Scale to Zero: Optimize AI Infrastructure Without Wasting Resources ??
Welcome to the latest edition of AI in 5 newsletter with Clarifai!
Every week we bring you new models, tools, and tips to build production-ready AI!
Here's a summary of what we will be covering this week: ??
Optimize AI workloads with scaling to zero ??
Scaling to zero helps you cut down infrastructure costs by automatically shutting down idle compute resources, making it perfect for workloads with variable demand.
With Clarifai's Compute Orchestration, you can configure Node Auto Scaling Range to dynamically scale resources — from handling traffic spikes to scaling down to zero when idle — ensuring you only pay for what you use.
This feature is especially useful for:
Learn when to scale to zero, how to set it up, and key scenarios where it makes the most impact.
RAG app to chat with GitHub! ??
We’ve built an app that lets you chat with any GitHub repository using Clarifai's RAG (Retrieval-Augmented Generation) capabilities!
Simply enter a GitHub URL, and the app will:
? Automatically load the repo contents ?? Understand code structure, documentation, and README files ?? Answer your questions about the repo's functionality and code
Built with MiniCPM3-4B + Embedchain + Streamlit, making it easy to explore the codebases faster.
Log in to the Platform and try out the app here: clarifai.com/sumanth/AI-Apps/installed_module_versions/chat_with_github
Clarifai research seminar: Ethical reasoning in Large Language Models ????
Why human-in-the-loop may exacerbate value alignment challenges!?
Clarifai present research seminars!
Catch the recording of our research seminar featuring Erin Taylor, Associate Professor of Philosophy at Washington and Lee University.
In this session, Erin explores how Human-in-the-Loop (HITL) systems, often seen as a safeguard in AI ethics, can sometimes worsen value alignment issues even with unbiased and well-intentioned human oversight.
The talk dives into ethical complexities in AI applications, especially in sensitive domains like biomedical research and regulatory decision-making. ?
If you're building or integrating AI into your projects, this seminar is a must-watch!
Watch the recording here
Track platform activity with Audit Logs API ??
Monitor every action on the platform with detailed logs using the Audit Logging API.
? See who performed what action
? What changes were made
? Whether the operation succeeded or failed
Use Teams & Logs to track resource changes, debug failed operations, and meet compliance requirements.
Access logs directly from the platform or programmatically through the API to integrate auditing into your workflows.?
Check out the API docs ?? https://docs.clarifai.com/api-guide/audit-log/
Tip of the week: ???
Create your dedicated Compute Clusters using the Python SDK?
Compute Clusters allow you to allocate dedicated resources to run your AI workloads more efficiently, giving you better control over performance and scaling.?
With the Python SDK, you can easily create a Compute Cluster using the create_compute_cluster() method from the User class.
To create a Compute Cluster, you'll need:
? Your Clarifai PAT (Personal Access Token)
? Your Clarifai User ID
? A YAML config file with cluster configurations?
Check out the code here.
Want to learn more from Clarifai? “Subscribe” to make sure you don’t miss the latest news, tutorials, educational materials, and tips. Thanks for reading!