Taking Generative AI Enterprise Models to Production
This panel will address some of the common misconceptions as well as best practices and resources that users can adopt to make their GenAI applications more scalable and reliable.
This panel will address some of the common misconceptions as well as best practices and resources that users can adopt to make their GenAI applications more scalable and reliable.
Generative AI (GenAI) is an emergent area that has many AI users excited. One key feature of GenAI applications includes using Retrieval Augmented Generation (RAG) to pull up text data from internal enterprise sources. Another key feature is to reason about the retrieval results, the question, and the context of the enterprise LLM application.
These features, RAG and Reasoning, have the advantage of reducing hallucinations and reducing the need for foundational model training on enterprise domain data (which may constantly be changing on a large scale). Reasoning improvements start with prompt engineering best practices, such as specifying the LLM application’s role, subject domain, type of detailed answer, format of answer, and providing multiple-shot question-answer examples. Other reasoning improvements include Re-Act, to reason, and take action, to result in an observation.
SFbayACM hosts many lectures and training events. Please see https://sfbayacm.org for our upcoming full-day in-person workshops and monthly data science technical talks.
Stuart, CEO of Qwiet AI, presents the latest features of our AI powered AppSec platform and unveils our exciting roadmap for 2024.
Eric, founder and CEO of Second, will showcase the latest features revolutionizing complex codebase migrations. Discover the cutting-edge advancements empowering developers worldwide. Get an exclusive sneak peek into Second's ambitious roadmap for 2024.
Explore how Grit combines LLMs and compilers to deliver reliable migrations at scale