> ## Documentation Index
> Fetch the complete documentation index at: https://web2md.org/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Semantic Search

> Find saved content with natural language queries across languages.

## Overview

Semantic Search (v0.7) lets you find previously converted content using natural language instead of exact keywords. Ask for "articles about database optimization" and Web2MD will surface relevant results — even if those exact words never appeared in the content.

<Note>
  Semantic Search is a **Pro-only** feature.
</Note>

## How it works

<Steps>
  <Step title="Convert pages as usual">
    Every time you convert a page, Web2MD automatically generates a vector embedding of the content. No extra steps required.
  </Step>

  <Step title="Search with natural language">
    Open History and type a query in plain English (or any language). Web2MD matches your query against all stored embeddings.
  </Step>

  <Step title="Get ranked results">
    Results are ranked by semantic relevance, not keyword frequency. The most conceptually similar conversions appear first.
  </Step>
</Steps>

## Cross-language matching

Semantic Search works across languages. An English query will match Chinese, Japanese, Spanish, or any other language content — and vice versa.

| Query language | Content language | Works? |
| -------------- | ---------------- | ------ |
| English        | English          | Yes    |
| English        | Chinese          | Yes    |
| Chinese        | English          | Yes    |
| Any            | Any              | Yes    |

<Tip>
  This is especially useful if you read content in multiple languages. Search once, find everything relevant regardless of language.
</Tip>

## Related content

After converting a page, Web2MD automatically shows up to **3 related articles** from your history. This surfaces connections you might not have noticed — a blog post from last month that covers the same topic, or a documentation page with overlapping concepts.

Related content appears below the Preview Card after each conversion.

## Technical details

<CardGroup cols={2}>
  <Card title="Embeddings" icon="brain">
    Powered by OpenAI embeddings, generated automatically on every conversion. Stored securely in your account.
  </Card>

  <Card title="Vector search" icon="database">
    Uses pgvector for fast similarity search across your entire conversion history.
  </Card>
</CardGroup>

## Where to use it

<Tabs>
  <Tab title="Extension">
    Open the History tab in the Web2MD popup and type your query in the search bar. Results update as you type.
  </Tab>

  <Tab title="API">
    Use the `/api/search` endpoint to query your conversions programmatically. Pass a `q` parameter with your natural language query.

    ```bash theme={null}
    curl -H "Authorization: Bearer YOUR_API_KEY" \
      "https://web2md.org/api/search?q=database+optimization"
    ```
  </Tab>
</Tabs>

## Zero configuration

Embeddings are generated automatically — you don't need to enable anything or provide API keys. As long as you have a Pro plan, every conversion is searchable from the moment it's saved.

<Info>
  Embedding generation happens server-side and typically completes within a few seconds after conversion.
</Info>