Oops, I did it Again…In my previous article, I tried to set up Quepid for evaluating vector search and miserably failed. I tried harder, and now, the second…Feb 1Feb 1
Why Setting Up Quepid for Vector Search Evaluation Went WrongThere are many ways to perform vector search in Elasticsearch. Some methods, such as handling vectorization in the ingestion pipeline, can…Dec 30, 2024Dec 30, 2024
A step-by-step introduction to running your app in Kubernetes.I have been working in the software engineering industry for more than two decades. In this series of blog posts, I will try to do my best…Nov 21, 2024Nov 21, 2024
Dissecting the Process of Running Hugginface models Locally (including LLMs)Introduction to the problemOct 4, 2024Oct 4, 2024
To upscale, or not to upscale, that is the question…So, our data has outgrown the memory capacity of our Qdrant cluster. Do we have options besides increasing the bill?Jul 10, 2024Jul 10, 2024
How large is large? How small is small?In my previous article, I explored how to train a multiclass classifier using OpenAI embeddings as features. The focus was on…Jun 1, 2024Jun 1, 2024
Who the hell put this product here?Let’s dive deeper into the fascinating world of the Amazon ESCI dataset. This round, we’ll try to build a classifier that accurately…Apr 12, 2024Apr 12, 2024
How to slugify two quick brown foxes using ElasticseachSo, in one of my projects, from any human-readable string, I have to create its representation according to the URL slug rules.Dec 11, 2023Dec 11, 2023