LLM use: Application and Proprietary Data

(C) Copyright Elephant Scale January 28, 2024

Course Description

  • Large Language Models (LLM) are taking the world by storm. It can be ChatGPT, Claude, or Bard, but AI doubling productivity in many occupation.
  • This course teaches how to build applications with LLMs. It concentrates on multistep reasoning that includes the user’s proprietary documents.

Audience

  • Developers, data scientists, team leads, project managers

Skill Level

  • Intermediate to advanced

Duration

  • Two days

Prerequisites

  • General familiarity with machine learning

Format

  • Lectures and hands on labs. (50% – 50%)

Lab environment

  • Zero Install: There is no need to install software on students’ machines!
  • A lab environment in the cloud will be provided for students.

Students will need the following

  • A reasonably modern laptop with unrestricted connection to the Internet. Laptops with overly restrictive VPNs or firewalls may not work properly.
    • A checklist to verify connectivity will be provided
  • Chrome browser

Detailed outline

  • Introduction
  • Models, prompts, and parsers
  • Chains
  • Questions and answers
  • Agents
  • Workshop
  • Document loading
  • Document splitting
  • Vectorstores and embeddings
  • Retrieval
  • Question answering with documents
  • Chat with documents
  • Workshop