內容簡介
Creator Assistant Hub 是 Creator Assistant 生態系的核心基礎外掛，能將您的 WordPress 網站連接至 OpenAI 和 Qdrant，自動生成並儲存內容的向量嵌入，實現語義搜尋及 AI 驅動的功能。
【主要功能】
• 自動文章向量化：文章發佈或更新時自動生成向量嵌入
• 基於區塊的向量化：將文章內容分割為單詞級段落
• 摘要向量化：生成文章的 AI 簡短摘要
• 背景批次向量化：每小時自動處理未向量化的文章
• OpenAI 整合：使用 OpenAI 的文本嵌入模型
• WPML 相容：支持多語言過濾
外掛標籤
開發者團隊
原文外掛簡介
Creator Assistant Hub is the core infrastructure plugin of the Creator Assistant ecosystem. It connects your WordPress site to OpenAI and Qdrant to automatically generate and store vector embeddings for your content, enabling semantic search and AI-powered features.
How it works
The Hub is the shared infrastructure layer for the Creator Assistant ecosystem. When a compatible add-on is active and activates a vectorizer, the plugin generates vector embeddings via the OpenAI API and stores them in your Qdrant vector database cluster whenever a post is published or updated. This makes your content available for semantic search and retrieval by Creator Assistant add-ons. Without an active add-on, the Hub runs in standby mode: no content is sent to external services.
Key features
Automatic post vectorization: when an add-on activates a vectorizer, embeddings are generated and stored whenever a post is published or updated. Without an active add-on, no vectorization takes place.
Chunk-based vectorization: splits post content into word-level segments and stores each chunk as a separate Qdrant point, enabling fine-grained retrieval (activated by add-ons via filter).
Summary-based vectorization: generates a short AI summary of each post via the OpenAI Responses API, then embeds and stores a single point per post for high-level semantic search (activated by add-ons via filter).
Background batch vectorization: an hourly cron job automatically picks up any existing posts that have not yet been vectorized, so your entire content library is indexed without manual intervention.
OpenAI integration: uses the text-embedding-3-small model (1536 dimensions) via the OpenAI Embeddings API for all vectorizers; the Summary vectorizer additionally calls the OpenAI Responses API (gpt-4.1-nano) to generate post summaries.
Qdrant integration: stores and retrieves vector embeddings from your Qdrant Cloud cluster. Two collections are used: post_chunk for chunk-level points and post_summary for post-level summary points.
Block editor panel: shows the vectorization status of each post directly in the block editor sidebar (document settings panel).
Post list column: adds a “Vector Status” column to the posts and pages admin list, showing the vectorization status of each entry at a glance.
Settings page: configure OpenAI API key, Qdrant endpoint and API key, and cache expiration from a dedicated admin page.
API response caching: configurable cache duration to reduce API usage and latency.
Site Health check: reports the Hub service status in the WordPress Site Health screen.
Qdrant keep-alive: sends a daily lightweight ping to prevent free-tier Qdrant Cloud clusters from being suspended.
WPML compatible: detects the post language via WPML hooks (when WPML is active) and includes it in the Qdrant payload for multilingual filtering.
Extensible: exposes actions and filters so add-ons can register additional post types, override vectorizer behaviour, customise Qdrant payloads, and add settings tabs.
Requirements
An OpenAI account with a valid API key.
A Qdrant Cloud account with an active cluster (free tier is supported).
WordPress 6.8 or higher.
PHP 7.4 or higher.
External services
This plugin connects to up to three third-party services. By using this plugin you agree to their respective terms and privacy policies.
OpenAI: used to generate vector embeddings from your post content via the Embeddings API. When the Summary vectorizer is active (enabled by an add-on), post content is also sent to the Responses API to generate a short AI summary before embedding.
Service: https://platform.openai.com/
Privacy Policy: https://openai.com/policies/privacy-policy
Terms of Use: https://openai.com/policies/terms-of-use
Qdrant Cloud: used to store and query vector embeddings.
Service: https://cloud.qdrant.io/
Privacy Policy: https://qdrant.tech/legal/privacy-policy/
Terms of Service: https://qdrant.tech/legal/terms_and_conditions/
Google (OAuth sign-in), through a proxy run by the plugin author: used only if you click “Connect with Google” in the plugin settings, so that Creator Assistant add-ons can read data from your Google services. Nothing is sent before you click it, and “Disconnect” revokes the connection.
What is sent: your browser goes to Google’s consent screen (the only scope the Hub requests is your account email; add-ons may request more, and say so on the settings page). When you accept, Google returns an authorization code to an AWS Lambda proxy (*.lambda-url.eu-north-1.on.aws) operated by the plugin author, which exchanges it with Google for tokens, because the Google client secret must not be shipped in a public plugin, and hands the tokens back to your site. The same proxy is called to refresh the access token. The proxy does not store the tokens; your site keeps the refresh token encrypted in its own database. The plugin also calls Google’s userinfo endpoint to show the connected email, and Google’s revoke endpoint when you disconnect.
Service: https://accounts.google.com/
Google Privacy Policy: https://policies.google.com/privacy
Google Terms of Service: https://policies.google.com/terms
Proxy operator (plugin author) Privacy Policy: https://www.creator-assistant.it/privacy-policy
Proxy operator Terms of Service: https://www.creator-assistant.it/terms-of-service
Data is only transmitted to OpenAI and Qdrant after you explicitly accept the Creator Assistant Terms of Service in the plugin settings and provide your own API credentials, and to Google only after you click “Connect with Google”. No data is transmitted automatically upon activation.
Development
The source files for all compiled assets are included in the plugin: front-end
assets under assets/src/, and the block-editor integration under src/.
Build tools required: Node.js (includes npm).
Install dependencies: npm install
Build the front-end assets: npm run build
JS only: npm run build:js (uses esbuild)
CSS only: npm run build:css (uses PostCSS + Sass)
Build the block-editor integration: npm run build:editor (uses @wordpress/scripts)
Front-end JS source files are in assets/src/js/ and compiled to assets/dist/js/.
Front-end CSS/SCSS source files are in assets/src/css/ and compiled to assets/dist/css/.
Block-editor source files are in src/ and compiled to build/.
