{"adoption": {"forks": 2750, "observed_at": "2026-08-28T04:11:52.872269+00:00", "stars": 28817}, "canonical_url": "https://ross.abutalabs.com/products/opendataloader-pdf", "card": {"archived": false, "artifact_type": "library", "description": "PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.", "domain": ["pdf", "accessibility", "developer-tools", "files"], "enriched": true, "function": ["parser", "pdf", "ocr", "rag"], "health_score": 100, "homepage": "https://opendataloader.org", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["opendataloader-project/opendataloader-pdf"], "name": "opendataloader-project/opendataloader-pdf", "platform": ["cross-platform", "cli", "python", "jvm"], "pushed_at": "2026-08-26T13:05:00+00:00", "repo": "opendataloader-project/opendataloader-pdf", "stars": 28817, "tags": ["pdf-parser", "document-parsing", "rag-pipeline", "pdf-accessibility", "tagged-pdf", "pdf-ua", "eaa-compliance", "bounding-boxes", "reading-order", "table-extraction", "markdown-conversion", "llm-ready-data", "prompt-injection-defense", "layout-analysis", "a11y", "retrieval-augmented-generation", "nodejs"], "topics": ["json", "markdown", "pdf", "ai", "document-parsing", "html", "pdf-converter", "tables", "pdf-parser", "rag", "accessibility", "bounding-box", "eaa", "ocr", "pdf-accessibility", "pdf-extraction", "pdf-ua", "tagged-pdf", "ocr-recognition", "a11y"], "urls": [], "use_cases": ["convert PDF documents to markdown for a RAG pipeline", "extract tables from PDFs while preserving row and column structure", "parse multi-column or academic PDFs with correct reading order", "get bounding box coordinates for every PDF element to support citations", "run OCR on scanned PDFs locally without cloud APIs", "automate PDF accessibility tagging for EAA or Section 508 compliance", "detect hidden prompt injection text in PDFs before feeding them to agents"], "what_it_is": "OpenDataLoader PDF is an open-source (Apache-2.0) PDF parser that converts PDFs into AI-ready Markdown, JSON with per-element bounding boxes, and HTML, featuring XY-Cut++ reading order, table extraction, and optional hybrid-mode OCR for scanned documents. It also automates PDF accessibility by auto-tagging untagged PDFs into Tagged PDF as a foundation for PDF/UA compliance, and ships local AI-safety filters that strip hidden prompt-injection text before documents reach LLM agents.", "when_to_avoid": ["You only need to view, annotate, or fill PDF forms rather than extract structured data", "Your environment cannot run Java 11+, since the core parser is JVM-based", "You need PDF/UA export or the accessibility studio, which are gated behind the enterprise add-on rather than the open-source core", "You need a browser-side or pure-JavaScript in-process parser with no external runtime or backend server"], "when_to_choose": ["You need accurate, deterministic PDF-to-Markdown/JSON conversion for RAG or LLM pipelines with correct reading order, tables, and source coordinates", "You must process documents 100% locally and privately on CPU, with no data transmission and no GPU required", "You handle scanned or complex pages and want optional AI/OCR hybrid enhancement while keeping simple pages fast", "You need to scale PDF accessibility remediation by auto-tagging untagged PDFs toward PDF/UA and validating with veraPDF"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/opendataloader-pdf", "repo": "opendataloader-project/opendataloader-pdf", "role": "main", "score": 86}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:52.872269+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:54:19.141207+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2304f60bba1aa8e9fbbf94a76763c1a39a59392b90c9904af2a77c3126e328cd", "fetched_at": "2026-08-28T04:11:52.872269+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendataloader-project/opendataloader-pdf"}, {"content_hash": "23c88043f31e7c7972740419ab94a0ac9acc80f9c11ea72d201907efd2cce70c", "fetched_at": "2026-08-29T07:50:39.575049+00:00", "kind": "homepage", "missing": false, "url": "https://opendataloader.org"}, {"content_hash": "3a1541cedc184c8adf818924c14687b2a92a477e373366f219af8270157f88be", "fetched_at": "2026-08-29T07:50:39.584446+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs"}, {"content_hash": "668c8421d2aa5427e49882da9e23b79062281c55baf8098881917ee8b7cc4a01", "fetched_at": "2026-08-29T07:50:39.586759+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/quick-start-python"}, {"content_hash": "0e579ae96cb600809e6e599e73675fec6bef9782fa35678e611913ecdb1d8985", "fetched_at": "2026-08-29T07:50:39.589629+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reading-order"}, {"content_hash": "d23722d5ec13492708b11355152ba614c075bf92b32f718414537ec37e5b6e39", "fetched_at": "2026-08-29T07:50:39.592026+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/hybrid-mode"}, {"content_hash": "de2eece53ed9edff2b7b6a63be8c939dca26360ee1f80ffc4166a6d0367b9666", "fetched_at": "2026-08-29T07:50:39.594750+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/reference/json-schema"}, {"content_hash": "4016a8b17e2ac680b6f6f448e63d59b6876d9a5c1e860785b65f9cb91d371129", "fetched_at": "2026-08-29T07:50:39.598106+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/ai-safety"}, {"content_hash": "d8bd0ae2cf6c65d664cbe988361e1f130e1843ca65ec93c9fd5a776f3a3b11be", "fetched_at": "2026-08-29T07:50:39.601672+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/benchmark"}, {"content_hash": "56ac896c5221061ad73ccea41ec4059eb8fa7177463c7b4fdc7589cbc50434b6", "fetched_at": "2026-08-29T07:50:39.604473+00:00", "kind": "site_page", "missing": false, "url": "https://opendataloader.org/docs/rag-integration"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 34, "rhythm": 99}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 477, "days_push": 7, "days_rel": 8, "gap_med": 1, "n_releases_24m": 54}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}