Claude Integration

[
  {
    "name": "unsiloed_parse_document",
    "description": "Parse a document into structured chunks with element detection, text extraction, and reading order analysis. Use this tool when the user wants to break a document into its structural components (text blocks, tables, images, headers, footers) or convert a document to markdown. You must provide a publicly accessible URL to the document. Supported formats include PDF, PNG, JPEG, TIFF, BMP, DOCX, XLSX, and PPTX. The operation is asynchronous — it returns a job_id that you must poll using unsiloed_get_job_result to retrieve the parsed content.",
    "input_schema": {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Publicly accessible URL to the document to parse."
        },
        "use_high_resolution": {
          "type": "boolean",
          "description": "Use high-resolution image processing for better OCR accuracy. Defaults to false."
        },
        "segmentation_method": {
          "type": "string",
          "enum": ["smart_layout_detection", "page_by_page"],
          "description": "Document segmentation strategy. 'smart_layout_detection' (default) groups related elements into semantic chunks. 'page_by_page' creates one chunk per page."
        },
        "ocr_mode": {
          "type": "string",
          "enum": ["auto_ocr", "full_ocr"],
          "description": "OCR strategy. 'auto_ocr' (default) only runs OCR when needed. 'full_ocr' forces OCR on all pages."
        },
        "merge_tables": {
          "type": "boolean",
          "description": "Merge adjacent table segments into a single table. Defaults to false."
        },
        "segment_filter": {
          "type": "string",
          "description": "Filter output to include only specific segment types. Accepts comma-separated values (e.g., 'table', 'picture', 'table,picture') or 'all' for everything. Defaults to 'all'."
        },
        "xml_citation": {
          "type": "boolean",
          "description": "Enable citation extraction from PDF documents. Extracts structured bibliography and in-text citations in markdown output. Defaults to false."
        },
        "output_fields": {
          "type": "string",
          "description": "JSON object controlling which fields are included in the response. Set fields to false to exclude them and reduce response size. Available fields: html, markdown, ocr, image, content, bbox, confidence, embed. All default to true. Example: {\"html\":true,\"markdown\":true,\"ocr\":false,\"image\":false}"
        },
        "segment_analysis": {
          "type": "string",
          "description": "JSON object controlling HTML/Markdown generation strategy and AI model per segment type. Example: {\"Table\":{\"html\":\"VLM\",\"markdown\":\"VLM\"},\"Picture\":{\"html\":\"VLM\",\"markdown\":\"VLM\"}}"
        },
        "page_range": {
          "type": "string",
          "description": "Specify which pages to process. Formats: '1-5', '2,4,6', or '[1,3,5]'. Defaults to all pages."
        },
        "segment_type_naming": {
          "type": "string",
          "enum": ["Unsiloed", "Other"],
          "description": "Segment type naming convention. 'Unsiloed' (default) uses names like PageHeader, ListItem, Picture. 'Other' uses alternative names like Header, List Item, Figure."
        },
        "extract_colors": {
          "type": "boolean",
          "description": "Transfer text color from the PDF text layer to OCR results. Defaults to false."
        },
        "extract_links": {
          "type": "boolean",
          "description": "Attach hyperlink URLs from PDF annotations to OCR results. Defaults to false."
        },
        "export_format": {
          "type": "string",
          "description": "JSON array of export format(s) to generate after parsing. The exported files are available as presigned URLs in the exports field of the response. Currently supported: [\"docx\"]. Example: [\"docx\"]"
        },
        "error_handling": {
          "type": "string",
          "enum": ["Continue", "Fail"],
          "description": "How to handle per-page errors. 'Continue' (default) skips failed pages and continues. 'Fail' aborts the entire job on the first error."
        },
        "expires_in": {
          "type": "integer",
          "description": "Seconds until the task and its output are automatically deleted."
        },
        "chunk_processing": {
          "type": "string",
          "description": "JSON object for chunk processing configuration."
        },
        "llm_processing": {
          "type": "string",
          "description": "JSON object for LLM processing configuration."
        }
      },
      "required": ["url"]
    }
  },
  {
    "name": "unsiloed_extract_data",
    "description": "Extract structured data from a PDF document using a custom JSON schema. Use this tool when the user wants to pull specific fields (such as invoice numbers, names, dates, or line items) out of a PDF. You must provide a publicly accessible URL to the PDF and a JSON schema defining the fields to extract. The operation is asynchronous — it returns a job_id that you must poll using unsiloed_get_job_result to retrieve the extracted data. Do not use this tool for document classification or splitting.",
    "input_schema": {
      "type": "object",
      "properties": {
        "file_url": {
          "type": "string",
          "description": "Publicly accessible URL to the PDF file to process."
        },
        "schema_data": {
          "type": "string",
          "description": "A JSON-stringified schema defining the fields to extract. Example: {\"type\":\"object\",\"properties\":{\"invoice_number\":{\"type\":\"string\",\"description\":\"The invoice number\"},\"total\":{\"type\":\"number\",\"description\":\"Total amount\"}},\"required\":[\"invoice_number\"],\"additionalProperties\":false}"
        },
        "model": {
          "type": "string",
          "enum": ["alpha", "beta", "gamma", "delta"],
          "description": "Model tier for extraction. Default is 'gamma', recommended for most use cases."
        },
        "enable_citations": {
          "type": "boolean",
          "description": "When true, returns bounding box coordinates for each extracted value, enabling you to trace data back to its location in the PDF. Defaults to false."
        }
      },
      "required": ["file_url", "schema_data"]
    }
  },
  {
    "name": "unsiloed_classify_document",
    "description": "Classify a PDF document into one of several predefined categories. Use this tool when the user wants to determine what type of document a PDF is (for example, invoice, receipt, contract, or medical record). You must provide a publicly accessible URL to the PDF and a list of candidate categories. The operation is asynchronous — it returns a job_id that you must poll using unsiloed_get_job_result to retrieve the classification result with confidence scores. Do not use this for data extraction or document splitting.",
    "input_schema": {
      "type": "object",
      "properties": {
        "file_url": {
          "type": "string",
          "description": "Publicly accessible URL to the PDF file to classify."
        },
        "categories": {
          "type": "string",
          "description": "A JSON-stringified array of category objects. Each object must have a 'name' field and may have an optional 'description' field for better accuracy. Example: [{\"name\":\"Invoice\",\"description\":\"Financial invoices with itemized charges\"},{\"name\":\"Receipt\"},{\"name\":\"Contract\",\"description\":\"Legal agreements\"}]"
        }
      },
      "required": ["file_url", "categories"]
    }
  },
  {
    "name": "unsiloed_split_document",
    "description": "Split a multi-document PDF into separate files by classifying each page into predefined categories. Use this tool when the user has a single PDF containing multiple document types (for example, a scanned batch of invoices, receipts, and contracts) and wants them separated into individual files. You must provide a publicly accessible URL to the PDF and a list of candidate categories. The operation is asynchronous — it returns a job_id that you must poll using unsiloed_get_job_result to retrieve download links for the split files. Do not use this for single-document classification or data extraction.",
    "input_schema": {
      "type": "object",
      "properties": {
        "file_url": {
          "type": "string",
          "description": "Publicly accessible URL to the PDF file to split."
        },
        "categories": {
          "type": "string",
          "description": "A JSON-stringified array of category objects. Each object must have a 'name' field and may have an optional 'description' field for better accuracy. Example: [{\"name\":\"Invoice\",\"description\":\"Financial invoices\"},{\"name\":\"Contract\"},{\"name\":\"Receipt\"}]"
        }
      },
      "required": ["file_url", "categories"]
    }
  },
  {
    "name": "unsiloed_get_job_result",
    "description": "Poll for the result of an asynchronous Unsiloed job. Use this tool after calling unsiloed_parse_document, unsiloed_extract_data, unsiloed_classify_document, or unsiloed_split_document to check whether the job has completed and retrieve its results. If the status indicates the job is still processing, wait a few seconds and call this tool again. Once the job is complete, the response contains the output data. If the job failed, the response includes an error message explaining what went wrong.",
    "input_schema": {
      "type": "object",
      "properties": {
        "job_id": {
          "type": "string",
          "description": "The job_id returned by a previous Unsiloed tool call."
        },
        "job_type": {
          "type": "string",
          "enum": ["parse", "extract", "classify", "splitter"],
          "description": "The type of job to check. Use 'parse' for parsing jobs, 'extract' for extraction jobs, 'classify' for classification jobs, and 'splitter' for splitting jobs."
        }
      },
      "required": ["job_id", "job_type"]
    }
  }
]