The live stream recording of my #MovementData engineering workshop with #DVC and #MovingPandas is up now at 🎬 https://www.youtube.com/live/roPF1oth2Pk?si=qKcWpJU96VWc9vZZ 🎬

Thanks to @opengeohub!

There will also be an edited version on TIB.eu in the future, if you prefer an add free platform. Stay tuned

#OGH2023 #OGHSummerSchool2023 #MLOps #GISChat

A short and concise explanation about the VScode's Dev Containers extension 👇🏼

https://www.youtube.com/watch?v=b1RavPr_878

The Dev Containers extension enables to run code in VScode inside a containerized environment seamlessly.

#vscode #docker #devops #mlops #DataScience

I am excited to present in November at the Oredev Developer Conference in Sweden about forecasting and MLOps 🚀. In addition, I will run a workshop about forecasting methods with regression models ❤️.

https://oredev.org/

Please ping me if you are going to be there!

#DataScience #mlops #forecasting #oredev

There are tons of MLOps platforms, middlewares and lambdas... are there some missing components? Seems that all is already in place😅
#mlops #datascience #kubernetes

Is there a real alternative to prometheus? Seems that is the only player in metrics collection...
#kubernetes #mlops #docker

"The real issue with [LangChain] integrations is that it creates an inherent lock-in to only use LangChain-based code, and if you look at the code for the integrations they are not very robust. LangChain is building a moat, which is good for LangChain’s investors trying to get a return on their $30 million, but very very bad for developers who use it."

Rereading this critical review of LangChain by @minimaxir, which deserves more reads: https://minimaxir.com/2023/07/langchain-problem/

#llms #langchain #mlops #chatgpt

Maybe the fact that LangChain (the company) made it will lend LangSmith some legitimacy. LangChain (the framework) surely has seen a rapid rise in popularity -- although Github Stars might be a bad metric for actual production use.

Here is a comparison chart with some of the other popular NLP/LLM libraries -- these repos do not implement the same functionality but it should give you a rough idea.

#langsmith #langchain #llms #generativeai #mlops #ai

However, I'm curious about what the volume of adoption will be. LangSmith is a platform, not a self-hosted opensource MLOps tool. Are engineers/users really willing to give all their data to yet another third party?
Some people already hesitate to use AI API's (such as the OpenAI GPT API) because they're concerned with leaking sensitive data -- let alone using third-party AI platforms that man-in-the-middle your LLM conversations.

#langsmith #llms #generativeai #mlops #ai #privacy #infoleaks

The documentation is still a bit all over the place, but this walkthrough shows a sneak peek of what's possible:

https://github.com/langchain-ai/langchain/blob/master/docs/extras/guides/langsmith/walkthrough.ipynb

I especially like the idea of quickly evaluating variations of an LLM pipeline against a baseline of earlier runs.

#langsmith #langchain #llms #generativeai #mlops #ai

Today I took a first look at LangSmith, a new platform for LLM production pipelines by LangChain.
I can't hook it up to a working pipeline yet because it's in closed beta, but it surely looks ambitious. It should make it easier to do logging, monitoring, debugging and evaluating pipelines (chains) against each other. It's tightly integrated with LangChain but it should support other frameworks/models as well.

https://www.langchain.com/langsmith

#langsmith #langchain #llms #generativeai #mlops #ai

🚀 Neues Video «Ein Mate mit...» über Machine Learning und #MLOps.

Iwan Imsand, Software Engineer bei Puzzle, nimmt dich in die faszinierende Welt des Machine Learnings mit. Von den Feinheiten zwischen #AI, #MachineLearning und #DeepLearning bis hin zu schicken Open Source Tools, wie: #DVC, #CML, #MLflow, #Kubeflow.

Und weil wir bei Puzzle auch gerne komplexe Probleme lösen, zeigen wir dir, wie wir Unternehmen im MLOps Bereich unterstützen können. 🤖🚀💡

🚀 Check out what's new in Argo Workflows v3.5! It's packed with a whopping 54 new features!

For more details, check out the release blog: https://tinyurl.com/4pkcbuku

#Kubernetes #MLOps #AIOps #DevOps #CloudNative

Greetings from #DEFCON31! 👋

🐢 The Giskard team is now at #DC31 and we'll be happy to meet you. Join us at the #AIVillage for the #GenAI #RedTeam.

📩 DM us if you want to meet and discuss about #AISafety, #LLMs safety, #AI #Testing and #MLOps.

Are there any lists covering machine learning/AI focussed tooters? Im slowly but steadily steering my career to #LLM and #MLOps and would love to connect. #ml boost, please?

It's that times of the week for All Hands on #data 🥳

Whether you are trying to escape the summer heat, or hang out with Python's favorite bear 🐼 - this week's articles from across the data space have something for you!

Full articles 👇

(Subscribe to stay up to date 😊)

#dataorchestration #mlops #dataops #dataengineering

https://allhandsondata.substack.com/p/all-hands-on-data-61

Super excited to see Kubeflow joining CNCF as an incubating project!

🚀 https://cncf.io/blog/2023/07/25/kubeflow-brings-mlops-to-the-cncf-incubator/

#MLOps #CloudNative #kubernetes #MachineLearning

glad to see #MLOps growing within the CNCF. the @kubeflow project has been around since 2017, offering a #cloudnative solution to deploy machine learning workloads on #kubernetes.
Congrats to the #kubeflow team👏
https://cncf.io/blog/2023/07/25/kubeflow-brings-mlops-to-the-cncf-incubator/
#MachineLearning #DevOps

So you're thinking of deploying AI in your Organisation – but Have you thought of … 💭🤔

Here's my latest #AI article via @medium

2nd article of the week! 🤓😏

#GenerativeAI #LLMs #artificialintelligence #MLops #LanguageModels #aiethics #AIbias

https://medium.com/@paul.ekwere/so-youre-thinking-of-deploying-ai-in-your-organisation-but-have-you-thought-of-dcfdf20c6ef2

Hi everyone, Argo Workflows v3.4.9 is out! Please try it out and let us know if you see any issues!

Argo Project #Kubernetes #CloudNative #k8s #DevOps #MLOps #GitOps

https://github.com/argoproj/argo-workflows/releases/tag/v3.4.9

MLOps Business Challenges.
I previously described MLOps and how it’s possible build your own MLOps system by combining existing open-source libraries. There’s new research into MLOps that sheds more light on MLOps including the business challenges.
https://mrprediction.com/mlops-business-challenges/
#machinelearning #mlops