Table of contents :

What are the four stages of search?

DALL·E 2023-01-12 11.46.07 - An oipaint of a man climbing an infinite stair while morphing to a robot

Table of contents :

– Classical search –
Anything around BM25 statistical scoring. Including #elasticsearch , Apache #solrAlgolia, and WPSOLR https://www.wpsolr.com.

– Classical search AI augmented –
Still the classical engines, but with a pre-indexing phase to extract some semantic features. Including WPSOLR https://www.wpsolr.com/guide/configuration-step-by-step-schematic/activate-extensions/extension-nlp/

– Vector search pre-trained –
This includes all vector databases like SeMI Technologies Weaviate, Pinecone, Vespa, Qdrant, with a pre-trained LLM vectorizer. See https://www.wpsolr.com/guide/configuration-step-by-step-schematic/configure-your-indexes/create-weaviate-index/

– Vector search fine-tuned –
This includes all vector databases mentioned earlier, but with a fine-tuned LLM vectorizer.
None of them come with an automatic pipeline to fine-tune the model.
Or perhaps Google Retail search API https://www.wpsolr.com/guide/configuration-step-by-step-schematic/configure-your-indexes/create-a-google-retail-index/

#wpsolr #ai #google #pipeline #vectorsearch #finetuning #largelanguagemodels #searchengines #elasticsearch #apachesolr #algolia #weaviate #pinecone

Related posts ... not powered by WPSOLR 😊

An overview of Weaviate’s architecture

Introduction Weaviate is an open-source, cloud-native, and unified search engine that uses vector-based machine learning to power its search technology. It allows you to search