Title: VecPost AI Search for Posts
Author: krunalbalas
Published: <strong>2026 年 5 月 23 日</strong>
Last modified: 2026 年 5 月 23 日

---

搜索插件

![](https://ps.w.org/vecpost/assets/icon-256x256.png?rev=3545010)

# VecPost AI Search for Posts

 作者：[krunalbalas](https://profiles.wordpress.org/krunalbalas/)

[下载](https://downloads.wordpress.org/plugin/vecpost.1.0.0.zip)

 * [详情](https://cn.wordpress.org/plugins/vecpost/#description)
 * [评价](https://cn.wordpress.org/plugins/vecpost/#reviews)
 *  [安装](https://cn.wordpress.org/plugins/vecpost/#installation)
 * [开发进展](https://cn.wordpress.org/plugins/vecpost/#developers)

 [支持](https://wordpress.org/support/plugin/vecpost/)

## 描述

VecPost AI Search for Posts replaces WordPress’s default SQL LIKE search with vector-
based semantic search. Instead of matching exact words, it understands the _meaning_
of a search query.

**Example:** A user searching “heart workouts” will find your post titled “Best 
cardiovascular exercises” – even though no words overlap – because the meanings 
are similar.

#### How It Works

 1. When you publish a post, the plugin sends its content to your chosen AI provider(
    OpenAI or Google Gemini) to generate a vector embedding – a list of numbers that
    represents the meaning of the text.
 2. These numbers are stored in your database.
 3. When a user searches, their query is also converted to numbers, and the plugin 
    finds posts whose numbers are closest – meaning most semantically similar.

#### Features

 * Semantic search powered by OpenAI (`text-embedding-3-small` or `text-embedding-
   3-large`) or Google Gemini (`gemini-embedding-001`)
 * Hybrid re-ranking: combines semantic similarity with keyword matching for best
   results
 * Gutenberg block and shortcode `[vecpost_semantic_search]` for easy placement
 * Bulk indexer with progress bar for existing posts
 * WP-CLI support: `wp vecpost-semantic-search index`, `wp vecpost-semantic-search
   status`, `wp vecpost-semantic-search search "query"`
 * Configurable scoring thresholds via Settings -> VecPost – AI Semantic Search 
   for Posts
 * Automatic re-indexing when you switch embedding models
 * Results cached via WordPress object cache (Redis/Memcached compatible)

#### Third-Party Services

This plugin sends post content to external AI APIs to generate embeddings. By using
this plugin, you agree to the terms of service and privacy policies of your chosen
provider:

 * **OpenAI:** https://openai.com/policies/privacy-policy | https://openai.com/policies/
   terms-of-use
 * **Google Gemini:** https://policies.google.com/privacy | https://ai.google.dev/
   terms

No data is sent without your API key being configured. Data is only transmitted 
when posts are published or during bulk indexing.

#### Performance Note

Semantic search requires loading all embeddings into PHP memory for comparison. 
This works well for sites with up to approximately 1,500 posts. For larger sites,
a dedicated vector database (pgvector, Qdrant, or Pinecone) is recommended.

## 区块

该插件提供了 1 个区块.

 *   VecPost AI Search for Posts A basic search block for VecPost AI Search for 
   Posts.

## 安装

 1. Upload the plugin folder to `/wp-content/plugins/`
 2. Activate the plugin through the **Plugins** menu in WordPress
 3. Go to **Settings -> VecPost – AI Semantic Search for Posts**
 4. Enter your OpenAI or Google Gemini API key
 5. Click **Test Connection** to verify the key works
 6. Click **Start Bulk Index** to index your existing posts
 7. Add the search block to any page via the Gutenberg editor, or use the shortcode`[
    vecpost_semantic_search]`

## 常见问题

### Do I need an OpenAI account?

Yes. You need either an OpenAI API key (https://platform.openai.com) or a Google
Gemini API key (https://aistudio.google.com). Both have free tiers that are sufficient
for small sites.

### Does this replace the default WordPress search?

No. This plugin adds a separate search widget/block. Your default WordPress search
continues to work unchanged. You can place the semantic search widget on any page
alongside or instead of the default search.

### Is my content sent to OpenAI/Google?

Yes – post content is sent to the embedding API when you publish a post or run bulk
indexing. The API returns numbers (the embedding vector) and does not store or use
your content for training. See their privacy policies for full details.

### How much does it cost?

Using `text-embedding-3-small` (the default), indexing costs approximately $0.002
per 1,000 posts. Each search query costs a fraction of a cent. For most sites, monthly
costs are under $1.

### What happens if I change the embedding model?

The plugin detects the model change and automatically re-indexes all posts using
the new model. During re-indexing, searches will return no results until indexing
is complete.

### Can I use this on a multisite installation?

The plugin has not been tested on WordPress Multisite and is not officially supported
in that environment.

## 评价

此插件暂无评价。

## 贡献者及开发者

「VecPost AI Search for Posts」是开源软件。 以下人员对此插件做出了贡献。

贡献者

 *   [ krunalbalas ](https://profiles.wordpress.org/krunalbalas/)
 *   [ krunalb18 ](https://profiles.wordpress.org/krunalb18/)

[帮助将「VecPost AI Search for Posts」翻译成简体中文。](https://translate.wordpress.org/projects/wp-plugins/vecpost)

### 对开发感兴趣吗?

您可以[浏览代码](https://plugins.trac.wordpress.org/browser/vecpost/)，查看[SVN仓库](https://plugins.svn.wordpress.org/vecpost/)，
或通过[RSS](https://plugins.trac.wordpress.org/log/vecpost/?limit=100&mode=stop_on_copy&format=rss)
订阅[开发日志](https://plugins.trac.wordpress.org/log/vecpost/)。

## 更新日志

#### 1.0.0

 * Initial public release
 * OpenAI and Google Gemini embedding support
 * Hybrid semantic + keyword re-ranking (BM25)
 * Gutenberg block and shortcode
 * WP-CLI commands
 * Bulk indexer with progress UI
 * Configurable scoring thresholds
 * Redis/Memcached compatible caching
 * API connection test in admin
 * Automatic re-index on model change

## 额外信息

 *  版本 **1.0.0**
 *  最后更新：**5 天前**
 *  活跃安装数量 **不到10**
 *  WordPress 版本 ** 6.1 或更高版本 **
 *  已测试的最高版本为 **6.9.4**
 *  PHP 版本 ** 7.4 或更高版本 **
 *  语言
 * [English (US)](https://wordpress.org/plugins/vecpost/)
 * 标签
 * [ai search](https://cn.wordpress.org/plugins/tags/ai-search/)[embeddings](https://cn.wordpress.org/plugins/tags/embeddings/)
   [openai](https://cn.wordpress.org/plugins/tags/openai/)[search](https://cn.wordpress.org/plugins/tags/search/)
   [semantic search](https://cn.wordpress.org/plugins/tags/semantic-search/)
 *  [高级视图](https://cn.wordpress.org/plugins/vecpost/advanced/)

## 评级

尚未提交反馈。

[Your review](https://wordpress.org/support/plugin/vecpost/reviews/#new-post)

[查看全部评论](https://wordpress.org/support/plugin/vecpost/reviews/)

## 贡献者

 *   [ krunalbalas ](https://profiles.wordpress.org/krunalbalas/)
 *   [ krunalb18 ](https://profiles.wordpress.org/krunalb18/)

## 支持

有话要说吗？是否需要帮助？

 [查看支持论坛](https://wordpress.org/support/plugin/vecpost/)