How to combine my python nlp solution for document ranking with solr for indexing?

Asked Oct 26 '19 at 06:12

Active Oct 26 '19 at 06:12

Viewed 244 times

I'm new to NLP and Solr. I'm trying to build an application to rank past court case documents based on a newly given case document. I confused about how to use Solr for document indexing to speed up my processing time.

I have built a python solution including Preprocessing with NLTK library and lemmatization with Spacy library. And I have calculated document similarity with Word2Vec Word Embedding Model.

I'm stuck in the middle and am confused about whether I have done correctly. Can someone help me out?

Thanks in advance.

asked Oct 26 '19 at 06:12

Smirithika Chandrasegar

can you post some code – DBaker Oct 26 '19 at 12:37
1

So what is your goal by introducing Solr to the mix? – MatsLindh Oct 26 '19 at 20:15
I'm trying to index my documents to speed up the process. – Smirithika Chandrasegar Nov 05 '19 at 06:55
https://stackoverflow.com/a/2956962/11185766 check this one – Darkknight Feb 11 '21 at 03:00
@SmirithikaChandrasegar there are a bunch of ways to do this task. there is a tool called Milvus it's good for embedding search. I'm mentioning this because you mentioned you have the embedding. There is no use with embedding in solr as far as I know https://milvus.io/docs/v0.10.6/example_code.md – Darkknight Mar 04 '21 at 12:21

How to combine my python nlp solution for document ranking with solr for indexing?

0 Answers0