Go Beyond Chatbot – Emerging Patterns in Generative AI Applications

Join the Data Phoenix Slack community: https://join.slack.com/t/data-phoenix/shared_invite/zt-115lu0xo1-KhDX_4xAyEd4JiuiUZ3ieQ
Subscribe to Data Phoenix Digest: https://dataphoenix.info/

===========================

Join us for this talk where we will be sharing some reference architectures, use cases and demos for the emerging patterns on how to build a fully-functional Generative AI applications. We will show some of the most common systems, tools and design patterns used by AI startups, enterprises and sophisticated tech companies, and how they incorporate the ‘hype’ as part of their data strategy.
Speaker: Tingyi Li works as an Enterprise Solutions Architect at Amazon Web Services based in Stockholm Sweden, and is the founder and leader of the AWS Nordics Generative AI community. Prior to AWS, she has worked as Data and AI Engineer at Huawei, Intel, Foxconn etc, building large-scale intelligent industrial data systems and driving innovations using AI/ML. In her spare time, she also works as a part-time illustrator/prompt engineer who writes novels and plays the piano.

Linkedin post with the architecture: https://www.linkedin.com/posts/tingyi-li_llms-rag-llmops-activity-7094945760445706240-ikFI
Follow the speaker: https://www.linkedin.com/in/tingyi-li/

===========================

Extended technical resources mentioned in the session:
LangChain demo – build an SA agent: https://community.aws/posts/building-agent-aws
Safe image generation and diffusion models with Amazon AI content moderation services: https://aws.amazon.com/blogs/machine-learning/safe-image-generation-and-diffusion-models-with-amazon-ai-content-moderation-services/
RAG approach: https://medium.com/@pandey.vikesh/rag-ing-success-guide-to-choose-the-right-components-for-your-rag-solution-on-aws-223b9d4c7280
Fine-tuning LLMs with PEFT and LoRA: https://www.youtube.com/watch?v=Us5ZFp16PaU
Interactively fine-tune Falcon-40B and other LLMs on Amazon SageMaker Studio notebooks using QLoRA: https://aws.amazon.com/blogs/machine-learning/interactively-fine-tune-falcon-40b-and-other-llms-on-amazon-sagemaker-studio-notebooks-using-qlora/
Adversarial Attacks on Aligned Language Models paper: https://arxiv.org/pdf/2307.15043.pdf
Nemo guardrails: https://www.youtube.com/watch?v=SwqusllMCnE&t=677s