Emerging Architectures for Large Language Model Applications

Generative Al and Large Language Models have taken the world by storm. Applications like Bard, ChatGPT, Midjourney, and Dall.E crossed the proverbial chasm of technology adoption lifecycle; some applications like content generation and summarization have entered the mainstream. A large number of enterprise use cases of LLM applications still remain challenging. There are inherent challenges for a lot of tasks that require a deeper understanding of trade-offs like latency, accuracy, and consistency of responses. Any serious application of LLMs requires an understanding of nuances in how LLMs work, embeddings, vector databases, and retrieval.

This introductory tutorial will introduce the audience to prevalent approaches to building a custom large language model application. We will present a canonical architecture for an LLM application and various available commercial and open-source tools and technologies available to build these applications.

No prior background in Generative AI or LLMs is necessary to attend this talk.