As a part of OPEA Week, we invite you to join us for our latest virtual event – OPEA: GenAI Streamlined. This event will focus on practical insights with actionable technical details to help you drive your GenAI solutions in an efficient and cost-effective way. The agendas include:
To ensure developers across the globe can attend these events, we will be hosting an event in a different time zone during the week. We look forward to you joining us!
REGISTRATION NOTE: If you are already signed into the Linux Foundation system, look for the ‘Need an Invite Link’ when sent to the registration page.
↓See detailed Agendas for each region below registration links↓
Contact: rachel.roumeliotis@intel.com with questions
Monday, April 14
China Region
9AM – 12PM China Standard Time
Register Now
Tuesday, April 15
India Region
9:30AM – 12:30PM India Standard Time
Register Now
Wednesday, April 16
Americas Region
9AM – 12PM Pacific Daylight Time
Register Now
Thursday, April 17
EMEA Region
10AM – 1PM Central Europe Time
Register Now
Friday, April 18
Americas Region
9AM – 12PM Pacific Daylight Time
Register Now
| China Region Agenda | |||
|---|---|---|---|
| Title | Speaker | Session abstract | |
| 9:00AM CST - 9:01AM CST | Welcome | Kenny Chen, Intel | |
| 9:01AM CST - 9:06AM CST | Linux Foundation Welcome | ||
| 9:06AM CST - 9:15AM CST | State of OPEA Keynote | Ke Ding, Intel | The OPEA project joined the LF AI & Data Foundation in April of 2024 and since can be used across several hyperscalers, has made performance improvements, and added18 additional end-to-end examples. Join Ke Ding, OPEA TSC, as he gives an overarching view of achievements so far and high-level goals for the next year. |
| 9:10AM CST - 9:30AM CST | OPEA in 2025: A look ahead | Ke Ding, Intel | This session will take a look at what to expect in 2025 with a focus on forthcoming 1.3 release this April including an advanced Agent QnA exxample, a basic Financial Agent as well as vLLM enablement across all examples. |
| 9:30AM CST - 9:50AM CST | TBD | ||
| 9:50AM CST - 10:10AM CST | Building and Deploying AI Agents with OPEA | Kaokao Lv, Intel | Yes, the hottest topic in GenAI today! Agents! Find out: What an AI agent is, how they gain knowledge to complete tasks, and why they are important today. See why AI Agents have so much potential over traditional RAG using the Comprehensive RAG (C-RAG) benchmark andL earn how to build, customize, and deploy a hierarchical multi-agent system for QnA applications with OPEA. |
| 10:10AM CST - 10:20AM CST | 10 min break | ||
| 10:20AM CST - 10:40AM CST | InfiniEdge and OPEA | Wilson Wang, ByteDance | "In this session, attendees will get a brief introduction to InfiniEdge AI and the SPEAR workstream as well as insight into why OPEA is integrating into the SPEAR workstream. " |
| 10:40AM CST - 11:00AM CST | ArangoDB GraphRAG Techniques on OPEA | Anthony Mahanna, ArangoDB | ArangoDB is collaborating with the Intel Team to introduce custom GraphRAG techniques into the OPEA framework. *DataPrep: Generate Knowledge Graphs from unstructured and structured data *Retriever: Query Knowledge Graphs using Vector Search, Keyword Search, and Graph Traversals *ChatQnA: Easily build & deploy a GraphRAG-enhanced ChatBot for question-answering on PDFs via Knowledge Graphs |
| 11:00AM - 11:10AM CST | 10 min break | ||
| 11:10AM - 11:30AM CST | AI Eval on OPEA | Yu Lu & Suyue Chen, Intel | The goal is end-to-end evalution of its framework. See what OPEA has in place for eval such as HELMET and longbench. |
| 11:30AM CST - 11:50AM CST | OPEA on AWS | Feng Tian, Intel | Discover how to build and deploy enterprise-grade GenAI applications using OPEA in AWS. We’ll take a look at the public OPEA workshop—available for anyone to run in their own AWS environment—and explore its capabilities for simplifying the deployment of retrieval-augmented generation (RAG) pipelines. |
| 11:50AM CST - 12:00AM CST | OPEA Community Call to Action | Kenny Chen, Intel | We take a look at a snapshot of the OPEA community and what we want to accomplish in 2025. |
| India Region Agenda | |||
|---|---|---|---|
| Schedule | Title | Speaker | Session Abstract |
| 9:30AM IST - 9:31AM IST | Welcome | Sachin Kelkar, Intel | |
| 9:31AM IST - 9:40AM IST | State of OPEA Keynote | Malini Bhandaru, Intel | The OPEA project joined the LF AI & Data Foundation in April of 2024 and since can be used across several hyperscalers, has made performance improvements, and added18 additional end-to-end examples. Join Malini Bhandaru, Chair of the OPEA TSC, as he gives an overarching view of achievements so far and high-level goals for the next year. |
| 9:40AM IST-10:00AM IST | OPEA in 2025: A look ahead | Rama Karamsetty, Intel | This session will take a look at what to expect in 2025 with a focus on forthcoming 1.3 release this April including an advanced Agent QnA exxample, a basic Financial Agent as well as vLLM enablement across all examples. |
| 10:00AM IST - 10:20AM IST | XX | Gayathri NVS, Zensar | |
| 10:20AM IST - 10:40AM IST | Building and Deploying AI Agents with OPEA | Anish Kumar, Intel | Yes, the hottest topic in GenAI today! Agents! Find out: What an AI agent is, how they gain knowledge to complete tasks, and why they are important today. See why AI Agents have so much potential over traditional RAG using the Comprehensive RAG (C-RAG) benchmark andL earn how to build, customize, and deploy a hierarchical multi-agent system for QnA applications with OPEA. |
| 10:40AM IST - 10:50AM IST | 10-Min Break | ||
| 10:50AM IST - 11:10AM IST | Powered by OPEA: Moving from OpenAI to Open Source with OPEA | ISTE/Intel | See how organizations can reduce costs and better control data privacy by replacing OpenAI services with open source microservices from the Open Platform for Enterprise AI (OPEA) project running on Intel hyperscale instances. |
| 11:10AM IST - 11:30AM IST | GenAI Security on OPEA | Shriram Vasudevan, Intel | Security is one of the pillars of OPEA as it is a non-negotiable when creating enterprise-scale GenAI solutions, see how OPEA implements this across the framework. |
| 11:30AM IST - 11:50AM IST | OPEA on Azure | Kaushal Desai, Infosys | Infosys has contributed the work necessary to make OPEA available on Azure, find out how to build and deploy cloud-native GenAI solutions with OPEA on Azure. |
| 11:50PM IST - 12:00PM IST | OPEA Community (Call to action) & Farewell | Malini Bhandaru, Intel | We take a look at a snapshot of the OPEA community and what we want to accomplish in 2025. |
| Americas Region Agenda | |||
|---|---|---|---|
| Schedule | Title | Speaker | Session |
| 9:00AM PT - 9:01AM PT | Welcome | Rachel Roumeliotis, Intel | |
| 9:01AM PT - 9:10AM PT | State of OPEA Keynote | Malini Bhandaru, Intel | The OPEA project joined the LF AI & Data Foundation in April of 2024 and since can be used across several hyperscalers, has made performance improvements, and added18 additional end-to-end examples. Join Malini Bhandaru, Chair of the OPEA TSC, as he gives an overarching view of achievements so far and high-level goals for the next year. |
| 9:10AM PT - 9:30AM PT | OPEA in 2025: A look ahead | Rama Karamsetty, Intel | This session will take a look at what to expect in 2025 with a focus on forthcoming 1.3 release this April including an advanced Agent QnA exxample, a basic Financial Agent as well as vLLM enablement across all examples. |
| 9:30AM PT - 9:50AM PT | InfiniEdge and OPEA | Wilson Wang, ByteDance | In this session, attendees will get a brief introduction to InfiniEdge AI and the SPEAR workstream as well as insight into why OPEA is integrating into the SPEAR workstream. |
| 9:50AM PT - 10:10AM PT | Building and Deploying AI Agents with OPEA | Minmin Hou, Intel | Yes, the hottest topic in GenAI today! Agents! Find out: What an AI agent is, how they gain knowledge to complete tasks, and why they are important today. See why AI Agents have so much potential over traditional RAG using the Comprehensive RAG (C-RAG) benchmark andL earn how to build, customize, and deploy a hierarchical multi-agent system for QnA applications with OPEA. |
| 10:10AM PT - 10:20AM PT | 10-min Break | ||
| 10:20AM PT - 10:40AM PT | Composable RAG Pipelines With OPEA and Neo4j | Andreas Kollegger, Neo4j | GraphRAG can supercharge the output from your RAG solution when you need to pull a more context-aware substantial answers from your solutions. This demo showcases an OPEA RAG pipeline that uses the Neo4j GraphRAG solution. |
| 10:40AM PT - 11:00AM PT | ArangoDB GraphRAG Techniques on OPEA | Anthony Mahanna, ArangoDB | ArangoDB is collaborating with the Intel Team to introduce custom GraphRAG techniques into the OPEA framework. *DataPrep: Generate Knowledge Graphs from unstructured and structured data *Retriever: Query Knowledge Graphs using Vector Search, Keyword Search, and Graph Traversals *ChatQnA: Easily build & deploy a GraphRAG-enhanced ChatBot for question-answering on PDFs via Knowledge Graphs |
| 11:00AM - 11:10AM PT | 10-min Break | ||
| 11:10AM - 11:30AM PT | Guardrails | Prediction Guard | |
| 11:30AM PT - 11:50AM PT | OPEA on AWS | Eze Lanza, Intel | Discover how to build and deploy enterprise-grade GenAI applications using OPEA in AWS. We’ll take a look at the public OPEA workshop—available for anyone to run in their own AWS environment—and explore its capabilities for simplifying the deployment of retrieval-augmented generation (RAG) pipelines. |
| 11:50AM PT - 12:00AM PT | OPEA Community (Call to action) & Farewell | Rachel Roumeliotis, Intel | We take a look at a snapshot of the OPEA community and what we want to accomplish in 2025. |
| EMEA Region Agenda | |||
|---|---|---|---|
| Schedule | Title | Speaker | Session |
| 10:00AM CET - 10:01AM CET | Welcome | ||
| 10:01AM CET - 10:10AM CET | State of OPEA Keynote | Malini Bhandaru, Intel | The OPEA project joined the LF AI & Data Foundation in April of 2024 and since can be used across several hyperscalers, has made performance improvements, and added18 additional end-to-end examples. Join Malini Bhandaru, Chair of the OPEA TSC, as he gives an overarching view of achievements so far and high-level goals for the next year. |
| 10:10AM CET - 10:30AM CET | OPEA in 2025: A look ahead | Zhiwei Zhang, Intel | This session will take a look at what to expect in 2025 with a focus on forthcoming 1.3 release this April including an advanced Agent QnA exxample, a basic Financial Agent as well as vLLM enablement across all examples. |
| 10:30AM CET - 10:50AM CET | Guardrails | Prediction Guard | |
| 10:50AM CET - 11:10AM CET | Building and Deploying AI Agents with OPEA | Shriram Vasudevan, Intel | Yes, the hottest topic in GenAI today! Agents! Find out: What an AI agent is, how they gain knowledge to complete tasks, and why they are important today. See why AI Agents have so much potential over traditional RAG using the Comprehensive RAG (C-RAG) benchmark andL earn how to build, customize, and deploy a hierarchical multi-agent system for QnA applications with OPEA. |
| 11:10AM CET - 11:20AM CET | 10-min Break | ||
| 11:20AM CET - 11:40AM CET | Composable RAG Pipelines With OPEA and Neo4j | Andreas Kollegger, Neo4j | GraphRAG can supercharge the output from your RAG solution when you need to pull a more context-aware substantial answers from your solutions. This demo showcases an OPEA RAG pipeline that uses the Neo4j GraphRAG solution. |
| 11:40AM CET - 12:00PM CET | Powered by OPEA: Moving from OpenAI to Open Source with OPEA | See how organizations can reduce costs and better control data privacy by replacing OpenAI services with open source microservices from the Open Platform for Enterprise AI (OPEA) project running on Intel hyperscale instances. | |
| 12:00PM - 12:10PM CET | 10-min Break | ||
| 12:10PM - 12:30PM CET | ArangoDB GraphRAG Techniques on OPEA | Michael Hackstein, ArangoDB | ArangoDB is collaborating with the Intel Team to introduce custom GraphRAG techniques into the OPEA framework. *DataPrep: Generate Knowledge Graphs from unstructured and structured data *Retriever: Query Knowledge Graphs using Vector Search, Keyword Search, and Graph Traversals *ChatQnA: Easily build & deploy a GraphRAG-enhanced ChatBot for question-answering on PDFs via Knowledge Graphs |
| 12:30PM CET - 12:50PM CET | OPEA on Azure | Adarsh Ramachandra, Infosys | Infosys has contributed the work necessary to make OPEA available on Azure, find out how to build and deploy cloud-native GenAI solutions with OPEA on Azure. |
| 12:50PM CET - 1:00PM CET | OPEA Community Call to Action | Zhiwei Zhang, Intel | We take a look at a snapshot of the OPEA community and what we want to accomplish in 2025. |
