This was 2024 for me.We are approaching the end of 2024 — a good moment to reflect on a year full of personal milestones and significant developments in the…Dec 26, 2024Dec 26, 2024
Mastering State in Stateless LLMsLarge Language Models (LLMs) operate without inherent memory — they are stateless by design. The only “state” they recognise is your…Dec 12, 2024Dec 12, 2024
Published inTowards DevElastic.ON Amsterdam 2024This week, I attended Elastic.ON in Amsterdam. I still remember the first few Elastic events with just a few people, then going to San…Nov 27, 2024Nov 27, 2024
The Evolution of Creativity: Thriving in the Age of AIIn a world where reaching the end goal is easy, the interest in the journey starts to fade. Creativity, like a journey, derives its…Oct 9, 2024Oct 9, 2024
Build an Agent using Amazon Bedrock.A widespread use of large language models (LLMs) is creating agents. An agent can reason, decide what to do, and use tools to take action…Sep 15, 2024Sep 15, 2024
RAG: splitter chain for proper chunks.RAG, short for Retrieval Augmented Generation, is a popular pattern for working with Large Language Models. In previous blog posts, I…Aug 8, 2024Aug 8, 2024
What? A synonyms API for Elasticsearch?One often (over) used feature of lexical search is synonyms. If something does not work, we add a synonym. When used correctly, synonyms…Jul 11, 2024Jul 11, 2024
RAG optimisation: use an LLM to chunk your text semantically.In a previous blog post, I wrote about providing a suitable context for an LLM to answer questions using your content. The previous post…Jul 7, 20242Jul 7, 20242
Introducing Rag4p GUIYesterday was the first public appearance of my latest project, Rag4p-GUI. This project is a graphical interface for the Rag4p library. The…Jul 4, 2024Jul 4, 2024
Getting the proper context for RAG is choosing your chunking and retrieval strategy.You need a Large Language Model to answer questions about your content using only the content that you provide. This is where RAG or…May 21, 2024May 21, 2024
LLM size does matterLLM is short for Large Language Model. Companies like Google, Meta, OpenAI shout about the size of their models. On one end, models keep…May 1, 2024May 1, 2024
Bringing Lexical search to Python Pandas using SearchArrayI have been working in the search domain for some years now. During those years, I got to know Doug Turnbull. Doug is a writer for Manning…Apr 16, 2024Apr 16, 2024
Set your (search) metrics, and live by them.Search engines are all around us. We have become so used to them that we are not surprised to see strange results when entering a few terms…Mar 26, 2024Mar 26, 2024
DSPy and using Rockset as the RetrieverIn my previous post, I introduced you to DSPy and Weaviate. In this blog post, we take another approach. We use Rockset as the retriever.Mar 24, 2024Mar 24, 2024
DSPy is the missing piece in programming with LLMs.Retrieval Augmented Generation is hot. Multiple frameworks come to life, including the one of myself, Rag4p. You read about my first…Mar 19, 2024Mar 19, 2024
Rag4p is now available on PyPi.You want to create your own Retrieval Augmented Generation system. You want to be in control and not think about everything yourself. You…Mar 11, 2024Mar 11, 2024
Automate customer interaction using OpenAI Assistants.Almost everybody knows what ChatGPT is. At workshops I give, about 90% of the people have used ChatGPT. Most of them know about the…Mar 4, 2024Mar 4, 2024
Launching RAG4j/p — Learning to program a Retrieval Augmented Generation systemFrameworks like LlamaIndex, Langchain and Langchain4j make implementing your Retrieval Augmented Generation easy. The problem with these…Jan 25, 2024Jan 25, 2024
GenAI, It’s Happening NowAI is all around us, and the rise of Generative AI, also known as GenAI, is increasingly being discussed. Numerous articles have been…Jan 17, 2024Jan 17, 2024
Looking back at 2023 — The year of LLMsOpenAI gave the last push to LLMs right before the end of 2022 with ChatGPT. To me, 2023 will always be the year of the LLMs, together…Dec 30, 2023Dec 30, 2023