Reading contents of Word, PDF file

[cnshum]

i have this use case where i need to read the contents of CV/resume uploaded by users and pass it to a LLM to extract the skills. Currently, I am only able to do so using a txt file (refer to the below code).  But when i use this code on a pdf or word file, the contents are all weird symbols. Can anyone point me in the right direction?

code:

extractSkillsFromCV: function() {

        var tableSysId = this.getParameter('sysparm_tableSysId');

        var grAttach = new GlideRecord("sys_attachment");

        grAttach.addEncodedQuery("table_sys_id=" + tableSysId);

        grAttach.query();

        if(grAttach.next()){

            var document;

            var attach = new GlideSysAttachment().getContentStream(grAttach.sys_id);

            var reader = new GlideTextReader(attach);

            var ln = ' ';

            while ((ln = reader.readLine()) != null) {

                document += ln + "\n";

            }

            return document;

        }

[Tanushree Maiti]

Hi @cnshum 

You can try following code as  mentioned in following post:

getPayloadFileInBase64 : function(sourceGrSysId, fileName){

var attGr = this.getAttGr(sourceGrSysId, fileName);

if(attGr.next()) {

this.attachmentGr = attGr;

var gsa = GlideSysAttachmentInputStream(attGr.getValue("sys_id"));

var baos = new Packages.java.io.ByteArrayOutputStream();

gsa.writeTo(baos);

baos.close();

var payload = GlideBase64.encode(baos.toByteArray());

return payload;

}

return "";

},

getAttGr: function(sysId, fileName){

var attGr = new GlideRecord("sys_attachment");

attGr.addQuery("table_sys_id", sysId);

attGr.addQuery("file_name", fileName);

attGr.query();

return attGr;

},

Refer: https://www.servicenow.com/community/developer-forum/getting-contents-of-an-attachment/m-p/2003454

https://www.servicenow.com/community/developer-forum/reading-the-content-of-attachment-files/td-p/27...

https://www.servicenow.com/community/architect-articles/attachment-content-processing/ta-p/2330637