[
  {
    "id": "llamaparse-docs-1",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/getting_started/",
    "excerpt": "Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-2",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/",
    "excerpt": "Parse is an agentic document parser built for LLM pipelines—layout-aware OCR that turns PDFs, scans, tables, and charts into clean markdown, text, or JSON.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-3",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/extract/",
    "excerpt": "LlamaExtract provides a simple API for extracting structured data from unstructured documents like PDFs, text files, and images.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-4",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/classify/",
    "excerpt": "Classify lets you automatically categorize documents into types you define (for example: invoice, receipt, contract) using natural-language rules.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-5",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/split/",
    "excerpt": "The Split API provides a simple way to automatically segment concatenated PDFs into logical document sections based on content categories.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-6",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/webhooks/",
    "excerpt": "Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-7",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/self_hosting/",
    "excerpt": "LlamaCloud can be deployed entirely within your own infrastructure. Self-hosted deployments — also known as BYOC (Bring Your Own Cloud) — give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-8",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/for-agents/",
    "excerpt": "https://mcp.llamaindex.ai/mcp is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-9",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/",
    "excerpt": "Identity and access. Use SSO and role-based access controls to manage access to your organization and projects.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-10",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/supported_document_types/",
    "excerpt": "LlamaParse supports 130+ file formats across four categories.",
    "fetchedAt": "2026-09-10T18:45:46.511Z"
  },
  {
    "id": "llamaparse-docs-11",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/getting_started/",
    "excerpt": "result = client.parsing.parse(    file_id=file.id,    tier=\"agentic\",    version=\"latest\",    expand=[\"markdown\"],)",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-12",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/",
    "excerpt": "Turn PDFs, scans, or images into clean LLM-ready text",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-13",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/",
    "excerpt": "Pull structured JSON out of documents that matches my schema",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-14",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/extract/",
    "excerpt": "Just define your Extraction Configuration (schema and settings), drag and drop any supported document into LlamaParse and extract data from your documents.",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-15",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/examples/",
    "excerpt": "pull every table out into pandas DataFrames with source-page provenance, and turn on Cost Optimizer to keep costs down on long mixed-complexity documents",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-16",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/for-agents/",
    "excerpt": "`https://mcp.llamaindex.ai/mcp` is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-17",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/self_hosting/",
    "excerpt": "Self-hosted deployments — also known as **BYOC (Bring Your Own Cloud)** — give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-gh-1",
    "tier": "github",
    "url": "https://github.com/run-llama/llama_cloud_services",
    "excerpt": "Please migrate to the new packages: - **Python**: `pip install llama-cloud>=1.0`",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-18",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/",
    "excerpt": "Use SSO and role-based access controls to manage access to your organization and projects.",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-19",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/",
    "excerpt": "Build a hosted vector search pipeline for RAG",
    "fetchedAt": "2026-09-10T18:47:38.347Z"
  },
  {
    "id": "llamaparse-docs-20",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/",
    "excerpt": "One API key, one SDK, and five composable products: Parse (agentic OCR), Extract (structured data), Classify, Split, and Index.",
    "fetchedAt": "2026-09-10T18:49:54.533Z"
  },
  {
    "id": "llamaparse-docs-21",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/for-agents/mcp/",
    "excerpt": "search_docs — a basic lexical search using BM25 2. grep_docs — exact search using regex 3. read_doc — provides an interface to read the entire contents of any given page path",
    "fetchedAt": "2026-09-10T18:49:54.533Z"
  },
  {
    "id": "llamaparse-docs-22",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/examples/",
    "excerpt": "Turn on the enriched forms pass to get each form page as structured JSON — fields with values, checkbox states, and bounding boxes — and read it back with expand=forms.",
    "fetchedAt": "2026-09-10T18:49:54.533Z"
  },
  {
    "id": "llamaparse-docs-23",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/examples/",
    "excerpt": "turn on Cost Optimizer to keep costs down on long mixed-complexity documents",
    "fetchedAt": "2026-09-10T18:49:54.533Z"
  },
  {
    "id": "llamaparse-docs-24",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/self_hosting/",
    "excerpt": "LlamaCloud can be deployed entirely within your own infrastructure... give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.",
    "fetchedAt": "2026-09-10T18:49:54.533Z"
  },
  {
    "id": "llamaparse-docs-25",
    "tier": "claimed-docs",
    "url": "https://www.llamaindex.ai/llamaparse",
    "excerpt": "Turn even the most complex layouts, tables, charts, handwriting, checkboxes, and images into clean markdown",
    "fetchedAt": "2026-09-10T18:49:54.533Z"
  },
  {
    "id": "llamaparse-supp-1",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/",
    "excerpt": "Enterprise readiness: \"LlamaParse Platform has completed a SOC 2 Type II audit. The report and subprocessor list are available through the Trust Center. A HIPAA-compliant processing pipeline with a Business Associate Agreement (BAA) is available for Enterprise customers.\"",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "llamaparse-supp-2",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/",
    "excerpt": "Enterprise readiness, deployment & data residency: \"managed SaaS, single-tenant, BYOC, self-hosting, and regional endpoints\" — the platform documents self-hosting and regional deployment options alongside the managed cloud.",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "llamaparse-docs-26",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/for-agents/",
    "excerpt": "My agent should be able to search these docs",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-27",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/for-agents/mcp/",
    "excerpt": "The server ships with the following tools: 1. `search_docs` — a basic lexical search using BM25 2. `grep_docs` — exact search using regex 3. `read_doc` — provides an interface to read the entire contents of any given page path",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-28",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/self_hosting/",
    "excerpt": "Deploy LlamaCloud in your own cloud infrastructure with full self-hosting and BYOC support. Run LlamaParse, LlamaExtract, and the complete LlamaCloud platform on Kubernetes using Helm charts — on AWS, Azure, or GCP.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-29",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/",
    "excerpt": "LlamaParse Platform has completed a SOC 2 Type II audit. The report and subprocessor list are available through the Trust Center. A HIPAA-compliant processing pipeline with a Business Associate Agreement (BAA) is available for Enterprise customers.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-30",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/integrations/data_sinks/",
    "excerpt": "If you don’t want to set up and host a vector database, we offer a full-managed option in which we host the vector database for you. Alternatively, you can host your own vector database and connect it to Index",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-31",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/integrations/embedding_models/",
    "excerpt": "We support a variety of embedding models that you can choose from",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-32",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/extract/examples/",
    "excerpt": "Extract structured data from SEC filings with citations. Verify values against the source document when extracting from complex financial documents.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-33",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/extract/examples/",
    "excerpt": "Generate extraction schemas with a prompt",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-34",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/extract/examples/",
    "excerpt": "Extract repeating entities from documents using table row extraction",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-35",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/v1/examples/",
    "excerpt": "Guide parsing output with custom prompts. Extract specific data from a McDonald's receipt by instructing the parser to focus only on prices and totals.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-36",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/parse/v1/examples/",
    "excerpt": "Parse Excel files and build a RAG app to answer questions about spreadsheet dat",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-37",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/split/examples/",
    "excerpt": "Split a PDF containing multiple documents (essays, research papers) into separate segments using AI-powered classification.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-38",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/classify/examples/",
    "excerpt": "Classify documents from the CUAD dataset as co-branding contracts or affiliate agreements.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-39",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/classify/examples/",
    "excerpt": "Save reusable classification rules as a configuration and reference them by ID across multiple jobs.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-40",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/examples/",
    "excerpt": "Create your first index and build an AI agent using LlamaIndex workflows. Query banking documents with an agent that can use retrieval tools and perform calculations.",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-docs-41",
    "tier": "claimed-docs",
    "url": "https://developers.llamaindex.ai/python/framework/llama_cloud/",
    "excerpt": "Sign up for LlamaCloud and get 10,000 free credits per month",
    "fetchedAt": "2026-09-16T21:23:05.512Z"
  },
  {
    "id": "llamaparse-comm-1",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39443972",
    "excerpt": "I tried LlamaParse and was impressed by the result on a document with complex layout. None of the open-source parsers provided results even close.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-comm-2",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39443972",
    "excerpt": "LlamaParse solves exactly the problem I've encountered over and over with RAG. Getting structured info from unstructured data is a pain.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-comm-3",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39443972",
    "excerpt": "I found the LlamaParse interface a bit confusing. It can extract numbers in tables, but the output isn't provided in tabular format—access to the numbers is only available through question-answering.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-comm-4",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39443972",
    "excerpt": "Signing up for LlamaParse was rough: email signup endlessly redirected, click link in email, asked to sign up again with email, click link again, etc. Ended up using Google sign-in instead.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-comm-5",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39443972",
    "excerpt": "A PDF parser? Seriously that's what all this fuss is about? There are so many options already out there (PDFBox, iText, Unstructured, PyPDF, PDF.js, PdfMiner, hyperscaler extraction services). Super confused why anyone needs this.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-comm-6",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/39443972",
    "excerpt": "I ran the baseline PyPDF+Naive RAG benchmark myself and got a faithfulness score of 0.980, actually higher than the 0.667 the team reported for their LlamaParse-based pipeline—numbers didn't match what was published.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-comm-7",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=39443972",
    "excerpt": "LlamaParse looks nice. Is there a way to return page numbers also with the markdown? This is important for our use case.",
    "fetchedAt": "2026-09-10T18:50:48.780Z"
  },
  {
    "id": "llamaparse-probe-1",
    "tier": "probe",
    "url": "https://developers.llamaindex.ai/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://developers.llamaindex.ai/llms.txt # LlamaIndex Documentation\n\n> LlamaIndex is a framework for building LLM-powered applications over your data. It support",
    "fetchedAt": "2026-09-16T21:23:07.100Z"
  },
  {
    "id": "llamaparse-probe-2",
    "tier": "probe",
    "url": "https://developers.llamaindex.ai/llamaparse/.md",
    "excerpt": "PROBE docs-md: HTTP 404 at https://developers.llamaindex.ai/llamaparse/.md",
    "fetchedAt": "2026-09-16T21:23:07.100Z"
  },
  {
    "id": "llamaparse-probe-3",
    "tier": "probe",
    "url": "https://developers.llamaindex.ai/openapi.json",
    "excerpt": "PROBE openapi: all candidate paths 404 (https://developers.llamaindex.ai/openapi.json, https://developers.llamaindex.ai/swagger.json, https://developers.llamaindex.ai/api/openapi.json, https://developers.llamaindex.ai/.well-known/openapi.json)",
    "fetchedAt": "2026-09-16T21:23:07.100Z"
  },
  {
    "id": "llamaparse-probe-4",
    "tier": "probe",
    "url": "https://developers.llamaindex.ai/for-agents/mcp/",
    "excerpt": "official MCP server documented at https://developers.llamaindex.ai/for-agents/mcp/",
    "fetchedAt": "2026-09-16T21:23:07.100Z"
  }
]