In this episode we welcome back our good friend Demetrios from the MLOps Community to discuss fine-tuning vs. retrieval augmented generation. Along the way, we also chat about OpenAI Enterprise, results from the MLOps Community LLM survey, and the orchestration and evaluation of generative AI workloads.

There’s so much talk (and hype) these days about vector databases. We thought it would be timely and practical to have someone on the show that has been hands on with the various options and actually tried to build applications leveraging vector search. Prashanth Rao is a real practitioner that has spent and huge amount of time exploring the expanding set of vector database offerings. After introducing vector database and giving us a mental model of how they fit in with other datastores, Prashanth digs into the trade offs as related to indices, hosting options, embedding vs. query optimization, and more.

Chris and Daniel take a step back to look at how generative AI fits into the wider landscape of ML/AI and data science. They talk through the differences in how one approaches “traditional” supervised learning and how practitioners are approaching generative AI based solutions (such as those using Midjourney or GPT family models). Finally, they talk through the risk and compliance implications of generative AI, which was in the news this week in the EU.

Daniel & Chris delight in conversation with “the funniest guy in AI”, Demetrios Brinkmann. Together they explore the results of the MLOps Community’s latest survey. They also preview the upcoming AI Quality Conference.

What is the model lifecycle like for experimenting with and then deploying generative AI models? Although there are some similarities, this lifecycle differs somewhat from previous data science practices in that models are typically not trained from scratch (or even fine-tuned). Chris and Daniel give a high level overview in this effort and discuss model optimization and serving.

Large Language Model (LLM) capabilities have reached new heights and are nothing short of mind-blowing! However, with so many advancements happening at once, it can be overwhelming to keep up with all the latest developments. To help us navigate through this complex terrain, we’ve invited Raj - one of the most adept at explaining State-of-the-Art (SOTA) AI in practical terms - to join us on the podcast.

Raj discusses several intriguing topics such as in-context learning, reasoning, LLM options, and related tooling. But that’s not all! We also hear from Raj about the rapidly growing data science and AI community on TikTok.

There is crazy hype and a lot of confusion related to DeepSeek’s latest model DeepSeek R1. The products provided by DeepSeek (their version of a ChatGPT-like app) has exploded in popularity. However, ties to China have raised privacy and geopolitical concerns. In this episode, Chris and Daniel cut through the hype to talk about the model, privacy implications, running DeepSeek models securely, and what this signals for open models in 2025.

Recently a16z released a diagram showing the “Emerging Architectures for LLM Applications.” In this episode, we expand on things covered in that diagram to a more general mental model for the new AI app stack. We cover a variety of things from model “middleware” for caching and control to app orchestration.

We’ve seen a rise in interest recently and a number of major announcements related to local LLMs and AI PCs. NVIDIA, Apple, and Intel are getting into this along with models like the Phi family from Microsoft. In this episode, we dig into local AI tooling, frameworks, and optimizations to help you navigate this AI niche, and we talk about how this might impact AI adoption in the longer term.

Dominik Klotz from askui joins Daniel and Chris to discuss the automation of UI, and how AI empowers them to automate any use case on any operating system. Along the way, the trio explore various approaches and the integration of generative AI, large language models, and computer vision.

You might have heard a lot about code generation tools using AI, but could LLMs and generative AI make our existing code better? In this episode, we sit down with Mike from TurinTech to hear about practical code optimizations using AI “translation” of slow to fast code. We learn about their process for accomplishing this task along with impressive results when automated code optimization is run on existing open source projects.

As you start developing an AI/ML based solution, you quickly figure out that you need to run workflows. Not only that, you might need to run those workflows across various kinds of infrastructure (including GPUs) at scale. Ville Tuulos developed Metaflow while working at Netflix to help data scientists scale their work. In this episode, Ville tells us a bit more about Metaflow, his new book on data science infrastructure, and his approach to helping scale ML/AI work.

GenAI is often what people think of when someone mentions AI. However, AI is much more. In this episode, Daniel breaks down a history of developments in data science, machine learning, AI, and GenAI in this episode to give listeners a better mental model. Don’t miss this one if you are wanting to understand the AI ecosystem holistically and how models, embeddings, data, prompts, etc. all fit together.

Daniel and Chris groove with Jeff Smith, Founder and CEO at CHRP.ai. Jeff describes how CHRP anonymously analyzes emotional wellness data, derived from employees’ music preferences, giving HR leaders actionable insights to improve productivity, retention, and overall morale. By monitoring key trends and identifying shifts in emotional health across teams, CHRP.ai enables proactive decisions to ensure employees feel supported and engaged.

In this Fully Connected episode, Daniel and Chris kick it off by noting that Stability AI released their SDXL 1.0 LLM! They discuss its virtues, and then dive into a discussion regarding how the United States, European Union, and other entities are approaching governance of AI through new laws and legal frameworks. In particular, they review the White House’s approach, noting the potential for unexpected consequences.

We scoured the internet to find all the AI related predictions for 2024 (at least from people that might know what they are talking about), and, in this episode, we talk about some of the common themes. We also take a moment to look back at 2023 commenting with some distance on a crazy AI year.

Seems like we are hearing a lot about GraphRAG these days, but there are lots of questions: what is it, is it hype, what is practical? One of our all time favorite podcast friends, Prashanth Rao, joins us to dig into this topic beyond the hype. Prashanth gives us a bit of background and practical use cases for GraphRAG and graph data.

We discussed “🥦 Broccoli AI” a couple weeks ago, which is the kind of AI that is actually good/healthy for a real world business. Bengsoon Chuah, a data scientist working in the energy sector, joins us to discuss developing and deploying NLP pipelines in that environment. We talk about good/healthy ways of introducing AI in a company that uses on-prem infrastructure, has few data science professionals, and operates in high risk environments.

As a technologist, coder, and lawyer, few people are better equipped to discuss the legal and practical consequences of generative AI than Damien Riehl. He demonstrated this a couple years ago by generating, writing to disk, and then releasing every possible musical melody. Damien joins us to answer our many questions about generated content, copyright, dataset licensing/usage, and the future of knowledge work.

It was an amazing week in AI news. Among other things, there is a new NeRF and a new Llama in town!!! Zip-NeRF can create some amazing 3D scenes based on 2D images, and Llama 2 from Meta promises to change the LLM landscape. Chris and Daniel dive into these and they compare some of the recently released OpenAI functionality to Anthropic’s Claude 2.

Daniel & Chris explore the state of the art in prompt engineering with Jared Zoneraich, the founder of PromptLayer. PromptLayer is the first platform built specifically for prompt engineering. It can visually manage prompts, evaluate models, log LLM requests, search usage history, and help your organization collaborate as a team. Jared provides expert guidance in how to be implement prompt engineering, but also illustrates how we got here, and where we’re likely to go next.

You might have heard that “AI is only as good as the data.” What does that mean and what data are we talking about? Chris and Daniel dig into that topic in the episode exploring the categories of data that you might encounter working in AI (for training, testing, fine-tuning, benchmarks, etc.). They also discuss the latest developments in AI regulation with the EU’s AI Act coming into force.

Google has been releasing a ton of new GenAI functionality under the name “Gemini”, and they’ve officially rebranded Bard as Gemini. We take some time to talk through Gemini compared with offerings from OpenAI, Anthropic, Cohere, etc.

We also discuss the recent FCC decision to ban the use of AI voices in robocalls and what the decision might mean for government involvement in AI in 2024.

Model sizes are crazy these days with billions and billions of parameters. As Mark Kurtz explains in this episode, this makes inference slow and expensive despite the fact that up to 90%+ of the parameters don’t influence the outputs at all.

Mark helps us understand all of the practicalities and progress that is being made in model optimization and CPU inference, including the increasing opportunities to run LLMs and other Generative AI models on commodity hardware.

It seems like everyone is uses the term “agent” differently these days. In this episode, Chris and Daniel dig into the details of tool calling and its connection to agents. They help clarify how LLMs can “talk to” and “interact with” other systems like databases, APIs, web apps, etc. Along the way they share related learning resources.

This week Daniel & Chris hang with repeat guest and good friend Demetrios Brinkmann of the MLOps Community. Together they review, debate, and poke fun at the 2024 Gartner Hype Cycle chart for Artificial Intelligence. You are invited to join them in this light-hearted fun conversation about the state of hype in artificial intelligence.

How do you systematically measure, optimize, and improve the performance of LLM applications (like those powered by RAG or tool use)? Ragas is an open source effort that has been trying to answer this question comprehensively, and they are promoting a “Metrics Driven Development” approach. Shahul from Ragas joins us to discuss Ragas in this episode, and we dig into specific metrics, the difference between benchmarking models and evaluating LLM apps, generating synthetic test data and more.

The new open source AI book from PremAI starts with “As a data scientist/ML engineer/developer with a 9 to 5 job, it’s difficult to keep track of all the innovations.” We couldn’t agree more, and we are so happy that this week’s guest Casper (among other contributors) have created this resource for practitioners.

During the episode, we cover the key categories to think about as you try to navigate the open source AI ecosystem, and Casper gives his thoughts on fine-tuning, vector DBs & more.

Workflow orchestration has always been a pain for data scientists, but this is exacerbated in these AI hype days by agentic workflows executing arbitrary (not pre-defined) workflows with a variety of failure modes. Adam from Prefect joins us to talk through their open source Python library for orchestration and visibility into python-based pipelines. Along the way, he introduces us to things like Marvin, their AI engineering framework, and ControlFlow, their agent workflow system.

Chris & Daniel are out this week, so we’re bringing you a panel discussion from All Things Open 2023 moderated by Jerod Santo (Practical AI producer and co-host of The Changelog) and featuring keynoters Emily Freeman and James Q Quick.