[
  {
    "id": "datalab-docs-1",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/quickstart",
    "excerpt": "Get started with Datalab to convert PDFs, images, and documents into Markdown, HTML, or JSON in minutes.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-2",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/sdk",
    "excerpt": "The Datalab Python SDK provides a simple interface for document conversion, pipelines, structured extraction, form filling, and file management.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-3",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/recipes/structured-extraction/api-overview",
    "excerpt": "Extract specific fields from documents by providing a JSON schema. Marker parses the document and fills in your schema with extracted values.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-4",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Pipelines — Chain processors into versioned, reusable configurations and deploy to production",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-5",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Document Segmentation — Split multi-document PDFs into separate logical sections",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-6",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Track Changes — Extract redlines and comments from Word documents, PDFs, and scans",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-7",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Form Filling — Automatically fill PDF and image forms with structured data",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-8",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/webhooks",
    "excerpt": "Webhooks provide real-time notifications when your document processing jobs complete, eliminating the need for continuous polling.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-9",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/quickstart",
    "excerpt": "Want to try before writing code? Upload a document to Forge to see results instantly — no API key required.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-10",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/quickstart",
    "excerpt": "new accounts include a **free monthly usage allowance** (no credit card required), enough to run a full proof of concept on your own documents",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-11",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/security",
    "excerpt": "Two-factor authentication (TOTP) is available for all Datalab accounts. Enable it from the Security page in the dashboard.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-12",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/security",
    "excerpt": "Team plan admins can require two-factor authentication for all team members",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-13",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/on-prem/overview",
    "excerpt": "Customers can run our models on infrastructure they control with an Enterprise contract.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-14",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/sdk/cli",
    "excerpt": "Use the Datalab CLI to convert documents from the command line.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-15",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/changelog",
    "excerpt": "Track Changes is now available in the Playground — upload a DOCX, PDF, or image file to preview tracked changes extraction results directly in the UI.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-16",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/extract-structured-data",
    "excerpt": "Provide a file for end-to-end processing, or a checkpoint_id from a previous /convert call to skip re-parsing.",
    "fetchedAt": "2026-09-10T18:46:30.670Z"
  },
  {
    "id": "datalab-docs-17",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Parse PDFs, Word docs, and spreadsheets into Markdown, HTML, or JSON",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-18",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Extract specific fields with citations back to source bounding boxes for auditability",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-19",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Automatically fill PDF and image forms with structured data",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-20",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Split multi-document PDFs into separate logical sections",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-21",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to",
    "excerpt": "Chain processors into versioned, reusable configurations and deploy to production",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-22",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/quickstart",
    "excerpt": "The SDK provides a simple interface to convert documents to Markdown, HTML, JSON, or chunks.",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-23",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/quickstart",
    "excerpt": "Upload a document to Forge to see results instantly — no API key required.",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-24",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/webhooks",
    "excerpt": "You can override the default webhook URL for specific API requests by including the webhook_url parameter",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-25",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/security",
    "excerpt": "Two-factor authentication (TOTP) is available for all Datalab accounts.",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-26",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/billing",
    "excerpt": "Review cost_breakdown in the completed response for the billed amount.",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-27",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/on-prem/running-the-container",
    "excerpt": "A Helm chart is available for deploying the container on Kubernetes clusters.",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-28",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/changelog",
    "excerpt": "New surya-us on-premises container type — a lightweight Chandra-compatible container",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-29",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/convert-document",
    "excerpt": "Use save_checkpoint=true to save parsed state for later /extract or /segment calls.",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-docs-30",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/common/limits",
    "excerpt": "For documents exceeding these limits, use the page_range parameter to process in segments",
    "fetchedAt": "2026-09-10T18:48:31.946Z"
  },
  {
    "id": "datalab-supp-1",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/on-prem/overview",
    "excerpt": "On-prem overview: \"Customers can run our models on infrastructure they control with an Enterprise contract.\" The paid on-prem options target teams that \"Require data privacy/operate in highly-regulated environments\", need \"Extremely high volume\", or \"Model training or customization\" — while Chandra, Marker, and Surya remain free open source.",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "datalab-supp-2",
    "tier": "claimed-docs",
    "url": "https://www.datalab.to/pricing",
    "excerpt": "Pricing page: the Team plan ($400/mo) lists \"BAA / DPA\" as included, alongside 400 req/min rate limits; Enterprise adds running on your own infrastructure (air-gapped) with SSO.",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "datalab-docs-31",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/convert-document",
    "excerpt": "Convert a PDF, image, or document to markdown, HTML, JSON, or chunks.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-32",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/extract-structured-data",
    "excerpt": "Extract structured data from a document using a JSON schema.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-33",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/segment-document",
    "excerpt": "Segment a document into sections using a schema. Returns page ranges for each identified segment.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-34",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/webhooks",
    "excerpt": "Configure webhooks to receive real-time notifications when Datalab jobs complete.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-35",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/webhooks.md",
    "excerpt": "You can override the default webhook URL for specific API requests by including the `webhook_url` parameter",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-36",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/sdk/form-filling.md",
    "excerpt": "Fill PDF and image forms with structured field data using the Datalab SDK.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-37",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/sdk/file-management.md",
    "excerpt": "Datalab provides file storage for documents you want to process with pipelines or reuse across multiple API calls.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-38",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/sdk/pipelines.md",
    "excerpt": "Pipelines chain processors (convert, extract, segment, custom) into reusable, versioned configurations.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-39",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/create-document.md",
    "excerpt": "Create a DOCX document from markdown with track changes support. Supports <ins>, <del>, and <comment> tags.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-40",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/run-document-agent.md",
    "excerpt": "Run a published agent processor on a document. Address it with processor=<id>, optionally pinned to a version as <id>@<version>",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-41",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/generate-extraction-schemas.md",
    "excerpt": "For a given file, generate potential extraction schemas.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-42",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/docs/welcome/quickstart",
    "excerpt": "new accounts include a **free monthly usage allowance** (no credit card required)",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-43",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/api-reference/api-health.md",
    "excerpt": "This endpoint is used to check the health of the API, given an API key.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-44",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/billing",
    "excerpt": "Datalab bills for the processors and add-ons you run. Most have per-page rates; some also use measured compute costs.",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-docs-45",
    "tier": "claimed-docs",
    "url": "https://documentation.datalab.to/platform/changelog",
    "excerpt": "In-app playground renamed from “Forge Playground” to **Forge** (`/app/playground`).",
    "fetchedAt": "2026-09-16T21:02:57.325Z"
  },
  {
    "id": "datalab-comm-1",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/46920056",
    "excerpt": "On Datalab's Chandra-OCR: 'it doesn't follow what I consider to be a fundamental OCR rule: the input document type should also be a possible output document type. So, PDF in should mean that composited PDF output is possible. This is necessary for groundtruthing.'",
    "fetchedAt": "2026-09-10T18:51:26.704Z"
  },
  {
    "id": "datalab-probe-1",
    "tier": "probe",
    "url": "https://documentation.datalab.to/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://documentation.datalab.to/llms.txt # Datalab Documentation\n\n- [Welcome to Datalab](https://documentation.datalab.to/index.md): Datalab provides document in",
    "fetchedAt": "2026-09-16T21:03:01.378Z"
  },
  {
    "id": "datalab-probe-2",
    "tier": "probe",
    "url": "https://documentation.datalab.to/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://documentation.datalab.to/openapi.json, https://documentation.datalab.to/swagger.json, https://documentation.datalab.to/api/openapi.json, https://documentation.datalab.to/.well-known/openapi.json)",
    "fetchedAt": "2026-09-16T21:03:01.378Z"
  },
  {
    "id": "datalab-probe-3",
    "tier": "probe",
    "url": "https://documentation.datalab.to/docs/welcome/sdk/cli",
    "excerpt": "official CLI documented at https://documentation.datalab.to/docs/welcome/sdk/cli",
    "fetchedAt": "2026-09-16T21:03:01.378Z"
  }
]