I've indexed a few pdf files but when I search with a specific query I'm not getting relevant results as I expected. I would like to improve the relevancy of each document.
we need to perform analysis phase(kind of NLP) to get the most relevant document, so while searching it doesn't match with stop words etc.
Can you please give me any info of how to perform analysis(applying analysers and tokenizers) once I index the document. ?
any suggestions will be helpful.
Thanks for your time