{
    "name": "Apache Tika",
    "slug": "apache-tika",
    "categories": [
        12
    ],
    "date_created": "2025-02-05",
    "type": "ct",
    "updateable": true,
    "privileged": false,
    "interface_port": 9998,
    "documentation": null,
    "website": "https://tika.apache.org/",
    "logo": "https://tika.apache.org/tika.png",
    "description": "The Apache Tika™ toolkit detects and extracts metadata and text from over a thousand different file types (such as PPT, XLS, and PDF). All of these file types can be parsed through a single interface, making Tika useful for search engine indexing, content analysis, translation, and much more.",
    "install_methods": [
        {
            "type": "default",
            "script": "ct/apache-tika.sh",
            "resources": {
                "cpu": 1,
                "ram": 2024,
                "hdd": 10,
                "os": "debian",
                "version": "12"
            }
        }
    ],
    "default_credentials": {
        "username": null,
        "password": null
    },
    "notes": []
}