diff --git a/content/images/solr/LLMs-in-search.jpg b/content/images/solr/LLMs-in-search.jpg new file mode 100644 index 000000000..bb696ea07 Binary files /dev/null and b/content/images/solr/LLMs-in-search.jpg differ diff --git a/content/pages/resources.md b/content/pages/resources.md index e78649594..09d0e1a65 100644 --- a/content/pages/resources.md +++ b/content/pages/resources.md @@ -58,7 +58,25 @@ If you want to run Solr on Kubernetes, the easiest way to get started is via ins If you have a Solr book that you would like to see listed here, please [edit this website and submit a Pull Request](/editing-website.html). -
[Alessandro Benedetti](https://www.linkedin.com/in/alexbenedetti/) and [Sease](https://www.sease.io) are proud to introduce the book, "[How Large Language Models Can Help Your Search Project](https://link.springer.com/book/10.1007/978-3-032-01563-1)".
+The primary scope of this book is to communicate the current state of the art of large language model applications in the domain of information retrieval and search with a pragmatic perspective on industrial adoption via open source software.
+
+To this end, the book is organised in three parts: “Large Language Models” gives an introduction to artificial intelligence and large language models, including an overview of open source and commercial options. Next, “Large Language Models and Search” describes techniques and strategies to integrate large language models in search projects, including how to choose the right model for a specific use case and how to avoid the classic mistakes that can happen in the process. Eventually, “How to Use Open Source Software to Interact with Large Language Models” gives an overview of open source technologies to interact with large language models and gives a detailed survey of how the most popular open source search engines support them.
+
+The book lays the foundations, deeply analyses the building blocks and shows examples how to implement the ideas described. It highlights both the positives, negatives and possible mitigations of the limitations. This way, it caters primarily software engineers, data scientists and practitioners in artificial intelligence or information retrieval who are curious to learn about the latest trends, research and industrial applications related to search and large language models.
+
+The book has a chapter dedicated to Apache Solr, exploring the ways you can interact with Large Language Models related features, specifically:
+
+- dense vector search, quantisation and nested vectors
+- text vectorisation using LLM fine tuned for sentence similarity
+- Intro to Future features such as Retrieval augmented generation, Semantic highlighting and LLM query parser
+
+[Buy Here](https://link.springer.com/book/10.1007/978-3-032-01563-1)
+
+***
+
[Rauf Aliev](https://www.linkedin.com/in/raufaliev/) is proud to announce his book, "[Inside Apache Solr and Lucene: Algorithms and Engineering Deep Dive](https://testmysearch.com/books/inside-solr.html)". This book dives deep into the core of Apache Solr and Lucene, offering answers from a system engineer's perspective. It explores the architectural decisions, data structures, and algorithms that enable these world-class search platforms to deliver exceptional performance and scalability, providing a blueprint for designing high-performance systems.
@@ -70,7 +88,7 @@ The insights in this book extend beyond the Solr and Lucene ecosystem. By using
***
-
Markus Klose, Daniel Wrigley and O’Reilly are proud to present the first book on Apache Solr in German.
@@ -174,7 +192,7 @@ Trey Grainger, Timothy Potter, and Manning Publications are proud to announce [S *** -
Alexandre Rafalovitch and Packt Publishing are proud to announce [Instant Apache Solr for Indexing Data How-to](https://www.amazon.com/Instant-Apache-Solr-Indexing-Data/dp/1782164847) - an example-driven guide that will take you on a journey from the basic collection of data to a multi-lingual, multi-field, multi-type schema.
@@ -185,7 +203,7 @@ Content and data searching is a very important part of the modern user experienc
***
-
Rafał Kuć and Packt Publishing are proud to announce the second edition of [Apache Solr 4 Cookbook](http://www.packtpub.com/apache-solr-4-cookbook/book). The Cookbook is newly updated and improved with new chapters on SolrCloud and every chapter updated to Solr 4.
@@ -200,7 +218,7 @@ With numerous practical chapters centered on important Solr techniques and metho
***
-
Taming Text is a hands-on, example-driven guide to working with unstructured text in the context of real-world applications. This book explores how to automatically organize text using approaches such as full-text search with Apache Solr (v3), proper name recognition,
@@ -211,7 +229,7 @@ is available on [Github](https://github.com/tamingtext/book).
***
-
Rafał Kuć is proud to introduce a new book on Solr, [Apache Solr 3.1 Cookbook](http://www.packtpub.com/solr-3-1-enterprise-search-server-cookbook/book) from Packt Publishing.
@@ -250,6 +268,8 @@ If you have a Solr video that you would like to see listed here, please [edit th
[Videos from Lucidwork's Lucene Eurocon](https://vimeo.com/search?q=lucene%20eurocon)
+[Videos from past London Information Retrieval & AI Meetups](https://www.youtube.com/playlist?list=PL3MGdCOBPhsccrQRGrUjQlzRSdlWrcF9N)
+