Alain Airom articles - 113 total
Implementing a Basic MCP Server and Two Communicating Agents in Python
A hands-on exercise to describe MCP server and agents in a basic understandable (so I hope) way! ...
Information Extraction (Tests on a Beta API) from Docling
An early test on information extraction API from Docling Introduction Docling provides...
Mixture of Experts Implementation using Granite4: Harnessing Specialization with the Latest Granite Family Model
A sample implementation of Mixture of Experts (MOE) using the latest Granite family LLM! ...
🪨 ‘Granite 4’ Meets ‘Kubectl-AI’: Building Your Own Local, Executable Kubernetes Assistant
Stop Googling Commands: A Personal Kubernetes AI Shell Powered by IBM Granite 4 and Google’s...
The Secret to Efficient RAG: A Step-by-Step Guide to Chunking and Counting Your Vectors
Debunking the vetor count estimation for documents Introduction In the often highly...
Embedded Intelligence: How SQLite-vec Delivers Fast, Local Vector Search for AI.
An experience with SQLite as a vector database Introduction - Embedded Intelligence:...
Decoding AI’s Inner Language: How to Test Your Embedding Models
Testing some embeddings… with Ollama Introduction — Embeddings If Large Language Models...
Testing Ollama Web Search 🔍 and a Thinking Model 💭
Testing Ollama Web Search with gpt-oss Ollama Web Search The recent addition of web...
Kubernetes Security Book (2nd Edition) — A Synthesis
A feedback after reading the “Kubernetes Security Book — 2nd Edition” by Packt Publishing ...
Introducing a Game-Changer: Docling and IBM Cloud Code Engine Join Forces
Combining Docling capacities with IBM Cloud Code Engine serverless compute capacities ...
Unlock Your Data: Supercharge Excel Document Processing with Docling
Docling does not manage Excel files natively for now, hereafter a workaround and implementation. ...
My very first hands-on epxerience with Langflow
A very short 1st experience with Langflow Introduction Langflow is an open-source...
Unlocking Insights: Monitoring Your Apps with Grafana & Prometheus (and Why LLMs Need It Too!)
Tests on monitoring LLM based application by Grafana/Prometheus Introduction Ever...
📣 Just announced: IBM Granite-Docling: End-to-end document understanding with one tiny model
Another exciting feature with Docling! Introduction The ability to seamlessly convert...
Moving Your Vector Database from ChromaDB to Milvus
A theorical approah to migrate data from ChromaDB to Milvus vector database ...
Unlocking the Power of Time: An Introduction to Time Series Analysis
Follow-up on my hands-on experieneces with TimeSeries Anlysis using Granite foundation models ...
First Hands-On Experience with Apple Containers!
A very first test with Apple containers! Introduction In the world of software...
Early Feedback on “Build a Reasoning Model (From Scratch)”
A feedback on the book “Build a Reasoning Model (From Scratch)” from Manning edition by Sebastian...
The Future of Document Scanning: A Look at LLM-Powered OCR
Hands-on experience using ‘Llama’ & ‘Granite’ Vision Models locally with Ollama ...
Code Generation with ‘Graph RAG’, AstraDB and gpt-oss
Exercise based on AstraDB’s notebook “Code Generation with GraphRAG” ...
A Developer’s Guide to Azure: A Deep Dive into the “Azure for Developers”
One of my readings during my summer break! Introduction I read a lot of technical books...
Hands-on and Testing of Google “langextract” and further thoughts…
A hands-on testing of Google’s LangExtract and future thoughts. ...
What I learnt from reading a book on Graph Query Language (GQL)
Feedback on Packt book Getting Started with the Graph Query Language (GQL) ...
My Local/Remote LLM Studio — watsonx.ai and Ollama (part 1)
Buiding my own LLM studio! Introduction & Motivation Building a Local LLM...
MCP Context Forge Gateway — Try it now! ⚡
A brief introduction to MCP Context Forge Gateway and why you should use it :) ...
Using “OpenLLMetry” is simple comme Bonjour :)
A first test on OpenLLMetry from Traceloop. The Unseen Navigator: Why Telemetry is...
Beyond Search: How to Chat with Your Documents Using AstraDB Vector Database, Docling and Granite
Hands-on vectorization and embedding with AstraDB (DataStax/IBM) vector database. ...
Unlocking Visual Intelligence: Picture Annotation with Remote VLM Power
Implementing Picture Annotation using Remote Visual Language Models and Docling! ...
Fun project of the week, Mermaid flowcharts generator!
Using a LLM to generate Mermaid flowcharts! Introduction It is not so long I discovered...
Maximize Your Documents: Exploring the Advantages of Full OCR of PDF files and chat with your documents!
A reflection on benfits of full text OCRization and how it becomes handy with LLM enables...