# Apify RAG Web Browser Actor

> Apify RAG Web Browser Actor is a paid API for AI agents from apify-jwhre9stu-merit-systems.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Performs Google searches and scrapes the top N result pages using a full browser, returning page content for use in AI/RAG pipelines

## Facts

- Endpoint: POST https://apify-jwhre9stu-merit-systems.vercel.app/api/actors/apify/rag-web-browser/call
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/apify-jwhre9stu-merit-systems-vercel-app-f19c1d72
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qp7GizETGRmy5xCjSpOyh

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability apify-jwhre9stu-merit-systems-vercel-app-f19c1d72 -d '<json body>'
```

Example prompt: Search the web for 'best practices for LLM prompt engineering' and scrape the top 5 result pages, returning the full text content so I can use it as context in my RAG pipeline.

## When to prefer this

Use this endpoint when an AI agent or RAG pipeline needs real, current web content from multiple pages for a given search query, especially when JavaScript rendering is required. Prefer over simple HTTP fetchers when pages require a full browser to render, or when you need Google Search integration combined with scraping in a single call.

## Known failure modes

- Search query returns no results — empty results array
- Target pages block scraping — partial or empty content for those URLs
- Actor timeout if pages are slow to load — incomplete results
- Invalid or missing query parameter — 400 error
- Payment/wallet issues — 402 error on first call per wallet
- Polling token expires before results are ready — re-fetch required

## How this service works

Start the "RAG Web Browser" Apify actor (apify/rag-web-browser). Web search and fetch tool for AI agents and RAG pipelines. It queries Google Search, scrapes the top N pages using a full web browser, and returns their conten… Returns a signed token for polling /api/actors/status (free SIWX) and fetching /api/actors/results (paid on first call per wallet, then free with SIWX replay).

## Output

Returns a signed token used to poll /api/actors/status for job completion and fetch /api/actors/results for the scraped page content from the top N Google search results, including full text extracted by a real browser.

## Example request

```json
{
 "input": {
  "query": "artificial intelligence",
  "maxResults": 3,
  "scrapingTool": "raw-http",
  "outputFormats": [
   "markdown"
  ],
  "htmlTransformer": "none",
  "requestTimeoutSecs": 40
 }
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "$schema": "https://json-schema.org/draft/2020-12/schema",
     "properties": {
      "input": {
       "type": "object",
       "required": [
        "query",
        "maxResults",
        "outputFormats",
        "requestTimeoutSecs",
        "serpProxyGroup",
        "serpMaxRetries",
        "proxyConfiguration",
        "scrapingTool",
        "removeElementsCssSelector",
        "htmlTransformer",
        "desiredConcurrency",
        "maxRequestRetries",
        "dynamicContentWaitSecs",
        "removeCookieWarnings",
        "debugMode"
       ],
       "properties": {
        "query": {
         "type": "string",
         "pattern": "[^\\s]+",
         "description": "Enter Google Search keywords or a URL of a specific web page. The keywords might include the [advanced search operators](https://blog.apify.com/how-to-scrape-google-like-a-pro/). Examples: - san francisco weather - https://www.cnn.com - function calling site:openai.com"
        },
        "debugMode": {
         "type": "boolean",
         "default": false,
         "description": "If enabled, the Actor will store debugging information into the resulting dataset under the `debug` field."
        },
        "maxResults": {
         "type": "integer",
         "default": 3,
         "maximum": 100,
         "minimum": 1,
         "description": "The maximum number of top organic Google Search results whose web pages will be extracted. If `query` is a URL, then this field is ignored and the Actor only fetches the specific web page."
        },
        "scrapingTool": {
         "enum": [
          "browser-playwright",
          "raw-http"
         ],
         "type": "string",
         "default": "raw-http",
         "description": "Select a scraping tool for extracting the target web pages. The Browser tool is more powerful and can handle JavaScript heavy websites, while the Plain HTML tool can't handle JavaScript but is about two times faster."
        },
        "outputFormats": {
         "type": "array",
         "items": {
          "enum": [
           "text",
           "markdown",
           "html"
          ],
          "type": "string"
         },
         "default": [
          "m
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/apify-jwhre9stu-merit-systems-vercel-app-f19c1d72/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from apify-jwhre9stu-merit-systems.vercel.app](https://www.zero.xyz/host/apify-jwhre9stu-merit-systems.vercel.app/llms.txt)