RiTriever
| 开发者 | rioriost |
|---|---|
| 更新时间 | 2026年7月3日 20:35 |
| PHP版本: | 8.1 及以上 |
| WordPress版本: | 7.0 |
| 版权: | GPLv2 or later |
| 版权网址: | 版权信息 |
详情介绍:
RiTriever adds RAG-style vector retrieval to WordPress search. Published content is embedded, stored in a local vector table, and blended with standard WordPress search results.
The plugin is intended for WordPress sites that can use native database vector support, primarily MariaDB 11.7 or later. It can index posts, pages, and configured public post types, then use those vectors during front-end search.
Main features:
- RAG-style search blending with standard WordPress search.
- Native vector storage in the WordPress database.
- OpenAI and Azure OpenAI support for external embedding APIs.
- Local or self-hosted embedding support through Ollama, LM Studio, Infinity, TEI, or Custom HTTP endpoints.
- RAG target language selection from WordPress-supported locales.
- Admin diagnostics for database support, embedding providers, indexing progress, and live vector queries.
安装:
- Upload the
ritrieverfolder to/wp-content/plugins/, or install the release ZIP from the WordPress admin. - Activate
RiTrieverfrom the Plugins screen. - Open Settings -> RiTriever.
- Run the database capability test.
- Choose the RAG target language.
- Configure and test the embedding provider.
- Initialize the index.
常见问题:
Which external embedding providers are supported?
OpenAI and Azure OpenAI are supported as external hosted embedding providers.
Can I use a local embedding server?
Yes. Ollama, LM Studio, Infinity, TEI, and Custom HTTP endpoints are available for local or self-hosted embeddings.
Does this plugin send content to external APIs?
Only when an external embedding provider is configured. See the External services section for details.
Does it require native vector database support?
Yes. MariaDB 11.7 or later is the primary supported target for native vector columns and indexes.
What happens when I change the target language or embedding model?
The vector table must be rebuilt. Run initialization again after changing target language, provider, model, dimensions, or vector distance settings.
更新日志:
0.2.3
- Resolve remaining Plugin Check SQL preparation warnings for dynamic queue, vector, and uninstall queries.
- Escape search title filter output consistently and prepare plugin table identifiers in direct SQL calls.
- Tighten WordPress.org review gates and clarify external embedding API documentation.
- Rename the public plugin name and WordPress.org slug to RiTriever.
- Add RAG target language selection based on WordPress-supported locales.
- Document why direct embedding APIs are used instead of WordPress AI Client.
- Add WordPress.org release gates for PHPCS, Plugin Check, readme, i18n, and package contents.