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

# Web Retrieval

> Find current sources with Venice Web Search and extract selected pages as Markdown with Venice Web Scrape.

Venice provides separate APIs for discovering web pages and extracting their content:

* **Web Search** returns structured results with titles, URLs, snippets, and dates.
* **Web Scrape** converts a selected public page into Markdown.

Use them together when your application needs current, inspectable source material before inference.

## Search the Web

Send a query to the Search API:

```bash theme={"system"}
curl https://api.venice.ai/api/v1/augment/search \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"latest developments in decentralized AI"}'
```

Brave is the default provider and provides Zero Data Retention. Google is also available with anonymized queries proxied through Venice. See the [Web Search API reference](/api-reference/endpoint/augment/search) for provider selection and the complete response schema.

## Scrape a Page

After selecting a result, send its public URL to the Scrape API:

```bash theme={"system"}
curl https://api.venice.ai/api/v1/augment/scrape \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/article"}'
```

The endpoint returns the page content as Markdown. It first requests the site's native Markdown representation when available and otherwise uses browser-based extraction.

## Search-to-Scrape Workflow

<Steps>
  <Step title="Search">
    Submit a focused query and collect the structured results.
  </Step>

  <Step title="Select sources">
    Filter results by relevance, domain, and date before fetching page content.
  </Step>

  <Step title="Scrape">
    Extract Markdown only from the pages your application intends to use.
  </Step>

  <Step title="Use or store the content">
    Include the Markdown in a prompt, create embeddings, cache it, or preserve source URLs for citations.
  </Step>
</Steps>

## Standalone Search or Model Web Search?

Use the standalone APIs when your application needs control over source selection or wants to reuse retrieved content. Enable web search on a model request when you want Venice to handle retrieval as part of a single inference request.

| Need                                                 | Approach              |
| ---------------------------------------------------- | --------------------- |
| Inspect or filter results before inference           | Standalone Web Search |
| Extract a specific known URL                         | Standalone Web Scrape |
| Cache or reuse retrieved content                     | Standalone APIs       |
| Let the model retrieve current context automatically | Model web search      |

<Warning>
  Web Search and Web Scrape are experimental APIs. Their request and response formats may change without notice. Web Scrape only accepts publicly accessible pages, and sites that block automated access may be rejected.
</Warning>

## Related Resources

* [Web Search API Reference](/api-reference/endpoint/augment/search)
* [Web Scrape API Reference](/api-reference/endpoint/augment/scrape)
* [Private Research Agent](/guides/projects/private-research-agent)
* [Embeddings](/guides/features/embeddings)