🇫🇷 Video in French État des lieux réalisé avec la GenAI (en français) 🎨🖼️🔊 Exemple d’usage non textuel des modèles génératifs

J'hoste un nouvel épisode d' E-After Work: Observabilité illimitée + OpenTelemetry. Make sure to attend it on December 4. Avec @VictoriaMetrics

But maybe they’re protecting us from something much bigger. 💡 In the end: both the “teenagers” and the “parents” have a point… …except teenagers often grow up to see the wisdom of their parents.

Just hack your OpenAI account. 🧬 Medical data → uploaded test results 💶 Financial info → GPT advice on investments 📝 Personal life → CVs, cover letters, even private docs ... One breach = your whole life exposed. So yes, EU rules can feel restrictive.

But here’s the thing… Privacy rules might actually make sense. Before, if someone wanted to social-engineer you, they had to: 🗑️ Dig through your trash 📞 Tap your phone 👥 Talk to your friends 📊 Track your finances 🏥 Spy on your medical records Today?

🚨 EU regulations: annoying or wise? Sometimes they feel like the wisdom of parents 👨‍👩‍👧 that teenagers just don’t want to hear. Take Apple’s new AirPods with live translation ; not allowed in the EU. First reaction? “Why are you stopping us from living our lives?”

🚀 Meetup Elastic FR #98 en approche ! 📅 Rentrée de Septembre (11, 18 ou 25) 🔎 On cherche : •📍 Un lieu pour accueillir la communauté •🎤 Des sujets à partager & présenter 🔥 Tu as un espace dispo ? Une idée de talk ? Faisons de ce meetup un super moment ensemble ! 🤗

Bon, ça y est, l'aventure des 12 Coups prend fin ! Merci pour tout, à @JL_Reichmann, aux équipes et au plaisir de se retrouver demain à 17h avec le goat @AREtoiles sur Twitch pour un p'tit react de l'émission d'aujourd'hui ! 😊 https://t.co/VHyeWbHDzo

Not evey search should be a vector search even In RAG use cases

At its most basic, this turns your RAG system into pure vector search. At its most advanced, it becomes full caching without querying the model.

Semantic caching can be a powerful tool to optimize your LLM calls by using your embedding model to find similarities with previously generated answers. The way it works: you set a similarity threshold between your current question and past questions that already have answers.

🎥 Meetup ElasticFR 96 : Observer son #RAG de R à G… et au-delà par @Aimgharne, consultant search indépendant 👉🏼 https://t.co/Cen3Z5dFLT

Speaking about observability for RAG Apps

📣 Rappel : rejoignez @Aimgharne, consultant search indépendant, pour notre meetup chez https://t.co/qDASjzNhQB le 12 juin 2025 à 19h à propos de "Observer son #RAG de R à G… et au-delà" ! Inscriptions 👉🏼 https://t.co/yiJ2WGC7yM

Interesting talk in french about vectorsearch in @weaviate_io https://t.co/dH1jPOZCG7

View my verified achievement from @awscloud. https://t.co/gaWlfqW7QG via @credly

https://t.co/dO5210lCoA

I’m gonna give 10 random people that repost this and follow me $25,000 for fun (the $250,000 my X video made) I’ll pick the winners in 72 hours

Whether you're a business owner or a budding data engineer, understanding the importance of data engineering is crucial in today's data-driven world. Stay tuned for more insights on #dataengineering and how it's shaping the future of #bigdata and #analytics.

In addition to technical skills, data engineers must possess strong problem-solving and communication skills to work effectively with cross-functional teams. They are key players in helping businesses make informed decisions based on data insights. #datascience #analytics