Merge pull request #1455 from swirlai/ds-3103

restore link to Xethub study; their site is working again

Author: erikspears

docs/index.md

@@ -33,7 +33,7 @@ The re-ranking process is roughly the following:
 * Vectorize each result snippet (or parts of it)
 * Re-rank the results by aggregating the similarity, frequency and position, and adjusting for other factors like length variation, freshness, etc 
 
-The [Xethub study](https://swirlaiconnect.com/blog/using-vectors-without-a-vector-database) as [explained by Simson Garfinkel](https://www.linkedin.com/pulse/vector-databases-rag-simson-garfinkel-hzule/) showed that re-ranking so-called "naive" search engines like those that use the BM25 algorithm for retrieval, outperforms moving the data into a vector database for many common NLP tasks such as question answering.
+The [Xethub study](https://xethub.com/blog/you-dont-need-a-vector-database) as [explained by Simson Garfinkel](https://www.linkedin.com/pulse/vector-databases-rag-simson-garfinkel-hzule/) showed that re-ranking so-called "naive" search engines like those that use the BM25 algorithm for retrieval, outperforms moving the data into a vector database for many common NLP tasks such as question answering.
 
 SWIRL AI Connect also includes state-of-the-art cross-silo [Retrieval Augmented Generation (RAG)](https://en.wikipedia.org/wiki/Retrieval-augmented_generation) for generating AI insights like summarization, question answering and visualization of relevant result sets.