Alain Airom articles - 64 total
Vector Databases: their utility and functioning (RAG usage)
A reflection on vector databases and their usage by LLMs, by implementing a rudimentary one! ...
Invoice Data Extraction using IBM Granite LLM locally (not from watsonx!)
Adapting Granite use-case to execute locally. Introduction The Granite family of...
Writing Code (and much much more…) with watsonx Code Assistant — An update
Experiencing code generation/documentation with “watsonx code assistant”. ...
Build a knowledge graph from documents using Docling
First experience of building a knowledge graph from a document using Docling! ...
Picture annotation with Docling
Use docling built-in features to make picture annotation. Introduction Picture annotation, a...
Building a RAG with Docling and LangChain
Hands-on experience building a RAG with Docling and LangChain. Introduction This...
MCP Server/Client and Agent and my unanswered philosophical question!
I wrote my sample MCP server, client and agent… 🤷♂️ Introduction Everyday, browsing...
Running Docling as an API Server
How to start with “docling serve”! Introduction Docling offers a user-friendly...
Steps to deploy Python applications in containers and to Kubernetes clusters for data scientists and ML engineers
Simple guidance for data science and/or ML engineers to help application deployment to containers and...
How to import sample data into a Python notebook on watsonx.ai and other questions…
Some tips regarding using notebooks in watsonx.ai studio! Introduction Recently one of...
Docling “Enrichment Features”
Using Docling enrichment features! Introduction Docling simplifies document processing,...
Visual Grounding from Docling!
My experience testing for a demonstration “Visual Grounding” feature of Docling on Intel CPU. ...
Nice open-source UI Tool to interact with kubernetes clusters
My hands-on experience with “Cyclops” to deploy applications on kubernetes clusters. [Image...
Processing data with “Data Prep Kit” (part 2)
Using “Data Prep Kit” to embed data in Milvus and query it! This is the part 2 of hands-on experience...
Crawling web sites using “Data Prep Kit”
A hands-on exercise using “data-prep-kit” and storing the result as parquet files. ...
Using Docling’s OCR features with RapidOCR
Using RapidOCR implementation with custom OCR models. Introduction Docling’s RapidOCR...
Building and running AI applications all in one place (prompts, notebooks, agents…); watsonx.ai studio!
If you want to build entreprise ready AI based applications, using different language models,...
User authentication caching in FastAPI
Mocking a user authentication with cached bearer token to reduce latencies and enhance end-user...
Figure Export from Docling — Exporting PDF to image
Using Docling “Figure Export” capacities. Introduction Among the export set of functionality...
Great one!
Introduction to branched RAG IBM...
Building your own code assistant! How long does it take?
I made my coding assistant based on the article “Build Your Own AI Coding Assistant in JupyterLab...
Using llama-cookbook “Text2SQL” and really impressed!
My experience trying ‘Text2SQL’ recipe from llama-cookbook series! Image from Meta’...
Impressive evolution of BeeAI
TL;DR — Introduction Agents 🤖 are coming and they are almost everywhere! IBM research...
New Interface to Build Agents in watsonx.ai Studio
The new GUI to build ReAct agents in watsonx.ai Introduction Building agents through a...
Using “Docling Parse”!
Extract text, paths and bitmap images with coordinates from programmatic PDFs! ...
Docling's new “SmolDocling-256M” Rocks
First impression of testing “SmolDocling-256M-preview” available on Hugging Face. ...
Deploying rapidly an enterprise grade Generative AI platform
Using deployable architectures on IBM Cloud to provision and use generative AI platforms. ...
My personal “majordhomme” (butler) AI agent with CrewAI, Granite, DeepSeek and more…
An agent based on CrewAI with different skills using Granite and DeepSeek so far (more to come) ...
Populating a RAG with data from enterprise documents repositories for Generative AI
Ingesting data from OneDrive into Milvus in order to use with generative ai. Image courtesy...
Simple Knowledge Retrieval: A RAG Implementation and query using IBM Granite on Hugging Face
A simple RAG implementation and query using IBM Granite on Hugging Face. ...