ArXiv Scout

arxiv_download_and_extract

Extract full text from a paper's PDF.

Remote shawnnygoh/arxiv-scout

Other tools also called arxiv_download_and_extract? See providers with this name

Input Schema


            {
  "type": "object",
  "properties": {
    "arxiv_id": {
      "type": "string",
      "description": "The arXiv ID of the paper from which to extract text."
    },
    "end_page": {
      "type": "integer",
      "description": "The 1-indexed page number where text extraction should stop."
    },
    "start_page": {
      "type": "integer",
      "description": "The 1-indexed page number where text extraction should begin."
    },
    "max_characters": {
      "type": "integer",
      "default": 50000,
      "description": "The maximum number of characters to return from the PDF to prevent context window overflow."
    },
    "include_sections": {
      "type": "boolean",
      "default": true,
      "description": "Whether to include an automatically detected outline of the paper's sections."
    },
    "include_references": {
      "type": "boolean",
      "default": false,
      "description": "Whether to include the bibliography list extracted from the end of the PDF."
    }
  }
}