Sells in this field
Semantic search and reranking with Cohere and Pinecone
Reranking models can improve the relevance of vector search results, and Pinecone and Cohere demonstrate this with Cohere's Rerank 3.5 on financial data.
Topic
6 videos.
Semantic search tries to match the meaning of a query, not just its exact words. A search for "cheap laptop for students" can then find a page that never uses those words. It usually works by turning text into lists of numbers called vectors and finding the closest ones. This matters to site owners in two ways. Big search engines use related methods, and some sites build their own search box.
This page leans towards the second. Most videos come from companies that sell search products, and they are about building search systems, not about website SEO. What is a vector database? starts from scratch and suits beginners. Semantic search and reranking with Cohere and Pinecone is more advanced and from 2025. Most of the rest are from 2020 to 2023, and the field has moved quickly, so check the tools they use.
Sells in this field
Reranking models can improve the relevance of vector search results, and Pinecone and Cohere demonstrate this with Cohere's Rerank 3.5 on financial data.
Sells in this field
A vector database stores vectors, and Zack Proser starts from what vectors are before explaining semantic search and how RAG addresses LLM hallucinations.
Older: check current guidanceSells in this field
Semantic search sounds like the future, but can it do the job today? Dustin Coates of Algolia sets out what goes into it and what it can actually do for users.
Older: check current guidanceSells in this field
Nils Reimers explains how Generative Pseudo-Labeling (GPL) can be used to train models for semantic search.
Older: check current guidanceSells in this field
Semantic search gets a hands-on workshop, moving from NLP basics to vector databases and a worked search app, then audience questions.
Older: check current guidanceSells in this field
Image search gets a talk from Bill Slawski, who explains how Google might make sense of pictures and link queries to them, with suggestions for choosing meaningful images for content.
Older: check current guidance