# RAG Web Search (`tacps126/rag-web-search`) Actor

Search the web and get the top result pages as clean Markdown for AI agents, RAG and LLM apps: rank, title, snippet and each page's main content without menus or ads. From $1 per 1,000 pages.

- **URL**: https://apify.com/tacps126/rag-web-search.md
- **Developed by:** [Tapaswai Choudhary](https://apify.com/tacps126) (community)
- **Categories:** AI, Developer tools
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.80 / 1,000 pages

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## RAG Web Search

**Search the web and get the top result pages as clean Markdown**, ready for AI agents, RAG and LLM apps. Each row has the search **rank, title and snippet**, plus the page's **main content as Markdown** without menus, footers or ads, and its title, description, language and publish date.

**Built for** AI agents that need fresh web context, chatbots that answer from current pages, researchers collecting sources, and RAG pipelines.

### Why this search

- **Pages, not just links.** Each result is opened and its main content returned as Markdown.
- **Clean text.** Navigation, sidebars, footers and ads are dropped; headings, lists, tables and code are kept.
- **Many searches at once.** List questions or phrases; each gets its own top results.
- **Your region.** Set the search language and country.
- **Fast.** Result pages are read at the same time; five pages in a few seconds.

### How to use it

1. Add **Web searches** (questions or phrases).
2. Set **Results per search** (3 to 5 is usual for an agent).
3. Press **Start**, or call it as an API from your agent.

```json
{
  "queries": ["how does retrieval augmented generation work", "best vector database 2026"],
  "maxResultsPerQuery": 5
}
```

### What you get

```json
{
  "query": "how does retrieval augmented generation work",
  "rank": 1,
  "url": "https://example.com/rag-explained",
  "searchTitle": "What is retrieval augmented generation?",
  "searchSnippet": "Retrieval augmented generation combines a search step with...",
  "title": "What is RAG?",
  "markdown": "# What is RAG?\n\nRetrieval augmented generation...",
  "wordCount": 1210,
  "language": "en"
}
```

Optional fields: `text` (plain text) and `links`.

### Pricing

Pay per page: **$1 per 1,000 pages**, plus a small start fee per run. You pay only for pages delivered.

### FAQ

**Which search engine?** A major web search engine's public results page, in the language and country you set.

**What about pages that need JavaScript?** Those come back thin; set a minimum word count to skip them.

**Can I crawl a whole site?** Use [Website to Markdown Crawler](https://apify.com/tacps126/website-markdown).

### Support

Open an issue on the **Issues** tab and include the run link.

# Actor input Schema

## `queries` (type: `array`):

Search phrases or questions. The top results are read as pages, each with its search rank, title and snippet.

## `maxResultsPerQuery` (type: `integer`):

Search results read as pages for each search.

## `fullPage` (type: `boolean`):

Keep the whole page body. Off: only the main content, without menus, headers, footers and ads.

## `includeText` (type: `boolean`):

Add a plain text version next to the Markdown.

## `includeLinks` (type: `boolean`):

Add every link found on the page.

## `minWords` (type: `integer`):

Skip pages with fewer words than this (empty or near-empty pages are always skipped).

## `searchLanguage` (type: `string`):

Two-letter language code for web searches.

## `searchCountry` (type: `string`):

Two-letter country code for web searches.

## `maxItems` (type: `integer`):

Maximum number of pages to return in total.

## `proxyConfiguration` (type: `object`):

Keep the default setting for reliable results.

## `debug` (type: `boolean`):

More detail in the run log.

## Actor input object example

```json
{
  "queries": [
    "how does retrieval augmented generation work"
  ],
  "maxResultsPerQuery": 5,
  "fullPage": false,
  "includeText": false,
  "includeLinks": false,
  "minWords": 0,
  "searchLanguage": "en",
  "searchCountry": "us",
  "maxItems": 50,
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "debug": false
}
```

# Actor output Schema

## `results` (type: `string`):

The produced items (default dataset items).

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": [
        "how does retrieval augmented generation work"
    ],
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("tacps126/rag-web-search").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "queries": ["how does retrieval augmented generation work"],
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("tacps126/rag-web-search").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "queries": [
    "how does retrieval augmented generation work"
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call tacps126/rag-web-search --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tacps126/rag-web-search"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/SavumacI1xSDRcjWq/builds/51RzreT0GD2fHe5GG/openapi.json
