New Quepid Features
New Quepid features include improved user interfaces, APIs and the ability to work with any search backend, plus new metrics including Jaccard similarity
New Quepid features include improved user interfaces, APIs and the ability to work with any search backend, plus new metrics including Jaccard similarity
How do you manage access control & data quality when building AI-powered enterprise search? A reality check
The challenges with compound nouns in search, how to successfully tackle them with decompounding using Query Rewriting and the role of LLMs.
Continuous experimentation as part of your CI/CD pipeline can drive continuous improvement of search quality
How we worked with AI-based search and retrieval augmented generation platform Vectara to evaluate and measure their engine – and added it to Quepid!
Enterprises and others building AI face some difficult choices – but there are already many with skills and experience to help!
How can generative AI help your customers find the right product by extracting information from reviews?
Meta have released their new Llama 2 large language model to great fanfare – but it’s not open source as they say. Why does this matter?
Berlin Buzzwords 2023 featured talks on search with AI, scaling, MLOps, vectorizing your search engine and which search engine to use
Human ratings for relevance tuning are resource-intensive to generate – so could we use a large language model like GPT instead?
A step-by-step approach to compare the results of two search systems using human ratings & NDCG
Lucene bugs, More Like This, ChatGPT, Elasticsearch, OpenSearch and MongoDB Atlas Search – just some of the things we worked on at our Search Hackday