugin — hooks into
wpai_has_ai_credentialsso the AI plugin recognises llama.cpp as a configured provider without requiring an API key
- Initial release
- Text generation with llama.cpp OpenAI-compatible API
- Settings page for server URL configuration
- Added documentation in the docs/ directory
- Fixed minor issues and small bugs
- Updated plugin icon and banner images