Accelerating AI Innovation: Building Advanced RAG Applications

Deep dive into how leading AI startups across Silicon Valley, Singapore, and Bangalore are fast-tracking their innovation using a cutting-edge tech stack. In this session, you’ll learn how the synergy of TiDB Vector for robust data management, AWS’s powerful compute infrastructure, and Dify’s versatile RAG framework can streamline your AI application development. Uncover how this integrated approach accelerates time-to-market, enhances performance, and delivers a seamless user experience—transforming the way AI applications are built.

🗓 Date: Thursday, Nov. 28th, 2024
⏰ Time: 09:30-11:00 AM GMT / 15:00-16:30 IST(UTC+05:30) / 17:30-19:00 SGT(UTC+08:00)
📍 Location: Online
👉 Register Now!

Who Should Attend
AI startup founders, AI application developers, Algorithm engineers, Architects, Data scientists, Data analysts, Database administrators, DevOps engineers, Engineering managers, Software engineers and developers, etc.

What You Will Get
Discover how this tech stack can help you overcome traditional coding barriers and revolutionize your data processes. Empower your AI agents with lightning-fast retrieval and unlock the full potential of RAG AI technology:
How this tech stack reduces AI applications’ time-to-market

• Cost-efficient scaling from prototype to production
• Built-in security and compliance features
• Pay-as-you-go pricing model
• Global data distribution capabilities
• Real-time data processing and querying

How does this tech stack impact on your users' experience

• Fast and accurate responses from AI applications
• Consistent performance under varying loads
• Secure handling of sensitive data
• Cost-effective solution scaling
• Global accessibility

How to get started

🗣Speakers

1. Carson Chan, Partner Solutions Architect | AWS
   Speaker Bio:
   In the era of Generative AI, Carson collaborates with clients to leverage new AWS services like Amazon Q and Amazon Bedrock to accelerate innovation, creating business value across various application scenarios such as chatbots and personalized analytics.
2. Yawen Zhao, RAG Product Designer | Dify
   Speaker Bio:
   Yawen leverages her expertise in NLP and LLM algorithms to drive innovation and develop advanced solutions for Retrieval-Augmented Generation (RAG).
3. Wish Shi, Senior Software Engineer | PingCAP
   Speaker Bio:
   Maintainer of TiDB and TiKV. Wish has been working with TiDB project for 7 years, and now leads the development of TiDB Vector Search.