Loading…
or to bookmark your favorites and sync them to your phone or calendar.
strong>AI & ML (CloudX) [clear filter]
Wednesday, November 6
 

9:30am PST

PRO SESSION (CloudX): Challenges and Takeaways of Managing AI Workloads on Cloud Environments
Wednesday November 6, 2024 9:30am - 9:55am PST
Graziano Casto, Mia-Platform, Developer Relations

In today's technological landscape, the synergy between Cloud Native technologies and Artificial Intelligence (AI) opens the stage to a myriad of unexplored challenges and opportunities. Dynamic, always-on and highly scalable infrastructures, typical of the Cloud Native paradigm, seamlessly integrate with AI's need to rapidly prototype solutions and access vast computational resources. The convergence of these two worlds has exposed some gaps in the Cloud Native ecosystem that need to be addressed. At the same time, AI opens numerous opportunities for innovation that are yet to be explored.
This talk will delve into the Cloud Native Artificial Intelligence (CNAI) paradigm as a holistic approach to unlocking the full potential of the cloud in managing AI workloads and aim to anticipate the growth opportunities that lie ahead for the Cloud Native world.
Speakers
avatar for Graziano Casto

Graziano Casto

Developer Relations Engineer, Mia-Platform
Graziano is a software engineer and passionate about agile development and product management. Formerly a developer of distributed systems in enterprise environments and a product manager, he focuses on sharing the myriad beauties of the cloud-native world. Active in international... Read More →
Wednesday November 6, 2024 9:30am - 9:55am PST
CloudX -- Stage 1

11:30am PST

OPEN SESSION (CloudX): Fast-Track Your AI App Deployment with GitHub and Azure
Wednesday November 6, 2024 11:30am - 11:55am PST
Gabriela de Queiroz, Microsoft, Director of AI

Discover how effortless it is to kickstart your AI app journey with GitHub and Azure. In this session, Gabriela de Queiroz, will demonstrate the power of starting with a GitHub repository from the Azure AI app template gallery. Participants will see the process unfold, beginning with GitHub Codespaces and a model from the GitHub Models catalog. Once the app is running smoothly locally, Gabriela will guide you through deploying it to Azure using the Azure Developer CLI. Plus, see how GitHub Copilot for Azure can simplify every step of your deployment process, answering all your questions along the way. 
Speakers
avatar for Gabriela de Queiroz

Gabriela de Queiroz

Director of AI, Microsoft
Gabriela de Queiroz is the Director of AI at Microsoft, where she provides strategic guidance to both early and growth-stage startups, helping them harness the full capabilities of AI and Microsoft’s products.Prior to joining Microsoft, Gabriela held significant positions at IBM... Read More →
Wednesday November 6, 2024 11:30am - 11:55am PST
CloudX -- Expo Innovation Stage
  OPEN SESSIONS, CloudX

1:30pm PST

KEYNOTE (CLOUDX): CloudZero -- Streamlining the Digital Factory: Lean Cloud Computing for Next-Gen Software Development
Wednesday November 6, 2024 1:30pm - 1:55pm PST
Erik Peterson, CloudZero, CTO & Founder

The cloud-centric world has turned every line of code into a buying decision and highlighted the economic aspects of software design. After first struggling with the ramifications of this, (and a meager $3000.00 budget on my first cloud project in 2009) I discovered how cloud economics presented an opportunity to merge efficiency concepts taken from classic manufacturing with modern software engineering and architecture.

Since that time we have seen an industry wide focus on cloud cost management and new practices like FinOps emerge, but few have explored how to apply cloud economics directly to modern DevOps practices resulting in million dollar lines of code and unprofitable system design that has soured some on cloud computing as a whole. My experience however has been very different. I will share the lessons I've learned over the last 15 years treating cost as a key non-functional requirement during development.

By integrating the Theory of Constraints, Lean Manufacturing, and unit economics, alongside cloud cost efficiency goals and performance as crucial inputs, I will share a strategy that fosters continuous improvement and boosts profitability under current consumption-based cloud pricing models. This approach ensures an economical path from concept to deployment, and ongoing operations, without compromising innovation and time-to-market.
Speakers
avatar for Erik Peterson

Erik Peterson

CTO & Founder, CloudZero
Erik Peterson is the Founder and CTO of CloudZero and a pioneer in engineering-led cost optimization and unit economics. He has been building in the cloud since its arrival and has over two decades of software startup experience, with a passion for cost-efficient engineering and excellent... Read More →
Wednesday November 6, 2024 1:30pm - 1:55pm PST
CloudX -- Main Stage

2:00pm PST

OPEN SESSION (CloudX): APIs for Data: How to Build Data-Intensive Cloud Applications with Snowflake and Large Language Models
Wednesday November 6, 2024 2:00pm - 2:25pm PST
Daniel Myers, Snowflake, Director of Developer RelationsAPIs for data - do you start with the data model or the API model? Learn best practices and how to build data-intensive applications on Snowflake and large language models (LLMs). In this session, you’ll learn different API architectural patterns, including Connected Apps and Snowflake Native Apps. Daniel will demonstrate how to develop, deploy, and run applications directly on Snowflake.

Speakers
avatar for Daniel Myers

Daniel Myers

Director of Developer Relations, Snowflake
With cross-functional experience in software engineering, product management, and business development, Daniel is the Director of Developer Relations at Snowflake. Daniel leads global, cross-functional teams in software development and customer adoption, with a focus on bottom-up... Read More →
Wednesday November 6, 2024 2:00pm - 2:25pm PST
CloudX -- Expo Innovation Stage

4:00pm PST

OPEN SESSION (CloudX): Is Your Engineering Org Really Prepared for the GenAI Revolution?!
Wednesday November 6, 2024 4:00pm - 4:25pm PST
Yishai Beeri, LinearB, CTO

GenAI has gone from generally available, novel technology to widely adopted in a matter of months. Most engineering organizations are using GenAI to generate code, write tests, and assist in code reviews. New code is becoming dirt cheap to write - but our delivery pipelines remain miserably unprepared for the tsunami of new code flowing at a much more rapid pace.

Our current pipelines need a hard reset to prepare us for the GenAI revolution - and engineering managers need to get started TODAY.

This talk will dive into where GenAI is starting to break down our delivery pipelines. While scaling CI/CD is easy, and we can always add a few more workers, scaling the humans in the process is the hard part. This talk will demonstrate how massive amounts of new machine-generated code will impact our pipelines, in ways that will require either greater headcount, or smarter, automated pipelines. You'll come away with ideas for how to modernize your delivery pipeline so you can fully embrace the GenAI revolution.
Speakers
avatar for Yishai Beeri

Yishai Beeri

CTO, LinearB
Yishai Beeri likes to solve problems, and that’s why he was so fascinated with programming when first encountered Logo back in the 80s, where the possibilities seemed endless.He has made it a focus of his career to solve complex programming problems, both as a consultant and entrepreneur... Read More →
Wednesday November 6, 2024 4:00pm - 4:25pm PST
CloudX -- Main Stage
 
Thursday, November 7
 

9:30am PST

PRO SESSION (CloudX): Navigating the Ethical Terrain of AI-Enhanced Marketing Automation: Strategies for Responsible Innov
Thursday November 7, 2024 9:30am - 9:55am PST
Sravan Yella, Hewlett Packard, Lead Solutions Engineer

The integration of Artificial Intelligence (AI) in marketing, particularly through social media, presents profound opportunities and ethical challenges that demand careful consideration. As AI technologies like Machine Learning (ML), Natural Language Processing (NLP), and predictive analytics become central to marketing strategies, they facilitate unparalleled personalization and efficiency in analyzing vast datasets and optimizing marketing efforts. Despite these advancements enhancing customer engagement by 40% and reducing operational costs by 30%, the rapid proliferation of AI tools in marketing raises significant ethical concerns. Key issues include the potential for data privacy breaches, the accuracy and bias in AI algorithms, and the lack of transparency in AI-driven decisions. These challenges not only affect consumer trust, which has seen a decline of 20% in brands using AI indiscriminately but also pose risks to brand integrity and compliance with evolving regulatory frameworks. To navigate this landscape responsibly, this presentation will explore best practices and frameworks for ethical AI usage in marketing. We will discuss the implementation of rigorous data governance protocols that ensure user data protection and privacy, techniques for auditing and mitigating biases in AI models to boost decision transparency, and strategies for maintaining compliance with international data use regulations. By fostering an ethical AI deployment approach, companies can enhance customer satisfaction by 25% and improve brand loyalty. This talk aims to equip professionals with actionable insights to leverage AI in marketing ethically and sustainably, ensuring long-term business success and consumer trust.

This abstract emphasizes the balance between leveraging AI's capabilities and addressing ethical considerations, backed by relevant data points to enhance its appeal to conference reviewers.
 
Speakers
avatar for Sravan Yella

Sravan Yella

Lead Solutions Engineer, Hewlett Packard
Sravan Yella is an expert CRM Engineering Leader with extensive experience in leveraging exponential backoff strategies to enhance the robustness and efficiency of distributed systems. His strategic implementations have significantly reduced downtime and improved system response in... Read More →
Thursday November 7, 2024 9:30am - 9:55am PST
CloudX -- Stage 1

10:00am PST

OPEN SESSION (API): Unlocking Live Data Access for AI
Thursday November 7, 2024 10:00am - 10:25am PST
Anushrut Gupta, Hasura, Senior Product Manager, Generative AI

“Over the last 3 months, summarize the top billing issues faced by my enterprise customers within the first 30 days of their onboarding.”

On the surface, building an internal AI customer intelligence application that can answer questions like this is a perfect use-case for Gen AI.
However, building a production ready app that retrieves the data (RAG) before hauling it off to your favorite LLM for summarization soon becomes a terrible engineering experience.

The data is spread across 3 places: a tickets database (eg: elastic), a CRM (eg: salesforce) and your user-accounts transactional database (eg: postgres).
In production, your app can’t access the data from these databases directly. Given security & privacy concerns, your app won’t have direct access to these databases.
Making independent retrieval requests to each of these sources and then joining them in memory might be prohibitively expensive and needs a level of query planning to do efficiently.
Moving all data into one location is expensive to build, maintain and govern
Predictable quality is further made hard because underlying data formats and storage interfaces are continuously changing.
Different types of user queries might require additional filtering and joining of data, which becomes hard to generalize.

APIs solve almost all of these very well known challenges. APIs offer standardization and security. APIs can provide a stable contract to interact with underlying data.

And in all likelihood, you already have APIs on these internal and external data sources.

Ironically, while APIs have become a necessity for other parts of the stack, they are clearly not the first thing that AI engineers building RAG reach for.

In this talk, we’ll discuss:
Why API based retrieval doesn’t work well for RAG
What we need from our existing internal and external APIs to make them RAG ready
How we can get existing APIs to become RAG ready without needing to rebuild the APIs

This talk will be technical, with code demos (possibly with some live coding!) and end with key resources (reference architectures, API best practices, tools/technologies) that attendees can take back to their work.
Speakers
avatar for Anushrut Gupta

Anushrut Gupta

Senior Product Manager, Generative AI, Hasura
Thursday November 7, 2024 10:00am - 10:25am PST
API World -- OPEN Workshop Stage

11:00am PST

OPEN SESSION (CloudX): Responsible AI and Security in the Generative Era: Science and Practice
Thursday November 7, 2024 11:00am - 11:25am PST
Ishneet Dua, Amazon Web Services, Senior Generative AI Solutions Architect
Parth Girish Patel, Amazon Web Services, Sr AI/ML Architect


The rapid growth of generative AI brings promising innovation and, at the same time, raises new challenges around its security, safe, and responsible development and use. These challenges include some that were common before generative AI, such as bias and explainability, and new ones unique to generative models, including hallucinations, toxicity, and intellectual property protection. During this session, participants will gain an overview of the challenges that generative AI presents, survey the emerging science surrounding these challenges, and engage in a discussion about the hands-on, security, and Responsible AI work currently being conducted on AWS.
Speakers
avatar for Ishneet Dua

Ishneet Dua

Senior Generative AI Solutions Architect, Amazon Web Services
Ishneet Dua (Isha) is a recognized expert in leveraging AI and machine learning for sustainability solutions. She has established herself as a go-to authority on combating climate change, pollution, and other environmental challenges through cutting-edge technologies.Dua has authored... Read More →
avatar for Parth Girish Patel

Parth Girish Patel

Sr AI/ML Architect, AWS
Parth Girish Patel is a seasoned architect with a wealth of experience spanning over 17 years, encompassing management consulting and cloud computing. Currently, at Amazon Web Services (AWS), he specializes in Artificial Intelligence/Machine Learning, generative AI, sustainability... Read More →
Thursday November 7, 2024 11:00am - 11:25am PST
CloudX -- Main Stage

1:30pm PST

OPEN SESSION (CloudX): Unlocking the Promise of AIOps: Leveraging AI to Realize Full-Context Operations
Thursday November 7, 2024 1:30pm - 1:55pm PST
Fred Koopmans, BigPanda, Chief Product Officer

Context is fundamental to well-run tech operations: With the right context, IT teams can better understand their systems, interpret real-time data quickly, and facilitate better incident management to achieve operational efficiency. But too often, gathering the necessary context is a lengthy, inconsistent, and elusive process. IT teams are forced to grapple with fragmented tools, siloed workflows, and inconsistent manual processes, which have turned context collection into a definitive pain point for the ITOps industry. Teams are losing out on precious time, money, and attention that should be directed towards digital transformation and innovation.

The tech industry has recently transformed thanks to the AI boom: ITOps is at a critical juncture where AI can enable faster, more efficient ITOps as well as deliver Full-Context Operations. Fred Koopmans, Chief Product Officer of AIOps platform BigPanda, will speak to the promise of Full-Context Operations – the process of unifying IT teams’ tools and processes with AI to provide the institutional knowledge needed to address every incident immediately. He’ll dive deep into the ways that teams can tangibly benefit from having the right context, outlining how the IT industry can leverage AI to collect comprehensive and contextual data to help operators achieve better incident resolution. Fred can share detailed proof points from developing BigPanda’s AI-powered assistant that was purpose-built for delivering full context in IT operations. With Full-Context Operations, the IT industry can finally fulfill the long-sought-after promise of AIOps, putting AI into practice to deliver unprecedented operational efficiency.
Speakers
avatar for Fred Koopmans

Fred Koopmans

Chief Product Officer, BigPanda
Fred Koopmans, BigPanda's Chief Product Officer, is dedicated to driving innovation and collaboration, building trusted partnerships with customers, creating product roadmaps, and empowering individuals to achieve the extraordinary. He leads product strategy, product management, product... Read More →
Thursday November 7, 2024 1:30pm - 1:55pm PST
CloudX -- Main Stage
 
Wednesday, November 13
 

9:30am PST

[Virtual] PRO SESSION (CloudX): Challenges and Takeaways of Managing AI Workloads on Cloud Environments
Wednesday November 13, 2024 9:30am - 9:55am PST
Graziano Casto, Mia-Platform, Developer Relations

In today's technological landscape, the synergy between Cloud Native technologies and Artificial Intelligence (AI) opens the stage to a myriad of unexplored challenges and opportunities. Dynamic, always-on and highly scalable infrastructures, typical of the Cloud Native paradigm, seamlessly integrate with AI's need to rapidly prototype solutions and access vast computational resources. The convergence of these two worlds has exposed some gaps in the Cloud Native ecosystem that need to be addressed. At the same time, AI opens numerous opportunities for innovation that are yet to be explored.
This talk will delve into the Cloud Native Artificial Intelligence (CNAI) paradigm as a holistic approach to unlocking the full potential of the cloud in managing AI workloads and aim to anticipate the growth opportunities that lie ahead for the Cloud Native world.
Speakers
avatar for Graziano Casto

Graziano Casto

Developer Relations Engineer, Mia-Platform
Graziano is a software engineer and passionate about agile development and product management. Formerly a developer of distributed systems in enterprise environments and a product manager, he focuses on sharing the myriad beauties of the cloud-native world. Active in international... Read More →
Wednesday November 13, 2024 9:30am - 9:55am PST
VIRTUAL CloudX -- Stage 1

10:30am PST

[Virtual] OPEN SESSION (CloudX): Is Your Engineering Org Really Prepared for the GenAI Revolution?!
Wednesday November 13, 2024 10:30am - 10:55am PST
Yishai Beeri, LinearB, CTO

GenAI has gone from generally available, novel technology to widely adopted in a matter of months. Most engineering organizations are using GenAI to generate code, write tests, and assist in code reviews. New code is becoming dirt cheap to write - but our delivery pipelines remain miserably unprepared for the tsunami of new code flowing at a much more rapid pace.

Our current pipelines need a hard reset to prepare us for the GenAI revolution - and engineering managers need to get started TODAY.

This talk will dive into where GenAI is starting to break down our delivery pipelines. While scaling CI/CD is easy, and we can always add a few more workers, scaling the humans in the process is the hard part. This talk will demonstrate how massive amounts of new machine-generated code will impact our pipelines, in ways that will require either greater headcount, or smarter, automated pipelines. You'll come away with ideas for how to modernize your delivery pipeline so you can fully embrace the GenAI revolution.
Speakers
avatar for Yishai Beeri

Yishai Beeri

CTO, LinearB
Yishai Beeri likes to solve problems, and that’s why he was so fascinated with programming when first encountered Logo back in the 80s, where the possibilities seemed endless.He has made it a focus of his career to solve complex programming problems, both as a consultant and entrepreneur... Read More →
Wednesday November 13, 2024 10:30am - 10:55am PST
VIRTUAL CloudX -- Stage 1

11:30am PST

[Virtual] OPEN SESSION (CloudX): The Future of AI Is Already Here
Wednesday November 13, 2024 11:30am - 11:55am PST
Marco Casalaina, Microsoft, Vice President of Products, Azure AI

This session will discuss the new and revolutionary changes that you're about to see in AI - and how many of them are available for you to try now. We'll look at how AI is becoming ubiquitous, multimodal, multilingual, and autonomous, and how it will change our lives and our businesses.
This session will cover:
  1. Incredible advances in multilingual AI
  2. How Copilot (and every AI) are grounded to data, and how we do it in Azure OpenAI
  3. Responsible AI, including evaluation for correctness, and real time content safety
  4. The rise of AI Agents, and how AI is going to move from question-answering to taking action
Speakers
avatar for Marco Casalaina

Marco Casalaina

Vice President of Products, Azure AI, Microsoft
Marco Casalaina is VP Products of Azure AI and AI Futurist at Microsoft. He leads the AI Futures team, which finds trends and develops products that will lead to the next generation of AI. He has previously led a number of teams across Azure AI, including Azure OpenAI, Vision, Speech... Read More →
Wednesday November 13, 2024 11:30am - 11:55am PST
VIRTUAL CloudX -- Expo Innovation Stage

12:30pm PST

[Virtual Exclusive] PRO SESSION (CloudX): AI-Enhanced Dev Innovation: Shaping the Future of Cloud-Native Development
Wednesday November 13, 2024 12:30pm - 12:55pm PST
Dileep Kumar Pandiya, ZoomInfo, Principal Engineer

Explore how AI is transforming development practices in cloud-native environments. Highlight innovative tools, frameworks, and methodologies that incorporate AI to enhance developer productivity and software quality. 
Speakers
avatar for Dileep Kumar Pandiya

Dileep Kumar Pandiya

Principal Engineer, ZoomInfo
Technology Leader with expertise in scaling digital businesses and navigating complex digital transformations has been pivotal in the success of numerous high-profile projects. Dileep dedicates himself to staying ahead of industry trends and utilizes his skills to create robust, scalable... Read More →
Wednesday November 13, 2024 12:30pm - 12:55pm PST
VIRTUAL CloudX -- Stage 1

1:30pm PST

[Virtual] KEYNOTE (CLOUDX): CloudZero -- Streamlining the Digital Factory: Lean Cloud Computing for Next-Gen Software Development
Wednesday November 13, 2024 1:30pm - 1:55pm PST
Erik Peterson, CloudZero, CTO & Founder

The cloud-centric world has turned every line of code into a buying decision and highlighted the economic aspects of software design. After first struggling with the ramifications of this, (and a meager $3000.00 budget on my first cloud project in 2009) I discovered how cloud economics presented an opportunity to merge efficiency concepts taken from classic manufacturing with modern software engineering and architecture.

Since that time we have seen an industry wide focus on cloud cost management and new practices like FinOps emerge, but few have explored how to apply cloud economics directly to modern DevOps practices resulting in million dollar lines of code and unprofitable system design that has soured some on cloud computing as a whole. My experience however has been very different. I will share the lessons I've learned over the last 15 years treating cost as a key non-functional requirement during development.

By integrating the Theory of Constraints, Lean Manufacturing, and unit economics, alongside cloud cost efficiency goals and performance as crucial inputs, I will share a strategy that fosters continuous improvement and boosts profitability under current consumption-based cloud pricing models. This approach ensures an economical path from concept to deployment, and ongoing operations, without compromising innovation and time-to-market.
Speakers
avatar for Erik Peterson

Erik Peterson

CTO & Founder, CloudZero
Erik Peterson is the Founder and CTO of CloudZero and a pioneer in engineering-led cost optimization and unit economics. He has been building in the cloud since its arrival and has over two decades of software startup experience, with a passion for cost-efficient engineering and excellent... Read More →
Wednesday November 13, 2024 1:30pm - 1:55pm PST
VIRTUAL CloudX -- Main Stage

2:00pm PST

[Virtual] OPEN SESSION (CloudX): Crafting Realities: The Role of Synthetic Data in AI Training
Wednesday November 13, 2024 2:00pm - 2:25pm PST
Arpit Shrivastava, Meta, Product Leader

Problem: The challenge at the heart of this presentation is the efficient training of AI models in scenarios where real-world data is limited, sensitive, or expensive to acquire. This issue is particularly pressing in fields such as autonomous vehicle development and medical research, where the quality and diversity of training data directly influence the performance and reliability of AI systems. Addressing this problem is crucial for advancing AI capabilities while ensuring ethical standards and privacy are upheld.

Methodology: To tackle this challenge, our approach involves the creation and use of synthetic data. The methodology encompasses techniques for generating high-fidelity, diverse synthetic datasets that mimic real-world complexities without compromising privacy or incurring high costs. Key techniques include Generative Adversarial Networks (GANs), simulation-based synthesis, and rule-based data generation. The presentation will detail these methods, along with strategies for validating the realism and utility of synthetic data in training robust AI models.

Conclusions: Preliminary results demonstrate that synthetic data can significantly enhance AI model training, especially in constrained environments. By leveraging synthetic datasets, we've observed improvements in model accuracy, robustness, and generalizability across several applications. The presentation will outline these findings, showcasing examples where synthetic data has successfully bridged the gap between the data needs of AI systems and the limitations of real-world datasets.
Speakers
avatar for Arpit Shrivastava

Arpit Shrivastava

Product Leader, Meta
Customer Obsessed Product Leader with a proven track record at tech giants like Meta and Cisco Systems, where I've led the charge in product innovation and managed multi-billion dollar portfolios. My expertise lies in driving Machine Learning-focused product strategies and spearheading... Read More →
Wednesday November 13, 2024 2:00pm - 2:25pm PST
VIRTUAL CloudX -- Main Stage

2:00pm PST

[Virtual] OPEN SESSION (CloudX): APIs for Data: How to Build Data-Intensive Cloud Applications with Snowflake and Large Language Models
Wednesday November 13, 2024 2:00pm - 2:25pm PST
Daniel Myers, Snowflake, Director of Developer RelationsAPIs for data - do you start with the data model or the API model? Learn best practices and how to build data-intensive applications on Snowflake and large language models (LLMs). In this session, you’ll learn different API architectural patterns, including Connected Apps and Snowflake Native Apps. Daniel will demonstrate how to develop, deploy, and run applications directly on Snowflake.

Speakers
avatar for Daniel Myers

Daniel Myers

Director of Developer Relations, Snowflake
With cross-functional experience in software engineering, product management, and business development, Daniel is the Director of Developer Relations at Snowflake. Daniel leads global, cross-functional teams in software development and customer adoption, with a focus on bottom-up... Read More →
Wednesday November 13, 2024 2:00pm - 2:25pm PST
VIRTUAL CloudX -- Expo Innovation Stage
 
Thursday, November 14
 

10:00am PST

[Virtual] OPEN SESSION (API): Unlocking Live Data Access for AI
Thursday November 14, 2024 10:00am - 10:25am PST
Anushrut Gupta, Hasura, Senior Product Manager, Generative AI

“Over the last 3 months, summarize the top billing issues faced by my enterprise customers within the first 30 days of their onboarding.”

On the surface, building an internal AI customer intelligence application that can answer questions like this is a perfect use-case for Gen AI.
However, building a production ready app that retrieves the data (RAG) before hauling it off to your favorite LLM for summarization soon becomes a terrible engineering experience.

The data is spread across 3 places: a tickets database (eg: elastic), a CRM (eg: salesforce) and your user-accounts transactional database (eg: postgres).
In production, your app can’t access the data from these databases directly. Given security & privacy concerns, your app won’t have direct access to these databases.
Making independent retrieval requests to each of these sources and then joining them in memory might be prohibitively expensive and needs a level of query planning to do efficiently.
Moving all data into one location is expensive to build, maintain and govern
Predictable quality is further made hard because underlying data formats and storage interfaces are continuously changing.
Different types of user queries might require additional filtering and joining of data, which becomes hard to generalize.

APIs solve almost all of these very well known challenges. APIs offer standardization and security. APIs can provide a stable contract to interact with underlying data.

And in all likelihood, you already have APIs on these internal and external data sources.

Ironically, while APIs have become a necessity for other parts of the stack, they are clearly not the first thing that AI engineers building RAG reach for.

In this talk, we’ll discuss:
Why API based retrieval doesn’t work well for RAG
What we need from our existing internal and external APIs to make them RAG ready
How we can get existing APIs to become RAG ready without needing to rebuild the APIs

This talk will be technical, with code demos (possibly with some live coding!) and end with key resources (reference architectures, API best practices, tools/technologies) that attendees can take back to their work.
Speakers
avatar for Anushrut Gupta

Anushrut Gupta

Senior Product Manager, Generative AI, Hasura
Thursday November 14, 2024 10:00am - 10:25am PST
VIRTUAL API World -- OPEN Workshop Stage

11:00am PST

[Virtual] OPEN SESSION (CloudX): Responsible AI and Security in the Generative Era: Science and Practice
Thursday November 14, 2024 11:00am - 11:25am PST
Ishneet Dua, Amazon Web Services, Senior Generative AI Solutions Architect
Parth Girish Patel, Amazon Web Services, Sr AI/ML Architect

The rapid growth of generative AI brings promising innovation and, at the same time, raises new challenges around its security, safe, and responsible development and use. These challenges include some that were common before generative AI, such as bias and explainability, and new ones unique to generative models, including hallucinations, toxicity, and intellectual property protection. During this session, participants will gain an overview of the challenges that generative AI presents, survey the emerging science surrounding these challenges, and engage in a discussion about the hands-on, security, and Responsible AI work currently being conducted on AWS.
Speakers
avatar for Ishneet Dua

Ishneet Dua

Senior Generative AI Solutions Architect, Amazon Web Services
Ishneet Dua (Isha) is a recognized expert in leveraging AI and machine learning for sustainability solutions. She has established herself as a go-to authority on combating climate change, pollution, and other environmental challenges through cutting-edge technologies.Dua has authored... Read More →
avatar for Parth Girish Patel

Parth Girish Patel

Sr AI/ML Architect, AWS
Parth Girish Patel is a seasoned architect with a wealth of experience spanning over 17 years, encompassing management consulting and cloud computing. Currently, at Amazon Web Services (AWS), he specializes in Artificial Intelligence/Machine Learning, generative AI, sustainability... Read More →
Thursday November 14, 2024 11:00am - 11:25am PST
VIRTUAL CloudX -- Main Stage

11:30am PST

[Virtual Exclusive] OPEN SESSION (CloudX): Azure OpenAI in Action
Thursday November 14, 2024 11:30am - 11:55am PST
Jannik Reinhard, BASF, Senior Solution Architect

In this session I will guide you from how to start with a CoPilot to deploy and own Azure Open AI instance to use cases which brings benefit to your company. We will also have a look how to build custom solution with the power of Azure.

- Takeaways:
- What is a copilot and how you can use it in your daily business
- How to setup Azure Open AI
- How can you build a custom solution with help of Azure.
Speakers
avatar for Jannik Reinhard

Jannik Reinhard

Senior Solution Architect, basf
My name is Jannik Reinhard and I'm 25 years old and I am work in the internal IT department of the largest chemical company in the world. I am a senior solution architect in the area of modern device management and technical lead of AIOPS (AI of IT Operation).
Thursday November 14, 2024 11:30am - 11:55am PST
VIRTUAL CloudX -- Main Stage

12:00pm PST

[Virtual Exclusive] OPEN SESSION (CloudX): Adding Generative AI to Real-Time Streaming Pipelines
Thursday November 14, 2024 12:00pm - 12:25pm PST
Timothy Spann, Zilliz, Principal Developer Advocate

In this talk I walk through various use cases where bringing real-time data to LLM solves some interesting problems.

In one case we use Apache NiFi to provide a live chat between a person in Slack and several LLM models all orchestrated via NiFi and Kafka. In another case NiFi ingests live travel data and feeds it to HuggingFace and OLLAMA LLM models for summarization. I also do live chatbot. We also augment LLM prompts and results with live data streams. All with ASF projects. I call this pattern FLaNK AI.
Speakers
avatar for Timothy Spann

Timothy Spann

Principal Developer Advocate, Zilliz
Tim Spann is the Principal Developer Advocate for Data in Motion @ Zilliz. Tim has over a decade of experience with the IoT, big data, distributed computing, streaming technologies, and Java programming. Previously, he was a Developer Advocate at StreamNative, Principal Field Engineer... Read More →
Thursday November 14, 2024 12:00pm - 12:25pm PST
VIRTUAL CloudX -- Main Stage

1:30pm PST

[Virtual] OPEN SESSION (CloudX): Unlocking the Promise of AIOps: Leveraging AI to Realize Full-Context Operations
Thursday November 14, 2024 1:30pm - 1:55pm PST
Fred Koopmans, BigPanda, Chief Product Officer

Context is fundamental to well-run tech operations: With the right context, IT teams can better understand their systems, interpret real-time data quickly, and facilitate better incident management to achieve operational efficiency. But too often, gathering the necessary context is a lengthy, inconsistent, and elusive process. IT teams are forced to grapple with fragmented tools, siloed workflows, and inconsistent manual processes, which have turned context collection into a definitive pain point for the ITOps industry. Teams are losing out on precious time, money, and attention that should be directed towards digital transformation and innovation.

The tech industry has recently transformed thanks to the AI boom: ITOps is at a critical juncture where AI can enable faster, more efficient ITOps as well as deliver Full-Context Operations. Fred Koopmans, Chief Product Officer of AIOps platform BigPanda, will speak to the promise of Full-Context Operations – the process of unifying IT teams’ tools and processes with AI to provide the institutional knowledge needed to address every incident immediately. He’ll dive deep into the ways that teams can tangibly benefit from having the right context, outlining how the IT industry can leverage AI to collect comprehensive and contextual data to help operators achieve better incident resolution. Fred can share detailed proof points from developing BigPanda’s AI-powered assistant that was purpose-built for delivering full context in IT operations. With Full-Context Operations, the IT industry can finally fulfill the long-sought-after promise of AIOps, putting AI into practice to deliver unprecedented operational efficiency.
Speakers
avatar for Fred Koopmans

Fred Koopmans

Chief Product Officer, BigPanda
Fred Koopmans, BigPanda's Chief Product Officer, is dedicated to driving innovation and collaboration, building trusted partnerships with customers, creating product roadmaps, and empowering individuals to achieve the extraordinary. He leads product strategy, product management, product... Read More →
Thursday November 14, 2024 1:30pm - 1:55pm PST
VIRTUAL CloudX -- Main Stage
 

Share Modal

Share this link via

Or copy link

Filter sessions
Apply filters to sessions.
  • Talk Type
  • OPEN Session
  • PRO Session
  • PRO Workshop
  • Track or Conference
  • AI & ML (CloudX)
  • API Case Studies & Success Stories (API World)
  • API Design / Architecture (API World)
  • API Leadership Summit (API World)
  • API Ops & Scalability & Usability (DX) & Testing (API World)
  • API Program Management (API World)
  • API Security / Compliance (API World)
  • API World
  • API World: API Innovation
  • API World: API Lifecycle
  • API World: API Strategy
  • API World: Microservices World
  • API-First Development (API World)
  • APIs (Dev Innovation)
  • Automated Testing & Monitoring & Reporting (CloudX)
  • CI/CD (CloudX)
  • CI/CD / Deployment (API World)
  • Cloud Development Technologies (CloudX)
  • Cloud Development Technologies (Dev Innovation)
  • Cloud Infrastructure (CloudX)
  • Cloud Innovation (AI & Edge & etc) (CloudX)
  • Cloud Security (CloudX)
  • Cloud Talent & Skills (CloudX)
  • CloudX
  • CloudX: Cloud Architecture & Infrastructure
  • CloudX: Cloud Strategy Conference
  • CloudX: Cloud-Native Development
  • CloudX: DevOps Summit
  • Containers & Kubernetes (CloudX)
  • Deployment Strategies (CloudX)
  • Dev Innovation (CloudX)
  • Dev Innovation Summit
  • Developer Tools (Dev Innovation)
  • DevSecOps (CloudX)
  • Digital Acceleration (CloudX)
  • Edge Computing (CloudX)
  • Emerging APIs: AI & IoT & Blockchain & Web3 & XR (API World)
  • Expo Challenge
  • Future of Cloud-Native Computing (CloudX)
  • Hybrid & Multi-Cloud (CloudX)
  • Hybrid APIs & Low Code APIs (API World)
  • Industries: Open Banking & Healthcare & Retail (API World)
  • Infrastructure-as-Code (CloudX)
  • Integration Management (API World)
  • Leadership Lounge
  • Microservices Design & Architecture (API World)
  • Microservices Design (CloudX)
  • Microservices Management (CloudX)
  • Observability (CloudX)
  • OPEN Session
  • Platform Engineering (API World)
  • Programming Languages (Dev Innovation)
  • Roundtables
  • Service Mesh & Containers & Kubernetes (API World)
  • Sponsor Spotlight
  • Virtual
  • In-Person/Virtual
  • In Person
  • Virtual
  • Virtual Exclusive