pdf、doc、docx格式文档如何处理

[yangzheyulive]

示例中只有txt和web部分的处理，pdf、doc、docx部分如何处理呢？
CreateDocumentReq createReq = CreateDocumentReq.builder()
.datasetID(datasetID)
.documentBases(Arrays.asList(
DocumentBase.buildWebPage("web doc example", "https://your-website.com"), //create datasets documents by web page
DocumentBase.buildLocalFile("file doc example", "your file content", "txt"))) //create datasets documents by local file
.build();