ACAngel Chavezinblog.it-anc.cloud·2d ago · 5 min readPython for DevOpsWhy The Refresher I'm trying to bridge a gap in my Python knowledge as I pursue automations and a DevOps job. Refreshing the fundamentals now will solidify what I know, so I'm working through a course00
NLNexona Labsinnexonalabs.hashnode.dev·2d ago · 4 min readCaching a Product Catalogue With Redis + FastAPIA product catalogue is the most-read data in a shopping app and one of the least-changed. Every time someone opens the app, they load a category grid. A few times a week, someone in the team changes a00
MBMadhav Bhasininblog.madhav.dev·3d ago · 6 min readPrompt Versioning and Cost Control: Running LLMs Responsibly in ProductionThe monthly bill was ten times the estimate. Investigation took two hours. Three things were wrong. A retry loop was calling the model on every validation error — including schema mismatches that woul00
HHimaniinhimanitayal.hashnode.dev·4d ago · 3 min readPython for PHP Developers: A Practical Crash CourseIf you already write PHP, Java, or JavaScript, you don't need a "what is a variable" tutorial. You need to know how Python differs from what you already know. I moved from 8+ years of PHP/Magento to P00
MBMadhav Bhasininblog.madhav.dev·4d ago · 5 min readAsync AI Pipelines in FastAPI: Streaming, Queuing, and Long-Running RequestsThe document extraction endpoint was synchronous. A request came in, the service sent the document to OpenAI, waited for the full response, parsed it, wrote to the database, and returned. Each request00
Jjudeinsoit-ai.hashnode.dev·4d ago · 16 min readWhat your healthcheck actually checks: four probe bugs in a self-hosted agent runtimeThe short version When docker compose ps says the api container is unhealthy, is it right? And what is it actually checking? Our health checks turned out to have one probe that checks too hard, one th00
MAMuhammad Ariel Shakaramiroinshaka-ai.hashnode.dev·6d ago · 8 min readOne Answer, Four Different Scores: Learning LLM Evaluation the Hard WayThis week's material was about evaluating LLMs: offline metrics (tested against a fixed dataset) versus online metrics (measured from real user interaction). It sounds straightforward on the slides. O00
DIDaniel Idowuinthe-neural-notebook.hashnode.dev·Sep 24 · 11 min readBuilding PneumoTriage: What I Learned Screening Pediatric Chest X-Rays with ML in Nigeria In many hospitals in Nigeria, and in much of Africa, there are very few radiologists for the number of chest X-rays that need reading. A child with suspected pneumonia can wait hours or days for a spe00
NNevin-Baliinnevinbali.hashnode.dev·Sep 19 · 6 min readBuilding DevDocAI — A Production Multi-Agent LangGraph System | Part 6 — The Full Loop Works. Now: Deployment...Series: Building DevDocAI — A Production Multi-Agent LangGraph System Part 6 — The Full Loop Works. Now: Deployment. The Milestone Something clicked this week that hasn't clicked before in this pr12A
MAMuhammad Ariel Shakaramiroinshaka-ai.hashnode.dev·Sep 19 · 7 min readFace Recognition: Turning a Classifier Into an Embedding That Can Learn New FacesPhones that unlock just by looking at you, office systems that recognize whoever just walked through the door: the trick behind both is rarely "just train a classifier." This post walks through why, a00