Minimizing the risks of a search migration project
A search migration project can be risky – how can you identify & mitigate those risks with measurement, a great team and expert help?
Hybrid vigor: a winning way to use hybrid search
How we utilized a variant of BM25 for sparse vector scoring and combined it with cosine similarity between dense vectors to achieve a hybrid ranking algorithm with better search performance than either technique alone, validated at TREC 2021
Pete learns that sometimes redirects are all you need
Some queries require a special technique to be improved: the need a redirect to a landing page. Learn how to implement this with Chorus and about types of redirects, pitfalls, …
How to train a search team – and what does it cost?
What are the options for training a search team? With news of a brand new training option from OSC
Maximizing Relevance with Hyperparameter Optimization
Find out how Hyperparameter Optimization helps you figure out the best values to use for classical search rankers
5 Reasons why you should remove stop words (at indexing time)
Here’s 5 reasons why you should remove stop words from your search index
10 Reasons why you shouldn’t remove stop words
Should you automatically remove stop words like ‘the’ from your search query or index? Here are 10 reasons you shouldn’t!
Pete establishes a Baseline Relevance Metric
On his continuing quest to build superior e-commerce search, Pete the Product Owner establishes a baseline relevance metric
Approaches to field boost tuning with Learning to Rank
A guest post from the Metarank team write on field boosts, Learning to Boost and Learning to Rank
Applying Vector Search in E-Commerce
How we built a prototype vector search application for e-commerce using Jina AI at the Vector Search Hackday
What is vector search? A guide to the new frontier
Vector search & neural search – what exactly are these new techniques, what can they do and what do you need to consider when implementing them?
How to succeed with explicit relevance evaluation using Probability-Proportional-to-Size sampling
How to use PPTS sampling to choose queries to reflect the actual needs of your users when carrying out explicit relevance evaluation.