# Collect deeper sources for RAG research

**Use case:** 

Search related documentation questions and collect up to ten ranked pages per query as Markdown and plain text. Replace the sample questions. Repeated URLs are fetched once while every query and rank stays visible.

## Input

```json
{
  "queries": [
    "site:docs.apify.com Actor input schema",
    "site:docs.apify.com Actor output schema"
  ],
  "maxResultsPerQuery": 10,
  "outputFormats": [
    "markdown",
    "text"
  ],
  "deduplicateUrls": true,
  "requestTimeoutSecs": 40
}
```

## Output

```json
{
  "query": {
    "label": "Query",
    "format": "string"
  },
  "query_index": {
    "label": "Query index",
    "format": "integer"
  },
  "rank": {
    "label": "Rank",
    "format": "integer"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "search_result": {
    "label": "Search result",
    "format": "object"
  },
  "fetch": {
    "label": "Fetch",
    "format": "object"
  },
  "markdown": {
    "label": "Markdown",
    "format": "string"
  },
  "text": {
    "label": "Text",
    "format": "string"
  },
  "source_url": {
    "label": "Source URL",
    "format": "string"
  },
  "scraped_at": {
    "label": "Observed",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [Batch RAG Web Search - 100 Queries to Markdown](https://apify.com/automa-flow/batch-rag-web-search.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/automa-flow/batch-rag-web-search.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

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 full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/automa-flow/batch-rag-web-search.md

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`).