[
  {
    "id": "unstructured-docs-1",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/quickstart-api",
    "excerpt": "Use Unstructured with Python to go from an unstructured source file to structured data output in about 5 minutes.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-2",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/quickstart",
    "excerpt": "Use Unstructured with Claude and plain language prompts to go from an unstructured source file to structured data output in about 5 minutes.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-3",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io",
    "excerpt": "Define your own target JSON schema and have Unstructured extract values from your source files and data records directly into that shape in JSON format.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-4",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/transform/overview",
    "excerpt": "You can call the Unstructured API with the Unstructured Python SDK and with standard REST clients (such as cURL and Postman).",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-5",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/api/job/job-apis",
    "excerpt": "Track and control the processing jobs that execute your workflows. Trigger runs, monitor status, download results, and inspect any files that failed during processing.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-6",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/workflow/overview",
    "excerpt": "The Unstructured Pipelines workflow designer features a no-code user interface for transforming your unstructured data into data that is ready for retrieval-augmented generation (RAG).",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-7",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/workflow/workflows",
    "excerpt": "Build and manage Unstructured workflows with the Python SDK or REST endpoints. Create, update, run, and delete workflows that process and transform documents from source to destination.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-8",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io",
    "excerpt": "Replace DIY pipelines: Move solutions into production faster. Reduce engineering costs. Eliminate maintenance. Resilient partitioning logic and robust visibility built in from day one.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-9",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io",
    "excerpt": "Unify data silos: Discover hidden insights with 35+ connectors and 65+ file types. Consistent JSON format. All-in-one data layer.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-10",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/quickstart-api",
    "excerpt": "Auto evaluates each page and routes it to Fast, High Res, or VLM partitioning, balancing quality, speed, and cost.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-11",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/chunking",
    "excerpt": "You can further control this behavior with by title, by page, and by similarity chunking strategies.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-12",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/enriching/table-to-html",
    "excerpt": "After partitioning, you can have Unstructured generate representations of each detected table in HTML markup format.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-13",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/enriching/generative-ocr",
    "excerpt": "After partitioning, you can have a vision language model (VLM) optimize the fidelity of text blocks that Unstructured initially processed during its partitioning phase.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-14",
    "tier": "claimed-docs",
    "url": "https://unstructured.io/pricing",
    "excerpt": "Start processing your data with 10,000 free pages.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-15",
    "tier": "claimed-docs",
    "url": "https://unstructured.io/pricing",
    "excerpt": "Deploy Unstructured in your own dedicated instance or VPC with multi-user access, full data isolation, dedicated technical support, and pricing tailored to your needs.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-16",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/business/dedicated-instances/security/security-model",
    "excerpt": "IP Allowlisting - restricts Unstructured platform access to specific source IP addresses or CIDR ranges. Submit a support ticket with your IP list to enable this.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-17",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/transform/overview",
    "excerpt": "This includes most AI code editors, IDEs, desktop assistants, and coding-agent frameworks. Tools such as the Codex CLI, Claude Code, Visual Studio Code, Cursor, Devin, and JetBrains IDEs are just a few examples.",
    "fetchedAt": "2026-09-10T18:46:47.124Z"
  },
  {
    "id": "unstructured-docs-18",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/quickstart-api",
    "excerpt": "This quickstart partitions an example company annual report with a sample Python script and the Unstructured API.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-19",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/transform/overview",
    "excerpt": "You can call the Unstructured API with the [Unstructured Python SDK](/overview-python-sdk) and with standard [REST clients](/overview-rest-api) (such as cURL and Postman).",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-20",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/workflow/overview",
    "excerpt": "The [Unstructured Pipelines](/pipelines/overview) workflow designer features a no-code user interface for transforming your unstructured data into data that is ready for retrieval-augmented generation (RAG).",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-21",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/business/dedicated-instances/security/security-model",
    "excerpt": "**IP Allowlisting** - restricts Unstructured platform access to specific source IP addresses or CIDR ranges. Submit a support ticket with your IP list to enable this.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-22",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/transform/overview",
    "excerpt": "The Transform MCP server enables you to link your AI tools to Transform. You can then use your AI tools to have Transform ingest your local files and output the results as partitioned, enriched, chunked, and embedded data, ready for your immediate use.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-23",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/overview-python-sdk",
    "excerpt": "The Unstructured Python SDK enables you to call the Unstructured API with standard Python code to partition, enrich, chunk, and embed your files.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-24",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/partitioning",
    "excerpt": "To choose one of these strategies, select one of the following four **Partition Strategy** options for the **Partitioner** node of a workflow.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-25",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/chunking",
    "excerpt": "You can further control this behavior with [by title](#chunk-by-title-strategy), [by page](#chunk-by-page-strategy), and [by similarity](#chunk-by-similarity-strategy) chunking strategies.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-26",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/structured-data-extractor/data-extractor",
    "excerpt": "It lets you define the target structure up front. Unstructured then extracts values in a consistent JSON format that matches your fields, ready to use in your own applications.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-27",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/enriching/table-to-html",
    "excerpt": "After partitioning, you can have Unstructured generate representations of each detected table in HTML markup format. This table-to-HTML output is generated by using agentic AI or a vision language model (VLM).",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-28",
    "tier": "claimed-docs",
    "url": "https://unstructured.io/pricing",
    "excerpt": "Built for teams of any size that need privacy, control, and security. Deploy Unstructured in your own dedicated instance or VPC with multi-user access, full data isolation, dedicated technical support, and pricing tailored to your needs.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-docs-29",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io",
    "excerpt": "Discover hidden insights with 35+ connectors and 65+ file types. Consistent JSON format. All-in-one data layer.",
    "fetchedAt": "2026-09-10T18:49:08.319Z"
  },
  {
    "id": "unstructured-supp-1",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/business/security-compliance/overview",
    "excerpt": "Security and compliance overview: \"SOC 2 Type 2: Controls are implemented and audited for security, availability, and confidentiality. GDPR: Data handling practices conform to the General Data Protection Regulation (GDPR) ... HIPAA: The system meets the security requirements of the Health Insurance Portability and Accountability Act (HIPAA) for safeguarding protected health information (PHI).\"",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "unstructured-docs-30",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/overview-rest-api",
    "excerpt": "You can call the Unstructured API through REST endpoints by using a REST client (such as cURL or Postman) to partition, enrich, chunk, and embed your files.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-31",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/quickstart-api",
    "excerpt": "From login to structured JSON in about 5 minutes, with Unstructured and Python.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-32",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/partitioning",
    "excerpt": "_Partitioning_ converts content from unstructured files and semi-structured data records into structured [document elements and metadata](/concepts/document-elements) in a predefined, consistent, expressive, and contextualized JSON format.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-33",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/chunking",
    "excerpt": "After partitioning, _chunking_ rearranges the resulting document elements into manageable “chunks” to stay within the limits of an embedding model and to improve retrieval precision.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-34",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/concepts/structured-data-extractor/data-extractor",
    "excerpt": "Learn how Unstructured’s structured data extractor turns partitioned documents into custom defined JSON fields instead of generic text elements.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-35",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/transform/quickstart/embed.md",
    "excerpt": "Create a job to partition, chunk, and embed local files into AI-ready JSON with vector embeddings for semantic search.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-36",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/transform/quickstart/enrich.md",
    "excerpt": "Create a job to partition and enrich local files into AI-ready JSON with image descriptions, table HTML, named entities, and generative OCR output.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-docs-37",
    "tier": "claimed-docs",
    "url": "https://docs.unstructured.io/api-reference/workflow/sources/azure-blob-storage.md",
    "excerpt": "Ingest your files into Unstructured from Azure Blob Storage.",
    "fetchedAt": "2026-09-16T22:01:17.934Z"
  },
  {
    "id": "unstructured-probe-1",
    "tier": "probe",
    "url": "https://docs.unstructured.io/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://docs.unstructured.io/llms.txt # Unstructured\n\n> ## Agent Instructions\n> Fetch site content guidance and key links about the MCP server, SDK, and API a",
    "fetchedAt": "2026-09-16T22:01:24.277Z"
  },
  {
    "id": "unstructured-probe-2",
    "tier": "probe",
    "url": "https://docs.unstructured.io/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://docs.unstructured.io/openapi.json, https://docs.unstructured.io/swagger.json, https://docs.unstructured.io/api/openapi.json, https://docs.unstructured.io/.well-known/openapi.json)",
    "fetchedAt": "2026-09-16T22:01:24.277Z"
  }
]