Kari Marttila's Blog (e.g. cloud and Clojure related articles)
A generative AI pipeline. Introduction In Part 1 , I described how I prepared and ingested historical comments and ground truth documents into Qdrant. In this second part, I focus on the LLM stage: how the system classifies unseen comments, applies expert-level reasoning for complex cases, validates quality, and exports results for SME review. From Ingestion to LLM Workflow After ingestion, the…
Qdrant Console. Introduction This year, I have been working on a new and very interesting generative AI Proof of Concept (POC). The purpose of this POC is to validate that we can use historical data and ground truth documents stored in Qdrant to generate similar structured data for new documents for one of our customer. The customer needs to automate a certain manual comment reviewing process…
VSCode / Calva. Introduction Since version 2.0.543 Calva supports arbitrary many Clojure REPLs of whatever kind. I wanted to test this new Multi-REPL Calva functionality in a minimal setup, so I created this minimal Calva multi-repl demo. I did this demo for myself to experiment with the new Calva multi-repl functionality, but if some other developer finds this setup useful, I thought I might…
Web app exercise implemented using Replicant, Nexus and Datascript. The right upper panel is showing Dataspex tool with Datascript database datoms. Introduction In my previous blog post Frontend Development with Clojurescript and Replicant I wrote about implementing a UI using the Replicant UI rendering library. In that previous exercise I built a custom dispatch system and used a Clojure Atom as…
A typical AWS Bedrock Agent architecture. Introduction In my previous Bedrock article Generative AI with AWS Bedrock - First Impressions I told my first experiences about working with AWS Bedrock service when creating a Retrieval Augmented Generation (RAG) chatbot. This year, I had a chance to work with a new AWS Bedrock related project. We are building infrastructure and applications that use AWS…
A typical AWS Batch architecture. Introduction Almost ten years ago I was working in another corporation and we built a system for one customer using AWS Batch. I have documented that story in this blog post: AWS Batch and Docker Containers . Now, after all these years, I got a similar use-case in my current project: batch processing in AWS infrastructure. A chance to implement the batch…
Python and Clojure side to side. Introduction We are building an in-house product in our unit. I was asked to create a quick proof of concept (POC) to see if it is feasible to create this kind of product. I asked if I am allowed to use what ever tools I want to build the POC as fast as possible. The product owner said yes. I chose to build a Clojure fullstack app. The application runs on AWS…
Clojure REPL. Table of Contents Introduction VSCode, Calva and REPL Editor Integration Babashka Fullstack Libraries Metosin Libraries: Reitit, Malli and Jsonista Aero and Integrant Replicant and Hiccup Development Practices and Tools REPL Personal Profile Deps Inline Defs Hashp Portal Gadget Calva Debugger Snitch Bonus Tool: Copilot Conclusions Introduction I have already covered Clojure Power…
Portfolio showing components of the application view, and the actual application, side by side. Introduction In my previous blog post Frontend Development with Clojurescript and Replicant I wrote about implementing a UI using the excellent Replicant library. In this new blog post I tell my experiences on how to use another Christian Johansen’s great library: Portfolio . The exercise I explain in…
Web app exercise implemented using Replicant, and showing the Gadget. Introduction In my previous blog post Clojure Re-Frame Exercise I wrote about implementing a UI using the Reagent Clojurescript React wrapper and the re-frame framework for managing state changes in your application. In this new blog post I tell my experiences using the Replicant library. The exercise I explain in this blog post…