MLOps.community

QuantumBlack and McKinsey discuss the trade-offs of buying vs building GenAI solutions, including considerations of black box solutions and transparency. They explore the roles of traditional AI and JAN-AI in messaging channels and the generative nature of AI. The challenges and considerations in using APIs for machine learning models are also discussed.

Jon Cooke, founder of Dataception and creator of the Data Product Pyramid, discusses using specialist small language models and graphs to accelerate data product ecosystems. Topics include deconstructed Encoder/Decoder Transformers, data product management, tech to eliminate data grunt work, and building sophisticated analytics in real-time.

Jake Watson, Principal Data Engineer at The Oakland Group, discusses the challenges and importance of data platforms for ML & AI projects. Topics include data engineering, real-time data updates, data modeling, scalability of ML pipelines, and the role of data platforms in the future.

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 to conferences including IEEE Big Data. He enjoys drinking bubble tea, spending time with family, and being near water. // MLOps Jobs board https://mlops.pallet.xyz/jobs // 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: 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 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

Jonathan Frankle, Chief Scientist at Databricks, discusses the realities and usefulness of AI, including face recognition systems, the 'lottery ticket hypothesis,' and robust decision-making protocols for training models. They also explore Jonathan's move into law, his experience with GPUs, and the revolutionary algorithm called Qstar.

Guests Patrick Barker, Founder / CTO of Kentauros AI and Farhood Etaati, Software Engineer at Yektanet, discuss the challenges and skepticism surrounding MLOps and its relation to previous ML models. They explore the potential future developments, the significance of knowledge transfer, and the emergence of persona-specific tools. The speakers also mention building a tool for TypeScript developers and discuss the challenges faced by MLOps engineers.

Aleksa Gordić, ex-Google DeepMind/Microsoft ML engineer, discusses pioneering AI models for regional languages, focusing on the development of YugoGPT. They explore unique language dynamics in the Balkans, business opportunities for multilingual models, and challenges in deploying large language models. The conversation delves into Aleksa's experience with vision and image models, collaborations with tech players, and use of advanced technologies. They also discuss open sourcing models, the lack of language support, and advantages/limitations of working for a company.

Navigate data management intricacies with Hannes Mühleisen and Jordan Tigani, the creators of DuckDB and MotherDuck. They discuss the controversial 'hallucinate' shirt, the origins of DuckDB and Oracle, CSV reading in data systems, addressing pain points, embracing community feedback, and the unique features and potential of DuckDB

Paco Nathan, Managing Partner at Derwen, Inc., talks about key findings from conferences, commonalities among teams with ROI on ML in production, leveraging existing resources and domain expertise in AI, the importance of software engineering and ops in AI, and the need to regulate AGI and implement universal basic income.

Guest Mihail Eric, co-founder of Storia AI, discusses the significance of human sentiment in an AI-driven era. They explore the evolution and impact of image generation models, the challenges of MLOps, and the importance of developer-friendly APIs. They also discuss fundraising struggles, the need for solid foundations in image generation, and the vision of creating generalized building blocks for different industries.