<feed xmlns="http://www.w3.org/2005/Atom"> <id>https://otmaneboughaba.com/</id><title>Otmane Boughaba.</title><subtitle>Decoding the AI Hype: Bridging the Gap Between Expectations and Reality.</subtitle> <updated>2026-10-26T18:09:09+00:00</updated> <author> <name>Otmane Boughaba</name> <uri>https://otmaneboughaba.com/</uri> </author><link rel="self" type="application/atom+xml" href="https://otmaneboughaba.com/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="https://otmaneboughaba.com/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 Otmane Boughaba </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>Cloudflare Now Lets You Crawl the Web - The Same Company That Spent Years Stopping You</title><link href="https://otmaneboughaba.com/posts/cloudfare-crawler/" rel="alternate" type="text/html" title="Cloudflare Now Lets You Crawl the Web - The Same Company That Spent Years Stopping You" /><published>2026-03-15T00:00:00+00:00</published> <updated>2026-03-15T00:00:00+00:00</updated> <id>https://otmaneboughaba.com/posts/cloudfare-crawler/</id> <content type="text/html" src="https://otmaneboughaba.com/posts/cloudfare-crawler/" /> <author> <name>Otmane Boughaba</name> </author> <category term="scraping" /> <summary>Cloudflare spent years building tools to block AI scrapers. Bot protection, Turnstile, rate limiting… the whole arsenal. And now, quietly, they’ve shipped a Browser Rendering REST API that lets you crawl and extract structured data from any website. Let’s see what it can actually do. What Is Cloudflare Browser Rendering? Cloudflare Browser Rendering spins up a real headless Chromium browse...</summary> </entry> <entry><title>Building a Local RAG Pipeline for the Hollow Knight Wiki with Crawl4ai, Supabase and Ollama</title><link href="https://otmaneboughaba.com/posts/hollow-knight-rag/" rel="alternate" type="text/html" title="Building a Local RAG Pipeline for the Hollow Knight Wiki with Crawl4ai, Supabase and Ollama" /><published>2026-03-14T00:00:00+00:00</published> <updated>2026-03-14T00:00:00+00:00</updated> <id>https://otmaneboughaba.com/posts/hollow-knight-rag/</id> <content type="text/html" src="https://otmaneboughaba.com/posts/hollow-knight-rag/" /> <author> <name>Otmane Boughaba</name> </author> <category term="project" /> <category term="tutorial" /> <category term="llms" /> <category term="rag" /> <summary>Introduction I’m a huge fan of the Hollow Knight games by Team Cherry. To me, it’s the best metroidvania ever made. The amount of detail, lore, music, and content packed into that game is genuinely fascinating. The games lean heavily into exploration and never hold your hand, which means there’s a good chance you’ll get stuck at some point and find yourself digging through the wiki or Googlin...</summary> </entry> <entry><title>Dockerizing a RAG Application with FastAPI, LlamaIndex, Qdrant and Ollama</title><link href="https://otmaneboughaba.com/posts/dockerize-rag-application/" rel="alternate" type="text/html" title="Dockerizing a RAG Application with FastAPI, LlamaIndex, Qdrant and Ollama" /><published>2025-05-09T00:00:00+01:00</published> <updated>2026-10-26T18:08:22+00:00</updated> <id>https://otmaneboughaba.com/posts/dockerize-rag-application/</id> <content type="text/html" src="https://otmaneboughaba.com/posts/dockerize-rag-application/" /> <author> <name>Otmane Boughaba</name> </author> <category term="tutorial" /> <category term="llms" /> <category term="rag" /> <summary>Update (October 2026): this post was revised after the original setup stopped building with recent versions of Docker Compose. The base image is now built through additional_contexts, all images install dependencies from uv.lock into one shared virtual environment, the NVIDIA GPU configuration is optional, and the run steps ingest documents before starting the API. Introduction In the previo...</summary> </entry> <entry><title>Model Context Protocol - Let's build an MCP server in Python</title><link href="https://otmaneboughaba.com/posts/model-context-protocol/" rel="alternate" type="text/html" title="Model Context Protocol - Let&amp;apos;s build an MCP server in Python" /><published>2025-04-13T00:00:00+01:00</published> <updated>2025-05-16T17:47:53+01:00</updated> <id>https://otmaneboughaba.com/posts/model-context-protocol/</id> <content type="text/html" src="https://otmaneboughaba.com/posts/model-context-protocol/" /> <author> <name>Otmane Boughaba</name> </author> <category term="project" /> <category term="llms" /> <summary>Introduction LLMs are advancing at a rapid pace lately. Each week, we witness breakthroughs with new, very powerful models. However, they all share a common limitation: the inability to execute tasks or perform actions independently. This raises the question: wouldn’t it be nice if these LLMs could perform actions for us? For example, sending emails, checking if a folder is available in our Go...</summary> </entry> <entry><title>Simple Word2Vec implementation in PyTorch</title><link href="https://otmaneboughaba.com/posts/Word2Vec-in-Pytorch/" rel="alternate" type="text/html" title="Simple Word2Vec implementation in PyTorch" /><published>2024-03-23T00:00:00+00:00</published> <updated>2025-05-16T17:47:53+01:00</updated> <id>https://otmaneboughaba.com/posts/Word2Vec-in-Pytorch/</id> <content type="text/html" src="https://otmaneboughaba.com/posts/Word2Vec-in-Pytorch/" /> <author> <name>Otmane Boughaba</name> </author> <category term="nlp" /> <category term="deeplearning" /> <category term="pytorch" /> <summary>Introduction One of the most important steps in solving NLP tasks using AI is finding a way to convert “words,” which humans can understand, into numbers, which computers and neural networks can understand. There are many ways to achieve this, but the challenge lies in preserving the meaning and significance of words without losing information in the process. In this article, we’ll explore wo...</summary> </entry> </feed>
