Session: Large Language Models (LLMs) – Building Applications with an Open Source Approach
Large Language Models (LLMs) can power more than just chatbots- this generative AI technology can also summarize large amounts of text and multi-modal data for quick consumption, sort/categorize/triage information based on semantic meaning, and bridge the gap between humans and computers by providing structure to unstructured data. However the need for data confidentiality, privacy, and security poses obstacles for many organizations wishing to utilize 3rd party LLM services such as ChatGPT. Thankfully, an open source approach to building LLM applications is not only feasible but preferable for organizations with such concerns.
Attendees of this talk will learn about:
- Why maintaining end-to-end control of the prompt chain matters for security and reliability
- The open source LLM models, vector databases, and frameworks that are available for rapid LLM application development
- A live demonstration of how such frameworks can be used to build useful LLM applications
- The runtime/deployment options for powering a LLM-powered application for their organization’s use
