src/main/resources/eu/mulk/aendggner/tika-config.xml

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<properties>
  <service-loader dynamic="true" loadErrorHandler="IGNORE"/>

  <encodingDetectors>
    <encodingDetector class="org.apache.tika.detect.DefaultEncodingDetector"/>
  </encodingDetectors>

  <translator class="org.apache.tika.language.translate.DefaultTranslator"/>

  <detectors>
    <detector class="org.apache.tika.detect.DefaultDetector"/>
  </detectors>

  <parsers>

    <parser class="org.apache.tika.parser.DefaultParser">
      <parser-exclude class="org.apache.tika.parser.pdf.PDFParser"/>
      <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
    </parser>

    <parser class="org.apache.tika.parser.pdf.PDFParser">
      <params>
        <param name="extractInlineImages" type="bool">true</param>
        <param name="ocrStrategy" type="string">auto</param>
      </params>
    </parser>

    <parser class="org.apache.tika.parser.ocr.TesseractOCRParser"/>

  </parsers>
</properties>