{"adoption": {"forks": 958, "observed_at": "2026-08-28T04:08:32.282441+00:00", "stars": 4011}, "canonical_url": "https://ross.abutalabs.com/products/tika", "card": {"archived": false, "artifact_type": "library", "description": "The Apache Tika toolkit detects and extracts metadata and text from over a thousand different file types (such as PPT, XLS, and PDF).", "domain": ["files", "pdf", "developer-tools", "large-language-models"], "enriched": true, "function": ["parser", "ocr", "nlp", "search-engine", "etl", "cli", "http-server", "rpc"], "health_score": 80, "homepage": "https://tika.apache.org/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["apache/tika"], "name": "apache/tika", "platform": ["jvm", "cli", "self-hosted", "cross-platform"], "pushed_at": "2026-08-26T22:14:35+00:00", "repo": "apache/tika", "stars": 4011, "tags": ["content-extraction", "metadata-extraction", "file-type-detection", "markdown-output", "rag-pipelines", "document-parsing", "tika-server", "grpc", "process-isolation", "apache-project", "search", "natural-language-processing", "data-engineering", "docker"], "topics": ["java", "tika", "metadata", "extraction", "content"], "urls": [], "use_cases": ["extract text from pdfs and office documents", "detect the real file type of an uploaded file", "index documents into elasticsearch or solr for search", "convert documents to markdown for LLM and RAG pipelines", "batch parse a directory of files with fault tolerance", "run a document parsing microservice over HTTP or gRPC", "extract metadata and embedded content from files"], "what_it_is": "Apache Tika is a Java toolkit that detects file types and extracts text and metadata from over a thousand file formats (PDF, Office documents, etc.) through a single interface. It ships as an embeddable Java library, a CLI jar, a REST server, and a gRPC service, with 4.x adding Markdown output for LLM/RAG pipelines and crash-isolated forked parsing.", "when_to_avoid": ["you only need PDF parsing with fine-grained layout control (dedicated PDF libraries fit better)", "you cannot run Java 17 or a JVM in your environment", "you need lightweight, single-format extraction with minimal dependencies"], "when_to_choose": ["you need one API to parse many heterogeneous file formats", "you are building search indexing or content analysis pipelines", "you want LLM/RAG-ready Markdown extraction from documents", "you need robust parsing of untrusted files with process isolation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tika", "repo": "apache/tika", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:32.282441+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:24:01.629658+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e88a9963825fe3336a2804504d4a437cdf2268c97b114eabaeb104a33569f37a", "fetched_at": "2026-08-28T04:08:32.282441+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/tika"}, {"content_hash": "7457e316c9a8c8149d822fb09d1e1270d61408824f57f3bf0f3b9d39a85fbb05", "fetched_at": "2026-08-29T09:17:08.272918+00:00", "kind": "homepage", "missing": false, "url": "https://tika.apache.org/"}, {"content_hash": "48b480381673253586f7f3d9c5c9cc8a388505697037a01d279e9c7bf4e43db4", "fetched_at": "2026-08-29T09:17:08.283036+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/index.html"}, {"content_hash": "524acdda97116ba7439b33b6a9a1745eba493cdc0a78d2b19230bc6fcb8c1ef4", "fetched_at": "2026-08-29T09:17:08.285257+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/migration-to-4x/index.html"}, {"content_hash": "2ec47ffa7b4d7254e5c8e2321bad3f4b6d23b3bbab24d78fead7e9e65f902272", "fetched_at": "2026-08-29T09:17:08.287448+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/index.html"}, {"content_hash": "dc665d330b3d9697de9ae92045b7459d221694fe7d7d210f2a14f0b05e2c0c0b", "fetched_at": "2026-08-29T09:17:08.289317+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/using-tika/java-api/getting-started.html"}, {"content_hash": "8d2303641644506912c2c44700018a2d779dcd2268ad6394f45e5699992481e8", "fetched_at": "2026-08-29T09:17:08.291548+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/pipes/index.html"}, {"content_hash": "e937cd81d0732cfe8f2087c008c2e4b004f916e87e3757e490b9fb5b751a0f40", "fetched_at": "2026-08-29T09:17:08.293306+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/docs/4.0.x/configuration/index.html"}, {"content_hash": "7278e24bd3997898ea1896c8902f1553b3c5da4194218cad629a49c7ecfe34a1", "fetched_at": "2026-08-29T09:17:08.295121+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/4.0.0/api"}, {"content_hash": "4747addd7bce3b2f8ae85cd8ce2319d010d33a3acd5e06f547d6aa2c764c925c", "fetched_at": "2026-08-29T09:17:08.296932+00:00", "kind": "site_page", "missing": false, "url": "https://tika.apache.org/3.3.2/api"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 6314, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}