Bogdan_Teleuca Tracker

Stocking the Library: Local Files, Custom Scripts, and Git Sources in SAS® Retrieval Agent Manager

Bogdan_Teleuca — Mon, 20 Apr 2026 21:26:41 GMT

A knowledge library is only as good as what's in it. In this third post of the series, we follow Ramona, our EMS Education Director, as she brings content into SAS® Retrieval Agent Manager using three different source types: local files, custom Python scripts, and Git repositories. Along the way, we unpack what sources and collections actually are and why the distinction matters.

Re: Code Smarter: AI as a SAS Programming Assistant

Bogdan_Teleuca — Tue, 14 Apr 2026 04:22:30 GMT

Thanks for sharing your experience. Keep on exploring for different programming use cases and please publish your conclusions. I would be curious how Claude or GPT fares for code generation versus the SAS Viya Copilot (code assistance).

Re: Building Applications Faster with SAS OpenAPI Specifications and GitHub Copilot in VS Code

Bogdan_Teleuca — Wed, 01 Apr 2026 23:44:23 GMT

Xavier, un grand merci (big thanks)! That's a very nice and well-timed article about using OpenAPI specifications in conjunction with agents from GitHub Copilot. It's a great use case, opening the door to a multitude of custom integrations across SAS products! Thanks. Keep on writing about this topic with other examples, I think it's highly relevant and important.

Setting Up LLMs, Embeddings, and Vector Databases in SAS® Retrieval Agent Manager

Bogdan_Teleuca — Mon, 30 Mar 2026 03:50:54 GMT

Discover how to wire the foundation of a Retrieval-Augmented Generation (RAG) system in SAS® Retrieval Agent Manager. In this second post of the series, we follow Ramona, our EMS Education Director, as she connects Large Language Models, embedding models, and vector databases so her knowledge library can actually think, search, and answer.

LLMOps with SAS Viya and Azure DevOps: A Parameter Change, Not a Project

Bogdan_Teleuca — Mon, 16 Mar 2026 02:13:15 GMT

LLMOps with SAS Viya and Azure DevOps: a four-stage Azure DevOps pipeline. Register, Publish, Deploy, Test that deploys containers for LLM wrappers needed inside SAS Intelligent Decisioning agentic AI workflows.

Re: Considerations for evaluating the effectiveness of RAG models

Bogdan_Teleuca — Tue, 24 Feb 2026 01:00:58 GMT

Thanks for your research, explaining the concepts and providing additional resources! Included the link to the post in the workshop.

Re: Evaluating the Performance of Retrieval Augmented Generation Pipelines using the Ragas Framework

Bogdan_Teleuca — Tue, 24 Feb 2026 00:59:59 GMT

Thanks for explaining Ragas in a bit more detail. Included the link to the post in the workshop.

A Day in the Life of Ramona: Building Trusted Knowledge with SAS® Retrieval Agent Manager

Bogdan_Teleuca — Tue, 24 Feb 2026 00:14:53 GMT

Discover, through the eyes of an EMS education director, how to turn scattered PDFs into a trusted, living knowledge system. In this post and demo video, you’ll see how SAS® Retrieval Agent Manager delivers instant, grounded answers, automates updates, and connects knowledge to real‑world workflows, so teams get the right guidance exactly when it matters.

SAS Agentic AI – Deploy and Score a SAS Agent on Kubernetes

Bogdan_Teleuca — Fri, 23 Jan 2026 09:37:39 GMT

In this post, we’ll take a SAS agent, an agentic AI workflow built in SAS Intelligent Decisioning, publish it as a container image to Azure Container Registry (ACR), deploy it to Kubernetes, and score it through a secure HTTPS endpoint. At the end of the post, you will have a SAS agent running in production.

Re: Can GPT-5 Build SAS Studio Flows? A Hands-On Test Drive

Bogdan_Teleuca — Fri, 03 Oct 2025 10:47:27 GMT

@AndreasMenrath You're welcome. Not to mention you will have costs for your LLM... 😁 The point of the post is the prompt and the prompting technique. And the post definitely not intended for users who want to click. It's intended for automatic processes that can use code to replicate a SAS Studio flow. Obviously, I failed to explain that. I should do a better job.

Can GPT-5 Build SAS Studio Flows? A Hands-On Test Drive

Bogdan_Teleuca — Wed, 01 Oct 2025 05:32:00 GMT

Can generative AI build an entire SAS Studio flow, not just snippets or code fragments?SAS Studio flows are a staple for data engineers working with the SAS Viya platform. Enter generative AI, specifically GPT-5 from Azure OpenAI: can it create entire SAS Studio flows from prompts? And just how well does it understand the structure, logic, and metadata behind your flows?

In this post, I’ll walk you through a pair of hands-on demos that probe the limits of GPT-5’s code generation for SAS Studio flows. You’ll see where it shines, where it stumbles, and what this means for the future of SAS Studio flows generation.

Re: Go with the Job Flow in SAS Viya 3.5

Bogdan_Teleuca — Wed, 03 Sep 2025 02:18:12 GMT

@touwen_k The job flow 0 is another job flow (made of jobs, logical gates). The point of the example was to show that you can also trigger a whole job flow, not only jobs...

Re: Go with the Job Flow in SAS Viya 3.5

Bogdan_Teleuca — Wed, 03 Sep 2025 02:14:48 GMT

@__david__ I apologize to answer so late. Hm...

By default, a connection from a job to another object (a job dependency) specifies that the connected object runs when the job it is connected to completes successfully. You can change the job-dependency criteria. See Modifying a Job Dependency.
I would click on the connector (arrow) between the connected objects. Then modify the job dependency.

Let me know if that helps.

Re: SAS Agentic AI – Deploy and Score Models – Kubernetes

Bogdan_Teleuca — Wed, 03 Sep 2025 02:07:24 GMT

@touwen_k that's the ultra secure version. Try it. Working on 8080 inside the cluster should be ok for most of the use cases. If you have ultra sensitive data and you don't want users with cluster access to potentially snoop it, working with 8443 should be the way to go forward. Bear in mind that when you open 8443, 8080 stays open. The doc explains how to close it.

SAS Agentic AI – Build Workflows in SAS Intelligent Decisioning

Bogdan_Teleuca — Fri, 03 Oct 2025 14:29:06 GMT

Welcome back, SAS Agentic AI explorers! Today, we’re going forward with Agentic AI workflows in SAS Intelligent Decisioning—focusing on the build. We'll detail how you can integrate Large Language Models (LLMs), deterministic models, code files, and custom rules into a governed, modular SAS Agentic AI workflow.

SAS Agentic AI – Deploy and Score Models – Kubernetes

Bogdan_Teleuca — Fri, 19 Dec 2025 03:16:22 GMT

Welcome back to the SAS Agentic AI Accelerator series! We’ve already cooked up LLM deployments with Docker and Azure’s managed services. Now, it’s time to turn up the heat with Kubernetes—the espresso machine of the cloud world. Sure, it has a few extra knobs and steam valves, but it gives you barista-level control.

If you crave fine-tuned control, serious scalability, and rock-solid HTTPS security, Kubernetes is your playground. Let’s roll up our sleeves and get an LLM running—with plenty of focus on keeping it secure and scalable. For simpler setups, Azure’s managed options work great, but for ultimate power and flexibility, Kubernetes is where magic happens!

SAS Agentic AI – Deploy and Score Models – Apps

Bogdan_Teleuca — Fri, 19 Dec 2025 03:12:48 GMT

Welcome back to the SAS Agentic AI Accelerator series! If you’ve followed the journey so far—through registration, publishing, and container deployments—then you’re ready for the next stop: deploying your Large Language Models (LLMs) in Azure using Container Apps and Web Apps.

If deploying with Docker containers felt like making espresso, get ready for an espresso macchiato. A bit more involved (and maybe some extra foam). Let’s get brewing!

Re: All about CORS and CSRF for developing web applications with the SAS Visual Analytics SDK

Bogdan_Teleuca — Thu, 10 Jul 2025 01:57:18 GMT

it's great, thanks!

Re: Configure Cross-Origin Resource Sharing for SAS Viya for REST API’s and web developments

Bogdan_Teleuca — Thu, 10 Jul 2025 01:54:03 GMT

super useful, merci!

SAS Agentic AI – Deploy and Score Models – Containers

Bogdan_Teleuca — Fri, 19 Dec 2025 03:09:51 GMT

Welcome back to the SAS Agentic AI Accelerator series! If you’ve made it this far in the series, you’ve survived the high-level overviews and cost comparisons—give yourself a pat on the back (or at least a fresh cup of coffee). Now, let’s roll up our sleeves and actually deploy something.

Ever tried to deploy a Large Language Model (LLM) and felt like you were assembling IKEA furniture with missing instructions? Today, I’ll walk you through the nuts and bolts—so you can get your models running in Azure with minimal head-scratching.

Today, we’re going to take all that theory and put it into practice: deploying a code-wrapped LLM as a container in Azure. We’ll start simple (public IP), then get secure (private IP), and make sure you know what to watch out for at every step.