News guides for WordPress & WooCommerce

Introduction In the world of content management systems, WordPress stands tall as one of the most popular platforms for website creation and management. However, its default search functionality has often left users wanting more. To address this, Jetpack Search, a powerful search plugin developed by Automattic, the creators of WordPress, has emerged as a solution to enhance the search experience for WordPress websites. In this article, we will explore how Jetpack Search improves upon the default WordPress search, delve into its technical details, examine some notable websites using the plugin, highlight its ten best features, discuss ten missing features, and touch upon any potential performance issues.   How Jetpack Search Helps Compared to the Default WordPress Search Jetpack Search provides several key advantages over the

Introduction WP Custom Fields Search is a powerful search plugin designed to enhance the default search functionality in WordPress. With its advanced features and capabilities, this plugin offers a significant improvement over the standard search capabilities provided by WordPress. In this article, we will explore how WP Custom Fields Search helps in comparison to the default WordPress search, delve into its technical details, examine some notable websites utilizing this plugin, highlight its ten best features, identify ten missing features, and discuss any potential performance issues.   How WP Custom Fields Search improves upon the default WordPress search The default search feature in WordPress is limited to searching through post titles and content. However, WP Custom Fields Search expands this functionality by allowing users to search

Introduction WP Search with Algolia is a powerful plugin that enhances the search functionality of WordPress websites. Built on Algolia’s advanced search technology, this plugin offers a range of benefits over the default WordPress search. In this article, we will explore how WP Search with Algolia improves the search experience, delve into its technical details, provide examples of websites using the plugin, and highlight its best features, missing features, and performance considerations.   How WP Search with Algolia Helps Compared to the Default WordPress Search WP Search with Algolia provides several advantages over the default search functionality offered by WordPress. Firstly, it delivers highly relevant search results with lightning-fast speed, ensuring that visitors can quickly find the information they seek. The plugin leverages Algolia’s robust

Introduction The search functionality is a crucial aspect of any website, allowing visitors to quickly find the information they are looking for. While WordPress offers a default search feature, it may not always deliver the desired results. This is where the ACF: Better Search plugin comes in, providing enhanced search capabilities and improving the overall search experience for WordPress users. In this article, we will explore how ACF: Better Search surpasses the default WordPress search, delve into its technical details, examine notable websites using the plugin, highlight its top features, identify some missing features, and discuss any performance issues.   How ACF: Better Search Enhances Default WordPress Search ACF: Better Search significantly improves upon the default WordPress search functionality in several ways. Firstly, it integrates

Introduction Advanced Woo Search is a powerful search plugin designed specifically for WooCommerce websites, offering enhanced search functionality compared to the default search feature provided by WooCommerce. With advanced indexing and Natural Language Processing (NLP) capabilities, this plugin aims to improve the search experience for both website administrators and customers. In this article, we will explore how Advanced Woo Search surpasses the default WooCommerce search, delve into its technical details, highlight some websites using the plugin, examine its best features, identify missing features, and discuss any potential performance issues.   How Advanced Woo Search Helps Compared to Default WooCommerce Search Advanced Woo Search outshines the default WooCommerce search in several ways. Firstly, it provides a faster and more accurate search experience by leveraging advanced indexing

Introduction FiboSearch is a powerful search plugin that enhances the default search functionality of WordPress websites. With its advanced indexing and natural language processing (NLP) capabilities, FiboSearch offers numerous benefits over the default WordPress search. In this article, we will explore how FiboSearch improves search functionality, delve into its technical details, discuss some websites that are successfully using the plugin, highlight its top 10 features, identify 10 missing features, and address any performance issues.   How FiboSearch Helps Compared to the Default WordPress Search FiboSearch surpasses the default WordPress search in several ways. Firstly, it provides more accurate and relevant search results by leveraging advanced algorithms and NLP techniques. The plugin understands user intent and context, enabling it to deliver precise search results even for

Introduction In today’s digital landscape, an efficient and accurate search function is essential for any website. WordPress, being one of the most popular content management systems, provides a default search feature. However, it often falls short in delivering precise results, leaving users frustrated and businesses struggling to meet their audience’s needs. This is where the “Better Search” search plugin comes in. Designed to enhance the search experience on WordPress websites, Better Search offers advanced features, superior indexing capabilities, and powerful natural language processing (NLP) techniques to revolutionize the way users find information.   How “Better Search” Enhances WordPress Search Compared to the default WordPress search, “Better Search” offers several notable advantages. Firstly, it provides more accurate search results, allowing users to find the content they’re

Introduction Search functionality is a crucial aspect of any website, enabling users to find the information they need quickly and efficiently. WordPress, being one of the most popular content management systems, comes with a default search feature. However, it often falls short in providing accurate and relevant results. This is where SearchIQ, a powerful search plugin, comes into play. SearchIQ offers advanced features, superior indexing capabilities, and natural language processing (NLP) capabilities to enhance the search experience on WordPress websites. In this article, we will delve into the benefits of using SearchIQ over the default WordPress search, explore its technical details, highlight websites that utilize this plugin, and discuss its best features, missing features, and any potential performance issues.   How SearchIQ Helps Compared to

Introduction Search functionality is an essential aspect of any website, and WordPress, being one of the most popular content management systems, offers a default search feature. However, the default WordPress search may not always provide the desired results or have advanced capabilities. This is where the Search & Filter search plugin comes into play. Search & Filter is a powerful WordPress plugin that enhances the search functionality, providing users with more control and flexibility over their searches. In this article, we will explore how Search & Filter improves upon the default WordPress search, delve into its technical details, examine some websites that use the plugin, and discuss its best features, missing features, and potential performance issues.   How Search & Filter Helps Compared to the

Introduction The search functionality is a critical component of any website, enabling users to find relevant information quickly and efficiently. While WordPress provides a default search feature, it may not always meet the specific needs of every website. That’s where the Ajax Search Lite plugin comes into play. Ajax Search Lite is a powerful search plugin for WordPress that offers enhanced functionality and customization options, improving the search experience for both website owners and visitors. In this article, we will explore how Ajax Search Lite compares to the default WordPress search, delve into its technical details, examine some notable websites that use this plugin, highlight its best features, identify missing features, and discuss any potential performance issues.   Ajax Search Lite vs. Default WordPress Search

Introduction Search functionality is a critical component of any website, as it directly impacts the user experience and the ability to find relevant content. WordPress, being one of the most popular content management systems, offers a default search feature. However, it often falls short in terms of accuracy and customization. This is where SearchWP, a powerful search plugin for WordPress, comes into play. In this article, we will explore how SearchWP improves upon the default WordPress search, delve into its technical details, examine notable websites using this plugin, highlight its top features, identify any missing features, and discuss its performance issues.   How SearchWP Helps Compared to the Default WordPress Search SearchWP enhances the search functionality of WordPress by providing a range of advanced features.

Introduction FacetWP is a powerful search plugin for WordPress that enhances the default search functionality and provides advanced filtering options for users. By integrating FacetWP into their websites, WordPress users can greatly improve the search experience for their visitors. In this article, we will explore how FacetWP compares to the default WordPress search, delve into the technical details of the plugin, discuss some websites that utilize FacetWP, and highlight its best features, missing features, and potential performance issues.   FacetWP versus Default WordPress Search Compared to the default WordPress search, FacetWP offers several advantages. The default search in WordPress relies primarily on keyword matching, which can often lead to inaccurate or irrelevant results. FacetWP, on the other hand, incorporates advanced filtering options that allow users

Introduction In recent years, the field of artificial intelligence (AI) has witnessed remarkable advancements, particularly in the realm of search algorithms. AI-powered search has revolutionized the way personalized recommendations are generated and delivered to users. This has had a profound impact on various industries, including e-commerce and online services. In this article, we will explore the significant influence of AI search on personalized recommendations and highlight the features and capabilities of notable platforms such as Google Retail, Recombee, Weaviate, and Algolia. We will also delve into the role of language models, vector search, similarity metrics, and embeddings in enhancing recommendation systems. Moreover, we will discuss how AI has rendered previous personalization tricks obsolete, opening up new possibilities for tailored user experiences.   Personalized Recommendations and

Introduction The field of artificial intelligence (AI) has undergone remarkable advancements over the years, particularly in the domain of search algorithms. From the early days of simple algorithms to the advent of deep learning, the evolution of AI search has revolutionized the way we discover and access information. In this article, we will explore this fascinating journey, highlighting key milestones and breakthrough technologies that have shaped the landscape of AI search. Specifically, we will delve into the contributions of Weaviate, Pinecone, Vespa, Elasticsearch, and Solr, each of which has played a significant role in advancing the capabilities of AI search.   The Emergence of Simple Algorithms In the early stages of AI search, simple algorithms were developed to enable basic keyword-based queries and matching. These

Introduction A vector database is a type of database that is specifically designed to store and retrieve high-dimensional vectors efficiently. Vectors are mathematical representations of objects or data points that capture their characteristics or features. In a vector database, these vectors are stored and indexed in a way that enables fast similarity searches and efficient retrieval of similar vectors.   Technical Details Vector databases typically employ advanced data structures and algorithms to efficiently handle high-dimensional vectors. Some common techniques used in vector databases include: 1. Vector Indexing: Vector indexing is a key component of vector databases. It involves creating an index structure that organizes the vectors in a way that enables efficient retrieval based on similarity. Various indexing methods, such as tree-based structures (e.g., k-d

Introduction A recommender system is an algorithmic technique used by various websites and applications to suggest relevant items or content to users based on their preferences and behavior. It analyzes user data, such as browsing history, purchase history, and explicit ratings, to generate personalized recommendations. Recommender systems play a crucial role in enhancing user experience, increasing user engagement, and driving sales for e-commerce platforms. In this post, we will explore the technical aspects of recommender systems, their usage on well-known websites, and provide code examples using popular technologies like WordPress, Elasticsearch, Solr, Weaviate, and Algolia. We will also discuss techniques like vector search and language models to improve performance and accuracy, along with potential performance issues. Technical Details of Recommender Systems Recommender systems typically utilize

Introduction Full-text search is a powerful technique used in information retrieval systems to efficiently search and retrieve relevant documents based on the presence of specific words or phrases. It enables users to search through large volumes of textual data and obtain accurate and comprehensive results. In this response, we will explore the technical aspects of full-text search, its applications on well-known websites, provide code examples for implementing it with different technologies, discuss techniques for improving performance and accuracy, and address the challenges that arise with increasing data, SQL joins, disk issues, and RM issues. Additionally, we will touch upon the difference between full-text search and AI search, highlighting the role of AI technologies such as Weaviate, LLMs, BERT, transformers, and HuggingFace.   Technical Details of

Introduction Weaviate is an open-source, cloud-native, and vector-based knowledge graph that empowers developers to build intelligent applications with natural language processing (NLP) capabilities. It utilizes machine learning algorithms to organize and connect data, enabling powerful semantic searches and contextual recommendations. In this article, we will explore ten prominent features of Weaviate that contribute to its effectiveness as a knowledge graph platform.   Feature Description Vector-Based Representation Utilizes vector-based embeddings to capture context and semantics of data entities. Automatic Schema Inference Automatically generates data structure definitions based on the provided data. Contextual and Semantic Search Enables powerful searches by interpreting natural language queries and providing relevant results. Real-Time Data Updates Supports real-time updates, keeping the knowledge graph up-to-date with the latest changes. GraphQL API Provides a

Introduction In the digital age, search engines have become an integral part of our daily lives, helping us find information quickly and efficiently. While keyword searches have been the traditional method of searching for information, advancements in artificial intelligence (AI) have introduced a new approach to search. In this article, we will explore the key differences between a keyword search and an AI search.   Comparison Keyword Search AI Search Input Method Specific words or phrases Natural language, voice commands, images, etc. Understanding Context Relies on exact keyword matches Considers context and meaning behind the query Results Relevance Based on keyword presence Provides more accurate and personalized results Natural Language Processing Does not typically involve NLP Utilizes NLP techniques to understand queries Contextual Understanding Lacks

Introduction WordPress search plugins are essential tools for improving the search functionality of your WordPress website. These plugins offer advanced features and customization options to enhance the default search engine, enabling visitors to find content more efficiently. With a wide range of WordPress search plugins available, it can be overwhelming to choose the right one for your specific needs. In this article, we will explore 10 well-known WordPress search plugins and compare their key features. Each plugin has its own unique set of capabilities, ranging from live search functionality and customizable search forms to support for custom post types, taxonomies, and advanced search filters. By understanding the features offered by these plugins, you can make an informed decision and select the one that aligns with

Introduction to AI Search Artificial Intelligence (AI) search refers to the process of finding relevant information or patterns within a dataset to answer queries or provide recommendations. It is a fundamental technology that drives various applications, including search engines, recommendation systems, and information retrieval. By leveraging advanced algorithms and models, AI search enables efficient and accurate exploration of large datasets to deliver valuable insights. In this article, we will explore the technologies that underpin AI search and their applications. Embeddings, Vector Search, and Vector Space One of the key components of AI search is the use of embeddings. Embeddings are numerical representations of objects or concepts that capture their semantic meaning and relationships. In the context of AI search, embeddings play a crucial role in

Introduction Effective search functionality is a critical component of any successful e-commerce platform, and WooCommerce understands the significance of providing a robust search experience to both customers and businesses. In a vast online marketplace, where countless products are available, the ability to quickly and accurately find desired items is indispensable. WooCommerce search offers a range of essential features that enhance the user experience, improve conversion rates, and empower businesses to optimize their product catalog. These features not only make the search process more convenient for customers but also enable businesses to gain valuable insights into user behaviour and tailor their offerings accordingly. Let’s explore why these ten features of WooCommerce search are indispensable for a thriving online store.   The 10 indispensable features for an

In today’s digital era, e-commerce has become an indispensable part of our lives. With the advent of platforms like WooCommerce, businesses have been able to set up online shops quickly and efficiently. However, the success of an online store heavily relies on the ability to deliver a seamless user experience, and one crucial element in achieving this is the search functionality. By integrating AI search services and leveraging the wide range of APIs and plugins available, WooCommerce shops can provide customers with intelligent and personalized search results, leading to increased customer satisfaction, conversion rates, and ultimately, business growth. In this article, we will explore the benefits of using AI search for WooCommerce shops and discuss some of the prominent AI search services, APIs, and plugins

Mostly about fixes, and still including 5 open-source search engines: Weaviate, #Elasticsearch, OpenSearch Project, The Apache Software Foundation #Solr, The Apache Software Foundation #SolrCloud A unique opportunity to test AI search on your data. Just download the plugin, install locally Weaviate, and enjoy: https://lnkd.in/dFueA7QY #wordpress #plugin #free #elasticsearch #opensearch #apachesolr #weaviate #wpsolr

Evaluating LLMs with benchmarks will be over very soon. Here is why: 1. Benchmarks are based on human knowledge 2. Benchmarks are difficult to collect and biased 3. LLMs are already close to 100% scores on benchmarks like SAT and Bar From the 3 points above, it is clear that we will run out of benchmarks soon. And in a short while, we will run out of human referees also, as LLMs will do things that are beyond human measure. The example of a ELO system described by David Hershey looks promising. LLMs competing again each other, in their own non-human league, like Chess bots competitions. Chess is a good example. Nowadays, top human players cannot explain most bot evaluations of a position. Same for Go play.

After years of nothingness, and a first timid ANN search, here comes the great announcement everyone was expecting. Thanks to ESRE, short for “Elasticsearch Relevance Engine”, the first real full-fledge offer around LLMs. Note that Elasticsearch already provided a vector search. But without dedicated embedding management, this just deported the work to good old Python code. Now, what looks great about ESRE? 1. Import and configure Hugging Face transformers inside Kibana It can be done from a local docker instance, or from a Colab 2. Build embeddings from the ingestion API 3. Search with ANN on embeddings 4. Hybrid ranking with RFF 5. APIs to manage all those steps You will need the Elastic Platinum plan to be able to activate ML nodes. Question: WPSOLR already integrates Elasticsearch

Some background: – Self-hosted Weaviate on a Google Cloud Kubernetes cluster – 2 replicas – 1 namespace co-hosting 5 demos (OpenAI, Cohere, Hybrid, CLIP, PaLM) – Weaviate v1.19.5 – WooCommerce with 2 thousand products – Faceting, pagination, sort, suggestions The PaLM demo The PaLM documentation All demos #wpsolr #weaviate #palmapi #woocommerce

1 – Recommenders already use vectors of products and users to improve predictions with few events. 2 – Vector databases already deliver predictions with similarity matching. 3 – An example is Algolia‘s new NeuralSearch. Here are two extracts from their NeuralSearch documentation: – “NeuralSearch combines the precision of keyword search with the deep understanding of natural language and contextual relevance provided by AI-based vector search. ” Algolia NeuralSearch is indeed a vector search and vector database. – “You need to collect at least 1,000 clickedObjectIDsAfterSearch or 100 convertedObjectIDsAfterSearch events within 30 days to activate NeuralSearch. If you have fewer events, you can’t use NeuralSearch.” Algolia NeuralSearch is also a recommender system, feeding on user events. But you cannot use Algolia NeuralSearch as a pure vector search, nor as a pure recommender. This is

We’ve started the integration of WPSOLR and Weaviate‘s new PaLM vectorizer Stay tuned for a few more days …. 🙂 WPSOLR + Weaviate + WooCommerce: https://wpsolr.com #wpsolr #weaviate #llm #palmllm #woocommerce

Finally! I was wondering how long before Google provides a LLM embeddings API ? Already integrated to Weaviate with Google PALM, and soon to WooCommerce  with WPSOLR:) WPSOLR + Weaviate + WooCommerce: https://wpsolr.com  

Vespa’s 2-phase state ranking can now be followed by a (stateless/autoscaling/GPU) global reranking from cross-encoder models

This is why closed LLMs developed so fast. There are not so many inference and even less training hosting providers for OSS LLMs. And even less with a full Pay-as you-Go billing. For instance, Hugging Face endpoints are currently billed per model per VM. One has to configure a VM, choose a model, then pay by the usage. This is great, but to try or switch off temporarily a model, you must configure a new endpoint. Interested in WooCommerce vector search? https://wpsolr.com #wpsolr #woocommerce #vectorsearch #weaviate #huggingface

But while vector search is, while embeddings are, sometimes the full integration is not … Let’s face it, most e-commerce demos start with some notebook python code to: – Load data – Tweak some parameters, like vocabulary size and tokenizer types – Download and call embedding models – Store vectors in the vector database After that, you’ll have to build the code to replace your actual E-Commerce SQL search with the vector search. But how to: – Build facets and filters ? – Index your data in real-time, as soon as your data is updated ? – Re-index all your data in batches, from time to time ? – Monitor your conversion rates ? – Compare search results from several search engines ? – Display

Until recently, you needed to be a data scientist and a python developer mastering tens of libraries. It is now easier with Hugging Face pipelines, or systems like Weaviate that completely hide the models. But the real problem is now money. You can find a Solr/Elasticsearch hosting service for €20/month. For a WooCommerce client, self-hosting his small cluster on K8s was €100/month + the embeddings API costs. WPSOLR + WooCommerce + AI search: https://www.wpsolr.com

— Typo corrected results — If you’re using vector search, you already get some form of spell tolerance. You will enjoy results even with a query written phonetically. (If you’re not using vector search, well, you should!) — Generic typo corrected query — But sometimes, you’d rater let the user choose his preferred typo correction inside a list, before starting the search. This is really easy nowadays. Here are the manual steps: – Open your GPT3.5/GPT4/ChatGPT sandbox – Prompt the AI with a proper sentence to fix your query. Something like: Fix the typo on the following query: A: plise fixe the tippo Answers: A: Please fix the typo That’s it. But of course, you want to automate corrections in your search, and it remains

— Pure vector search is amazing — After settling my first WooCommerce demos with Weaviate, I was shocked how good the results were. And with absolutely no tuning! Just a few elements of the vector search: – Misspelling is literally not a subject anymore It’s even quite impossible to fool the search, as it understands phonetic-like queries. And it could even be improved by asking a generative LLM like T5 or GPT pre-processing step to fix the query spelling or grammar. – Multi-language is almost not a subject anymore Who did not dream of selling to worldwide customers without translating in a hundred languages? – Usually hidden products can be found with semantic “Something to sleep on” returns mattresses 🙂 — Hybrid search: a step backwards? — I

– Chapter 1: embeddings – After years of exploiting the last layer of ML models, somebody discovered with BERT that the gem was in fact the before last layer, which we now call embeddings. Because embeddings could encapsulate semantic, indeed. – Chapter 2: vector databases from vector metrics – But, even deeper, because embeddings are vectors, and vector spaces bring vector metrics. With vector metrics you can compare, and therefore cluster, things that are not comparable else. How to compare 2 sentences, 2 images, a sentence to an image… And so, vector databases were born to store vectors and use vector metrics to find related vectors and concepts. – Chapter 3: embed embeddings – It remains difficult to build the embeddings, despite the rise of

Weaviate was probably the first to understand that fact, by delivering no-code vectorizer modules inside the database. Vespa too, but with more manual steps (download the model, convert to ONNX). Suddenly, anyone a bit technical (but not a data scientist) could index its raw data without worrying too much about the cogs behind the scene. Vector database + custom python code vectorizer => hard-core toolbox to build POC Vector database + integrated vectorizer => mainstream toolbox to go to prod More on WooCommerce + Weaviate : https://www.wpsolr.com

– Vegetable & fruits shop with Weaviate + Cohere. Content in Hebrew, visitors query (no translation, no stemming, no N-Grams, no synonyms, no nothing) in 5 languages. Suggestions and faceted search. https://freshuk.co.il/ – WooCommerce demo with Weaviate & hybrid search https://lnkd.in/d4YxuVhF – WooCommerce demo with Weaviate & Cohere search https://lnkd.in/dy_wcPYA – WooCommerce demo with Weaviate & CLIP text-to-image search https://lnkd.in/diUn-8Mm – WooCommerce demo with Weaviate & OpenAI https://lnkd.in/dBzeqUxC More on Weaviate + WooCommerce: https://www.wpsolr.com #weaviate #wpsolr WooCommerce

(Following Part 4) The coding of query filters and query aggregations (facets) for Vespa is now complete. One can define facets and filters with advanced facet layouts, from the WPSOLR admin. Some details below: – Vespa provides YQL, a SQL-like language, to build queries with filters and aggregations. It’s very simple to use for most developers who are already familiar with SQL. – Vespa does not provide a YQL syntax for filter exclusions yet. Filter exclusion is very important for e-Commerce, as it enable to show facet contents eliminated by the current facet selection. To overcome this issue, WPSOLR will call several aggregation queries in parallel https://lnkd.in/dvhAKJpZ. We did the same trick for Weaviate 🙂 All facet layouts are available to Vespa queries: – check boxes – radio

(Following Part 3) The coding of document indexing operations for Vespa is now complete. One can create a new document, update a document, and delete a document, from the WPSOLR admin. Some details below: – Vespa does not use server-side batching documents. WPSOLR will implement it client-side with asynchronous http/2 calls as recommended by Vespa https://lnkd.in/d8SYeA7p. – Vespa does not use dynamic field names, which would enable to index and search documents with fields not pre-defined in the schema.sd To overcome this issue, WPSOLR detect missing fields’ error sent by Vespa to update and redeploy the schema accordingly. This is important because some document fields like ‘_price’ may(not) be added by optional WPSOLR add-ons like WooCommerce – Vespa provides a documents deletion from query (named ‘selection’), which

(Following Part 2) The coding of index CRUD operations for Vespa is now complete. One can create a new index, update an index, and remove an index, from the WPSOLR admin. It was quite interesting: – Check that the application is deployed already. If not, deploy its zip – Create the new index’s schema file with a modified services.xml ( add the document element to the content’s documents elements of the downloaded services.xml) – Remove the deleted index’s schema file, but also remove the document element to the content’s documents elements of the downloaded services.xml. Also add a temporary validation-overrides.xml to authorise the schema removal. – Prepare and activate within a new session to deploy the new/updated/deleted application/schema WPSOLR: https://www.wpsolr.com #vespa #wpsolr #aisearch #vectorsearch #woocommerce #wordpress

https://aiquarious.com/ #vectorsearch #promptengineering #finetuning #largelanguagemodels

(Following Part 1) A major prerequisite of WPSOLR is to modify an index schema automatically when a user adds/update fields from the plugin admin screens. But when the Vespa application package is already created, how to redeploy the schema without overriding other files (hosts.xml, services.xml, models, …)? Thanks to Github discussion https://lnkd.in/dT-Yj95C, we now have a solution and can start coding! WPSOLR: https://www.wpsolr.com #vespa #wpsolr #aisearch #vectorsearch #woocommerce #wordpress

How to map your WooCommerce search to a Vespa architecture? Vespa is a highly modular big data engine, with many concepts: tenant, application package, zone, instance, deployment, service, schema. And many more. A first investigation of the documentation leads us to map WPSOLR search indices to application packages’ schemas. Here is the reasoning: 1. Vespa Cloud’s tenant can be used to model a project (customer, site, …) 2. Each tenant can host several application packages 3. Each application package can host several schemas 4. WPSOLR will automatically deploy a default application package, with a root schema and a child schema. 5. The virtual root schema contains all predefined field settings, but no data. It can only be modified by WPSOLR. 6. The child schema will inherit

After training LLMs on the whole world, prompting them for zero-shot, finetuning them on specialized domains, what is the next stage? The goal is clear: adapting models further and further. I can see two competitors there: website finetuning and recommenders. – Recommenders – Recommenders are basically finetuned on users. They already use embeddings, are effective, and do not need labeling thanks to user events. But privacy is a problem. – Website finetuning – On the other hand, Website finetuning is performed on the site content, especially vocabulary. But labeling is a problem. We can use LLMs to generate labels (questions), but is it not a chiken/eggs loop?