# Build a RAG Paper Corpus with Downloadable PDFs

**Use case:** 

Find open-access papers with verified downloadable PDFs and a trimmed, ingestion-ready output: build a RAG corpus from real research, no dead links.

## Input

```json
{
  "query": "large language models",
  "researchPreset": "none",
  "titleOnly": false,
  "fullTextOnly": true,
  "maxResults": 25,
  "pdfVerification": "head-check",
  "dropFiltered": false,
  "dedupeMode": "strict",
  "watchlistMode": "flag-all",
  "outputMode": "papers",
  "outputProfile": "minimal"
}
```

## Output

```json
{
  "title": {
    "label": "Title",
    "format": "string"
  },
  "readReady": {
    "label": "Read Ready",
    "format": "boolean"
  },
  "qualityGrade": {
    "label": "Readiness Grade",
    "format": "string"
  },
  "citationCount": {
    "label": "Citation Count",
    "format": "integer"
  },
  "yearPublished": {
    "label": "Year Published",
    "format": "integer"
  },
  "downloadUrl": {
    "label": "Download URL",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [CORE Open Access Paper Search](https://apify.com/ryanclinton/core-academic-search) with a specific input configuration. Visit the [Actor detail page](https://apify.com/ryanclinton/core-academic-search) to learn more, explore other use cases, and run it yourself.