In his article, “Databases in 2024: A Year in Review,” Andy Pavlo provides a comprehensive analysis of the state of databases in the past year, offering a reflection on the triumphs, struggles, and significant trends that have shaped the industry. The database market, always one of intense competition, faced a wave of major licensing changes, corporate acquisitions, and shifts in strategic direction. Andy’s annual roundup covers the most significant moments, from licensing wars to massive acquisitions, and highlights the fierce competition between some of the most prominent players in the da ..read more

As 2024 comes to a close, the world of AI and vector technologies stands on the brink of transformational change. What emerging trends will shape the landscape in 2025? From agentic AI systems to the growing importance of unstructured data, the next year promises significant advancements—and challenges—for businesses leveraging these technologies. In this post, I’ve summarized key predictions from industry thought leaders and added my take on what it means for vector technologies, databases, and AI. Let’s dive into the trends to watch in 2025. Josh Howard (Databricks Blog): Strategic Prior ..read more

Welcome to “Vector Vanguard: Tracking the Pulse of Vector Tech 11/2024” – a source for the latest developments in vector databases, vector indexes, RAG (Retrieval-Augmented Generation), similarity search, and related technologies that caught my attention in the last month. Exploring LLMs and RAG: A Comparison of Approaches I gave talks on vector databases during DOAG 2024 and KI-Navigator 2024 conferences. The architecture below is taken from my slide decks. Using LLM Without RAG Large Language Models (LLMs) are powerful tools capable of generating coherent and contextually relevant response ..read more

Welcome to “Vector Vanguard: Tracking the Pulse of Vector Tech 10/2024” – a source for the latest developments in vector databases, vector indexes, RAG (Retrieval-Augmented Generation), similarity search, and related technologies that caught my attention in the last month. Featured Vector Tech Topic: Advanced RAG techniques Guillaume Laforge summarises in his blog post a session and a workshop that he and Cédrick Lunven gave during Devoxx Belgium 2024. In the workshop, Guillaume and Cédrick explored how to overcome these pitfalls by adopting advanced techniques, drawing insights from the lat ..read more

“Humanizing Data Strategy: Leading Data with the Head and the Heart” by Tiankai Feng focuses on a people-centered approach to data strategy. The book introduces the Five Cs Framework, which highlights five key areas of focus: Competence, Collaboration, Communication, Creativity, and Conscience. Feng defines data strategy as: “a long-term plan that defines the people, processes, and technologies to create, process, and use data to intentionally drive value in a meaningful, secure, and transparent way.” While people, processes, and technologies are all critical to data strategies, this book em ..read more

Welcome to “Vector Vanguard: Tracking the Pulse of Vector Tech 09/2024” – a source for the latest developments in vector databases, vector indexes, RAG (Retrieval-Augmented Generation), similarity search, and related technologies that caught my attention in the last month. Featured Vector Tech Topic: Hybrid search with PostgreSQL and pgvector Jonathan Katz writes about Hybrid search as delivering precise and relevant search results is crucial for enhancing user experience. Traditional keyword-based searches often fall short in understanding the context or semantic meaning behind queries. This ..read more

Welcome to “Vector Vanguard: Tracking the Pulse of Vector Tech 08/2024” – a source for the latest developments in vector databases, vector indexes, RAG (Retrieval-Augmented Generation), similarity search, and related technologies that caught my attention in the last month. Featured Vector Tech Topic: Long Context RAG Performance of LLMs In the Databricks blog on “Long Context RAG Performance of LLMs,” the discussion centers around the effectiveness of Retrieval Augmented Generation (RAG) when paired with long-context large language models (LLMs). As LLMs like GPT-4, Claude, and Gemini extend ..read more

With the advent of Large Language Models (LLM), vector databases are becoming increasingly popular. Vector databases and similar approaches have existed for a long time such as geodata have long been established. Oracle offers since Oracle Database 23ai vector functionalities and further enriches the concept of a converged database. This article looks at similarity search and indexing for Oracle AI Vector. For an itroduction into vector databases and basic concepts see my article https://buckenhofer.com/2024/05/vector-database-what-why-and-how/. Oracle AI Vector – installation and first st ..read more

Vector indexes are crucial for semantic search performance, optimizing efficient querying. In this article, I will delve into various types of vector indexes, their workings, pros and cons, and recommendations for their use. The article also provides a practical example using PostgreSQL’s pgvector extension, demonstrating the use of indexes such as IVF and HNSW, including the difference between exact and approximate nearest neighbor (aKNN) searches. Optimizing Performance in Vector Searches Optimizing performance in vector searches can be achieved through two primary strategies: Reducing ..read more

Similarity search in vector databases has emerged as a pivotal technique enabling efficient retrieval of information by comparing complex data points within high-dimensional spaces. The ability to find similar items efficiently is crucial for applications ranging from RAG pipelines, search engines, recommendation systems, etc. In this blog post, I’ll dive into what similarity search means, explore different algorithms used, and explain each including strengths, weaknesses, and recommendations for when to use each algorithm. I’ll provide examples using pg_vector, a PostgreSQL extension for ha ..read more