Agentic Conversations (formally mlops.community)

Daniel Svonava is the Co-Founder of Superlinked. Daniel Svonava attended the Faculty of Informatics and Information Technologies at the Slovak University of Technology.

MLOps podcast #214 with Daniel Svonava, CEO & Co-founder at Superlinked, Information Retrieval & Relevance: Vector Embeddings for Semantic Search

// Abstract

In today's information-rich world, the ability to retrieve relevant information effectively is essential. This lecture explores the transformative power of vector embeddings, revolutionizing information retrieval by capturing semantic meaning and context. We'll delve into:- The fundamental concepts of vector embeddings and their role in semantic search- Techniques for creating meaningful vector representations of text and data- Algorithmic approaches for efficient vector similarity search and retrieval- Practical strategies for applying vector embeddings in information retrieval systems

// Bio

Daniel is an entrepreneurial technologist with a 20 year career starting with competitive programming and web development in highschool, algorithm research and Google & IBM Research internships during university, first entrepreneurial steps with his own computational photography startup and a 6 year tenure as a tech lead for ML infrastructure at YouTube Ads, where his ad performance forecasting engine powers the purchase of $10B of ads per year.

Presently, Daniel is a co-founder of Superlinked.com - a ML infrastructure startup that makes it easier to build information-retrieval heavy systems - from Recommender Engines to Enterprise-focused LLM apps.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Daniel on LinkedIn: https://www.linkedin.com/in/svonava/?originalSubdomain=ch

Timestamps:

[00:00] Daniel's preferred coffee

[00:13] Takeaways

[04:59] Please like, share, leave a review, and subscribe to our MLOps channels!

[05:22] Recommender system pivot insights

[08:49] RaaS Challenges and solutions

[10:23] Vector Compute vs Traditional Compute

[13:20] String conversion challenges

[17:18] Vector Computation in Recommender Systems

[20:55] RAG system setup overview

[26:00] ETL and Vector embeddings

[31:04] Fine-tuning embedding models RAG

[36:10] Flattening data for Vectors

[37:18] Vector compute control insights

[47:48] Vector Hub database comparison

[51:22] Vector database partnership strategy

[52:47] Vector computation in ML

[55:43] Wrap up

Morgan McGuire has held a variety of roles in the past 13 years. In 2008, he completed a Research Internship at Queen Mary, University of London. Currently, he is the Head of Growth ML and Growth ML Engineer at Weights & Biases.

Anish Shah has been working in the tech industry since 2015. In 2015, he was a Technical Support at Fox School of Business at Temple University. In 2021, he was an MLOps Engineer - Growth and a Tier 2 Support Machine Learning Engineer at Weights & Biases.

_________________________________________________________

Large Language Models have taken the world by storm. But what are the real use cases? What are the challenges in productionizing them? In this event, you will hear from practitioners about how they are dealing with things such as cost optimization, latency requirements, trust of output, and debugging. You will also get the opportunity to join workshops that will teach you how to set up your use cases and skip over all the headaches.

Join the AI in Production Conference on February 22 here: https://home.mlops.community/home/events/ai-in-production-2024-02-15

_________________________________________________________

MLOps podcast #213 with Weights and Biases' Growth Director, Morgan McGuire and MLE, Anish Shah, Evaluating and Integrating ML Models brought to you by our Premium Brand Partner  @WeightsBiases.

// Abstract

Anish Shah and Morgan McGuire share insights on their journey into ML, the exciting work they're doing at Weights and Biases, and their thoughts on MLOps. They discuss using large language models (LLMs) for translation, pre-written code, and internal support. They discuss the challenges of integrating LLMs into products, the need for real use cases, and maintaining credibility.

They also touch on evaluating ML models collaboratively and the importance of continual improvement. They emphasize understanding retrieval and balancing novelty with precision. This episode provides a deep dive into Weights and Biases' work with LLMs and the future of ML evaluation in MLOps. It's a must-listen for anyone interested in LLMs and ML evaluation.

// Bio

Anish Shah

Anish loves turning ML ideas into ML products. He started his career working with multiple Data Science teams within SAP, working with traditional ML, deep learning, and recommendation systems before landing at Weights & Biases. With the art of programming and a little magic, Anish crafts ML projects to help better serve our customers, turning “oh nos” to “a-ha”s!

Morgan McGuire

Morgan is a Growth Director and an ML Engineer at Weights & Biases. He has a background in NLP and previously worked at Facebook on the Safety team, where he helped classify and flag potentially high-severity content for removal.

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related LinksAI in Production Conference: https://home.mlops.community/home/events/ai-in-production-2024-02-15

Website: https://wandb.ai/

Prompt Templates the Song: https://www.youtube.com/watch?v=g6WT85gIsE8

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Morgan on LinkedIn: https://www.linkedin.com/in/morganmcg1/

Connect with Anish on LinkedIn: https://www.linkedin.com/in/anish-shah/

Alexandra Diem, PhD, has extensive experience in the field of AI, machine learning, and cloud analytics. Alexandra currently holds the position of Head of Cloud Analytics and MLOps at Gjensidige.

Large Language Models have taken the world by storm. But what are the real use cases? What are the challenges in productionizing them? In this event, you will hear from practitioners about how they are dealing with things such as cost optimization, latency requirements, trust of output, and debugging. You will also get the opportunity to join workshops that will teach you how to set up your use cases and skip over all the headaches.

Join the AI in Production Conference on February 22 here: https://home.mlops.community/home/events/ai-in-production-2024-02-15

_________________________________________________________

MLOps podcast #212 with Alexandra Diem, Head of Cloud Analytics & MLOps at Gjensidige, Data Governance and AI.

// Abstract

This recent session featuring the incredibly talented Alexandra Diem delves into the challenges of generative AI in sensitive data environments, the emergence of specialized chatbots, and data governance. Balancing high-tech projects with those offering significant business value, using agile methods, is also discussed. Alexandra's journey from academia to being a consultant in Norway is truly inspiring. The discussion explores the function of enabling and R&D in tech roles, the shift towards self-serve solutions, and the integration of AI into existing workflows. Stimulating conversations about future-oriented technologies married with sound data science and industry practices make this session a must-listen for anyone interested in machine learning operations!

// Bio

Former academic turned data scientist with a passion for data mesh architectures.🔬 Background in applied mathematics and statistics, adept at leveraging data-driven insights to solve complex problems. Experienced in diverse domains spanning the private and public sectors.🧠 Made significant contributions to research in physiological modeling, successfully debunking a leading biomedical hypothesis on Alzheimer's disease during my PhD. Developed innovative approaches to quantify blood supply to the heart.💡 Solution-oriented thinker with a track record of efficiently tackling challenging problems and adapting to novel scenarios.⚙️ Expertise: Data Science | Mathematical Modeling | Statistical Analysis | Problem Solving. In my spare time, you'll find me exploring the great outdoors—whether it's pedaling through scenic landscapes on a bike or riding down the slopes on a pair of skis.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related LinksAI in Production Conference: https://home.mlops.community/home/events/ai-in-production-2024-02-15

Website: https://github.com/alexdiem

Talk "DevOps revolutionised software engineering, it's time to revolutionise data" https://vimeo.com/861721829 from JavaZone 2023Zilliz Cloud: https://zilliz.com/

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Alexandra on LinkedIn: https://www.linkedin.com/in/dralexdiem/

Aayush Mudgal is a Senior Machine Learning Engineer at Pinterest, currently leading the efforts around Privacy-Aware Conversion Modeling.

Large Language Models have taken the world by storm. But what are the real use cases? What are the challenges in productionizing them? In this event, you will hear from practitioners about how they are dealing with things such as cost optimization, latency requirements, trust of output, and debugging. You will also get the opportunity to join workshops that will teach you how to set up your use cases and skip over all the headaches.

Join the AI in Production Conference on February 15 and 22 here: https://home.mlops.community/home/events/ai-in-production-2024-02-15

_________________________________________________________

MLOps podcast #211 with Aayush Mudgal, Senior Machine Learning Engineer at Pinterest, Ads Ranking Evolution at Pinterest.

// Abstract

Listen to the lessons from the journey of scaling ad ranking at Pinterest using innovative machine learning algorithms and innovation in the ML platform. Learn how they transitioned from traditional logistic regressions to deep learning-based transformer models, incorporating sequential signals, multi-task learning, and transfer learning. Discover the hurdles Pinterest overcame and the insights they gained in this talk, as Aayush shares the transformation of ad ranking at Pinterest and the lessons learned along the way. Discover how ML Platform evolution is crucial for algorithmic advancements.

// Bio

Aayush Mudgal is a Senior Machine Learning Engineer at Pinterest, currently leading the efforts around Privacy-Aware Conversion Modeling. He has a successful track record of starting and executing 0 to 1 projects, including conversion optimization, video ads ranking, landing page optimization, and evolving the ads ranking from GBDT to DNN stack. His expertise is in large-scale recommendation systems, personalization, and ad marketplaces. Before entering the industry, Aayush conducted research on intelligent tutoring systems, developing data-driven feedback to aid students in learning computer programming. He holds a Master's in Computer Science from Columbia University and a Bachelor of Technology in Computer Science from the Indian Institute of Technology Kanpur.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

https://www.youtube.com/watch?v=MZVIxtsGzBg https://www.youtube.com/watch?v=ffpPUr8Hg6U

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Aayush on LinkedIn: https://www.linkedin.com/in/aayushmudgal/

Timestamps:[00:00] Join the AI in Production Conference![02:10] Aayush preferred coffee[02:31] Takeaways[03:41] Evolving decision-making based on evolution and ROI[09:53] Companies have varying approaches to building[13:54] Continuous innovation and adaptation[17:13] Transform, train, and analyze data for effective predictions[21:01] Shift in traditional systems, monitoring, and visibility[22:36] Monitoring all pipelines, models, features, and predictions. Alerting[24:56] Maintain simplicity and optimize pipelines for scaling[28:40] Check if systems are ready for change[34:13] Commitment, tooling, and understanding are crucial for migration[36:30] Concerns about technology support and migration strategy[41:44] Difficulty removing hybrid systems, but speed benefit.[45:39] Recommendation models learn user-content interactions, transformer as a feature interaction layer[49:07] Optimize model complexity, control sequence length, and reduce costs[51:01] Pinterest uses Pytorch for training and complex serving[52:14] Wrap up

Large Language Models have taken the world by storm. But what are the real use cases? What are the challenges in productionizing them? In this event, you will hear from practitioners about how they are dealing with things such as cost optimization, latency requirements, trust of output, and debugging. You will also get the opportunity to join workshops that will teach you how to set up your use cases and skip over all the headaches.

Join the AI in Production Conference on February 15 and 22 here: https://home.mlops.community/home/events/ai-in-production-2024-02-15

_________________________________________________________

Aparna Dhinakaran is the Co-Founder and Chief Product Officer at Arize AI, a pioneer and early leader in machine learning (ML) observability.MLOps podcast #210 with Aparna Dhinakaran, Co-Founder and Chief Product Officer of Arize AI, LLM Evaluation with Arize AI's Aparna Dhinakaran.

// Abstract

Dive into the complexities of Language Model (LLM) evaluation, the role of the Phoenix evaluations library, and the importance of highly customized evaluations in software applications. The discourse delves into the nuances of fine-tuning in AI, the debate between the use of open-source versus private models, and the urgency of getting models into production for early identification of bottlenecks. Then, examine the relevance of retrieved information, output legitimacy, and the operational advantages of Phoenix in supporting LLM evaluations.

// Bio

Aparna Dhinakaran is the Co-Founder and Chief Product Officer at Arize AI, a pioneer and early leader in AI observability and LLM evaluation. A frequent speaker at top conferences and a thought leader in the space, Dhinakaran is a Forbes 30 Under 30 honoree. Before Arize, Dhinakaran was an ML engineer and leader at Uber, Apple, and TubeMogul (acquired by Adobe). During her time at Uber, she built several core ML Infrastructure platforms, including Michelangelo. She has a bachelor’s from Berkeley's Electrical Engineering and Computer Science program, where she published research with Berkeley's AI Research group. She is on a leave of absence from the Computer Vision Ph.D. program at Cornell University.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

Arize-Phoenix: https://phoenix.arize.com/

Phoenix LLM task eval library: https://docs.arize.com/phoenix/llm-evals/running-pre-tested-evals

Aparna's recent piece on LLM evaluation: https://arize.com/blog-course/llm-evaluation-the-definitive-guide/

Thread on the difference between model and task LLM evals: https://twitter.com/aparnadhinak/status/1752763354320404488

Research thread on why numeric score evals are broken: https://twitter.com/aparnadhinak/status/1748368364395721128

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Aparna on LinkedIn: https://www.linkedin.com/in/aparnadhinakaran/

Timestamps:[00:00] AI in Production Conference[02:12] Aparna preferred coffee[02:26] Takeaways[04:40] Shout out to Arize team for being a sponsor of the MLOps Community since 2020![05:30] Please like, share, & subscribe to our MLOps channels![08:23] Evaluation space[12:23] Chatbots Prevent Misinformation[18:48] Balancing eval response and impact on speed[26:16] GPT-4 excels, prompt iterations affect outcomes[31:28] Multiple sub-steps and requiring visibility on Application calls[37:43] Classification for evaluation Research[41:08] Benchmarks on Huggingface and Twitter reliability[44:19] Power of observability and retrieval embeddings[48:02] Tweaking data points[50:28] Hot take[53:35] Bottlenecks and errors from rapid production

Matt Bleifer is a Group Product Manager at Tecton, where he focuses on the core product experience, such as building, testing, and productionizing feature pipelines at scale.

Michael Eastham works as a Chief Architect at Tecton, which is a Business Intelligence (BI) Software company with an estimated 100 employees. Large Language Models have taken the world by storm. But what are the real use cases? What are the challenges in productionizing them? In this event, you will hear from practitioners about how they are dealing with things such as cost optimization, latency requirements, trust of output, and debugging. You will also get the opportunity to join workshops that will teach you how to set up your use cases and skip over all the headaches.

Join the AI in Production Conference on February 15 and 22 here: https://home.mlops.community/home/events/ai-in-production-2024-02-15

_________________________________________________________

MLOps podcast #209 with Tecton's Group Product Manager, Matt Bleifer, and Chief Architect, Mike Eastham, Powering MLOps: The Story of Tecton's Rift, brought to us by our Premium Brand Partner, Tecton.

// Abstract

Explore the intricacies of feature platforms and their integration in the data realm. Compare traditional predictive machine learning with the integration of Linguistic Model Systems into software applications. Get a glimpse of Rift, a product that enhances data processing with smooth compatibility with various technologies. Join in on the journey of developing Rift and making Tecton user-friendly, and enjoy Matt's insights and contributions. Wrap it up with lighthearted talks on future collaborations, music, and a touch of nostalgia.

// Bio

Matt Bleifer

Matt Bleifer is a Group Product Manager and an early employee at Tecton. He focuses on core product experiences such as building, testing, and productionizing feature pipelines at scale. Before joining Tecton, he was a Product Manager for Machine Learning at both Twitter and Workday, totaling nearly a decade of experience working on machine learning platforms. Matt has a Bachelor’s Degree in Computer Science from California Polytechnic State University, San Luis Obispo.

Michael Eastham

Michael Eastham is the Chief at Tecton. Previously, he was a software engineer at Google, working on Web Search.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

Website: https://www.tecton.ai/

Rift Article: https://www.tecton.ai/blog/unlocking-real-time-ai-for-everyone-with-tecton/

Rift: https://resources.tecton.ai/rift

Big Data is Dead blog: https://motherduck.com/blog/big-data-is-dead/

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Matt on LinkedIn: https://www.linkedin.com/in/mattbleifer/

Connect with Mike on LinkedIn: https://www.linkedin.com/in/mikeeastham/

Timestamps:

[00:00] AI in Production Conference

[02:13] Matt & Mike's preferred coffee

[02:37] Takeaways

[04:50] Matt & Mike's Tecton titles

[06:49] Matt's background in tech

[09:49] Mike's background in tech

[12:53] Tecton refresher

[18:23] Feature store to Feature platform

[21:06] Current evolution of Tecton

[24:41] The understatement

[26:12] Duck DB Con

[27:54] Rift

[30:10] Kafka Flink

[33:36] What is large in aggregations?

[38:09] Big Data is Dead!

[41:14] Principles of creating Rift

[45:54] The battle between Simplicity and Flexibility

[47:28] Is he serious? Segment

[50:54] Can you get any more hype Segment

[57:10] What are you excited about?

[1:02:45] Wrap up

Join our virtual conference 'AI in Production'

Transform faster. Innovate smarter. Anticipate the future. At QuantumBlack, we unlock the power of artificial intelligence (AI) to help organizations reinvent themselves from the ground up—and accelerate sustainable and inclusive growth.

MLOps Coffee Sessions Special episode with QuantumBlack, AI by McKinsey, GenAI Buy vs Build, Commercial vs Open Source, fueled by our Premium Brand Partner, QuantumBlack, AI by McKinsey.

Jon Cooke is the owner/founder of Dataception, a Data, Analytics, and Data Product company, and the creator of the Data Product Pyramid, an adaptive Data Product operating model.

MLOps podcast #208 with Jon Cooke, CTO of Dataception, Micro Graph Transformer - Specialist Small Language Models Using Graphs to Accelerate Data Product Eco-systems.

// Abstract

Specialist deconstructed Encoder/Decoder Transformers along with data product management and tech to vastly accelerate prototyping, building, and deploying business-facing data products at high speed and low cost.

// Bio

Jon is a 20-year veteran in Data, Analytics, and AI, and is a Data product specialist. After seeing the massive time, friction, failures, and costs typically associated with data and analytics initiatives, Jon founded Dataception. Its mission is to use tech to eliminate the data grunt and work together with data product management and AI to build and iterate sophisticated, business-facing analytics in real-time in front of the business.

// MLOps

Jobs board

https://mlops.pallet.xyz/jobs

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

AI in Production Conference: https://home.mlops.community/public/events/ai-in-production-2024-02-15

Website: www.dataception.com

https://www.linkedin.com/events/generativeai-dataproductsandbus7114951387100184576/theater/https://www.linkedin.com/events/12thevalueofadataproductmanagem7110920848416366594/comments/https://www.linkedin.com/events/howtoactuallyusedataproductstod7113570339535638528/theater/

Building Better Data Teams // Leanne Fitzpatrick // Coffee Sessions #113: https://www.youtube.com/watch?v=JxVS3-4wyKc

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Jon on LinkedIn: https://www.linkedin.com/in/jon-cooke-096bb0/

Timestamps:

[00:00] AI in Production Conference teaser

[02:12] Jon's preferred coffee

[02:24] Takeaways

[03:48] Please like, share, and subscribe to our MLOps channels!

[04:02] Backpacking, traveling, and almost cast for Lord of the Rings

[06:40] Jon's tech background

[11:07] Dataception

[15:05] Data Challenges: Delays & Causes

[16:46] Data Virtualization for Agility

[19:47] Large Company Change Challenges

[21:28] Sales Tools Migration Challenges

[24:44] Data and ML Integration

[28:13] Data Roles Evolution

[32:20] Tech for Prototyping Acceleration

[35:22] LLM Enables Natural Language Data Analytics

[36:36] Ensuring Reliable AI Information

[38:20] Proxy Routing and Intelligent Agents

[42:41] Human API for Data

[46:49] Engineer Success with Growth

[48:15] Tech CEO Balancing Act

[53:59] Iterative Development for Product-Market Fit

[56:16] Wrap up

Jake Watson is the writer of thedataplatform.substack.com⁠ and Principal Data Engineer at The Oakland Group.

MLOps podcast #207 with Jake Watson, Principal Data Engineer at The Oakland Group, How Data Platforms Affect ML & AI.

// Abstract

I’ve always told my clients and colleagues that traditional rule-based software is difficult, but software containing Artificial Intelligence (AI) and/or Machine Learning (ML)* is even more difficult, sometimes impossible.

Why is this the case? Well, software is difficult because it’s like flying a plane while building it at the same time, but because AI and ML make rules on the fly based on various factors like training data, it’s like trying to build a plane in flight, but some parts of the plane will be designed by a machine, and you have little idea what that is going to look like till the machine finishes.

This double goes for more cutting-edge AI models like GPT, where only the creators of the software have a vague idea of what it will output.

This makes software with AI / ML more of a scientific experiment than engineering, which is going to make your project manager lose their mind when you have little idea how long a task is going to take.

But what will make everyone’s lives easier is having solid data foundations to work from. Learn to walk before running.

// Bio

Jake has been working in data as an Analyst, Engineer, and/or Architect for over 10 years. Started as an analyst in the UK National Health Service, converting spreadsheets to databases tracking surgical instruments. Then continued as an analyst at a consultancy (Capita), reporting on employee engagement in the NHS and dozens of UK Universities. There, Jake moved reporting from Excel and Access to SQL Server, Python with frontend websites in d3.js. At Oakland Group, a data consultancy, Jake worked as a Cloud Engineer, Data Engineer, Tech Lead, and Architect depending on the project for dozens of clients, both big and small (mostly big). Jake has also developed and productionised ML solutions as well in the NLP and classification space.

Jake has experience in building Data Platforms in Azure, AWS, and GCP (though mostly in Azure and AWS) using Infrastructure as Code and DevOps/DataOps/MLOps. In the last year, Jake has been writing articles and newsletters for my blog, including a guide on how to build a data platform: https://thedataplatform.substack.com/p/how-to-build-a-data-platform

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

Website: https://thedataplatform.substack.com/

How Data Platform Foundations Impact AI and ML Applications blog: https://thedataplatform.substack.com/p/issue-29-how-data-platform-foundations

AI in Production Conference: https://home.mlops.community/public/events/ai-in-production-2024-02-15

How to Build a Data Platform blog: https://thedataplatform.substack.com/p/how-to-build-a-data-platform

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Jake on LinkedIn: https://www.linkedin.com/in/jake-watson-data/

Timestamps:

[00:00] Jake's preferred coffee

[00:26] AI in Production Conference teaser

[02:38] Takeaways

[04:00] Please like, share, and subscribe to our MLOps channels!

[04:17] Data Engineer's Crucial Role

[05:44] Jake's background

[06:44] Data Platform Foundations blog

[10:34] Data mesh organizational side of things

[17:58] Importance of data modeling

[20:13] Dealing with the sprawl

[22:03] Data quality

[23:59] Data hierarchy on building a platform

[29:34] ML Platform Team Structure

[31:47] Don't reinvent the wheel

[34:04] Data pipelines synergy

[37:31] Wrap up

Yujian is working as a Developer Advocate at Zilliz, where they develop and write tutorials for proof of concepts for large language model applications. They also give talks on vector databases, LLM Apps, semantic search, and tangential spaces.

MLOps podcast #206 with Yujian Tang, Developer Advocate at Zilliz, RAG Has Been Oversimplified, brought to us by our Premium Brand Partner, Zilliz

// Abstract

In the world of development, Retrieval Augmented Generation (RAG) has often been oversimplified. Despite the industry's push, the practical application of RAG reveals complexities beyond its apparent simplicity. This talk delves into the nuanced challenges and considerations developers encounter when working with RAG, providing a candid exploration of the intricacies often overlooked in the broader narrative.

// Bio

Yujian Tang is a Developer Advocate at Zilliz. He has a background as a software engineer working on AutoML at Amazon. Yujian studied Computer Science, Statistics, and Neuroscience with research papers published at conferences, including IEEE Big Data. He enjoys drinking bubble tea, spending time with family, and being near water.

// MLOps Jobs board

jobs.mlops.community

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

Website: zilliz.com

--------------- ✌️Connect With Us ✌️ -------------

Join our Slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Yujian on LinkedIn: https://linkedin.com/in/yujiantang

Timestamps:

[00:00] Yujian's preferred coffee

[00:17] Takeaways

[02:42] Please like, share, and subscribe to our MLOps channels!

[02:55] The hero of the LLM space

[05:42] Embeddings into Vector databases

[09:15] What is large and what is small LLM consensus

[10:10] QA Bot behind the scenes

[13:59] Fun fact: getting more context

[17:05] RAGs eliminate the ability of LLMs to hallucinate[18:50] Critical part of the rag stack

[19:57] Building citations

[20:48] Difference between context and relevance

[26:11] Missing prompt tooling

[27:46] Similarity search

[29:54] RAG Optimization

[33:03] Interacting with LLMs and tradeoffs

[35:22] RAGs are not suited for

[39:33] Fashion App

[42:43] Multimodel Rags vs LLM RAGs

[44:18] Multimodel use cases

[46:50] Video citations

[47:31] Wrap up