| |
Data For Generative AI Workshop w/ AWS & Cohere
|
| With Benjamin Skrainka (Principal Economist, Amazon), Shayon Sanyal (Principal Solns Architect Data & AI, AWS), Payal Singh (Solns Architect, Cohere). |
| AWS GenAI Loft, 525 Market St, 2nd Fl, San Francisco |
|
May 08 (Thu) , 2025 @ 09:30 AM
| |
FREE |
|
|
|
|
|
|
|
|
| |
| DETAILS |
|
Join a small cohort with subject matter experts & uncover generative AI solution insights with hands-on labs. Develop rapid prototypes. Learn to achieve high recall rates, reduce latency, minimize hallucinations, & balance cost-performance optimization at production scale through practical strategies. According to Deloitte's 2024 survey, barriers to generative AI adoption include errors with real-world consequences, not achieving expected value, lack of high-quality data, hallucinations, & inaccuracies.
In this data & use-case-focused generative AI workshop, developers, architects, & technical decision-makers will learn the framework to build & scale applications such as real-time conversational AI & recommendation engines with RAG (Retrieval-Augmented Generation).
Event Prerequisites:
Government issued ID required for event check in
Bring your laptop for hands-on sessions & labs
Please use your business email address for registration
Agenda
10:00 PM GMT+5:30
Check-in & Networking
10:30 PM GMT+5:30
Data to Decisions: Problem framing with data for business value
In this insightful keynote, data strategy expert Ben Skrainka addresses a crucial challenge: making sure data models deliver real business value. He explores evidence-based methods to validate whether models truly answer key business questions, assess data sufficiency, & establish model trustworthiness. Participants will learn practical approaches to meet business goals, ensuring that data-driven decisions create measurable impact in today's generative AI enterprise.
10:45 PM GMT+5:30
Foundations of scalable RAG for generative AI use cases
Unlock the foundation of enterprise-ready Retrieval-Augmented Generation (RAG) with PostgreSQL pgvector & Amazon Bedrock Knowledge Bases. Explore how developers efficiently build scalable & cost-effective AI applications including conversational AI, real-time semantic & hybrid search, & intelligent recommendation systems. Learn how to streamline development using Amazon Bedrock, LLMs, & a vector database to enhance retrieval accuracy & automation. We'll also explore agentic AI architectures, enabling seamless integration with enterprise data while optimizing performance & cost.
11:45 PM GMT+5:30
Rapid Prototyping: Build effective RAG pipelines for generative AI use cases
In this hands-on session discover how to quickly prototype RAG pipeline using Amazon Bedrock & Aurora PostgreSQL pgvector. Building a RAG pipeline involves data ingestion, chunking, embedding, & iterative tuning to optimize data quality. Amazon Bedrock simplifies this process with Knowledge Bases, automating unstructured data handling & providing fine-grained tuning options. Its built-in RAG evaluation features help assess & refine pipelines using custom datasets. We'll explore how to build, manage, & optimize RAG pipelines with Amazon Bedrock & Aurora PostgreSQL pgvector, followed by a live code walkthrough showcasing the end-to-end process in action.
12:45 AM GMT+5:30
Lunch & Networking
1:30 AM GMT+5:30
Partner Session - Enterprise-grade RAG with Cohere's Embed & Rerank models for generative AI
Learn how Cohere's LLMs enhance RAG pipelines through Embed & Rerank models, addressing challenges like data quality & hallucinations. Embed generates high-quality embeddings for efficient retrieval, capturing semantic meaning & enabling similarity searches in vector spaces. Rerank optimizes results by reordering them based on relevance, ensuring accurate & contextual information feeds into the generative pipeline. These models integrate seamlessly with vector databases, crucial for scalable storage & retrieval of embeddings in production-grade RAG pipelines. This combination supports low-latency, high-recall performance at enterprise scale.
2:30 AM GMT+5:30
Practical strategies for production launch with Generative AI Innovation Center
Using a real-world example of a RAG application, we'll highlight how we help customers to quickly develop prototypes & scale it to production. This session explores the journey from PoCs to enterprise-ready production solution, focusing on selecting optimal LLMs & vector databases for specific business objectives. Join us to learn practical strategies for moving beyond prototypes & building scalable, production-grade generative AI solutions for your use cases & business objectives.
3:30 AM GMT+5:30
Q&A & Networking
|
|
|
|
|
|
|
|
