Building AI Applications for Agencies

C) Copyright Elephant Scale

October 6, 2024

Course Description

  • AI opens ways to building smart applications as never before.
  • However, many use cases require implementing AI in a secure, responsible manner, including but not limited to:
    • Not sending your data to third-party online AI services
    • Keeping control over the data used for training
    • Controlling actions taken by AI
  • In this course, the students learn how build the AI systems.
    • Prepare your data and store it in the semantic search databases
    • Rules of sending questions to AI
    • Secure AI implementations using local models or networked local copy of the model
    • Best practices for cloud architecture

After the course, you will be able to do the following tasks

  • Talk to an AI in a correct way.
  • Script talking to AI for a programmatic implementation.
  • Organize your private documents for the implementation and break them into meaningful fragments for storing in the semantic search engine
  • Structure the flow of conversation with AI about your private documents.
  • Implement the system in production.
  • Architect testing, and continuous improvements.

Audience

  • Developers, data scientists, team leads, project managers

Skill Level

  • Intermediate to advanced.

Duration

  • Three to five days

Prerequisites

  • General familiarity with machine learning
  • Exposure to coding in any language
  • Familiarity with Python helpful

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

Prompt Engineering

  • Introduction to AI
  • Iterative development
    • How to iteratively analyze and refine your prompts to generate marketing copy from a product fact sheet.
  • Summarizing
    • How to make an AI summarize a document with different requirements and in different formats
  • Inferring
    • How to make an AI infer sentiment and topics from product reviews and news articles.
  • Transforming
    • How to use Large Language Models for text transformation tasks such as language translation, spelling and grammar checking, tone adjustment, and format conversion.
  • Expanding
    • How to generate customer service emails that are tailored to each customer’s review.
  • Chatbot
    • How to use an AI to have extended conversations with chatbots personalized or specialized for specific tasks or behaviors.

Semantic Search

  • Organize your private documents for the implementation and break them into meaningful fragments for storing in the semantic search engine
  • Semantic search
  • Retrieval Augmented Generation (RAG)
  • Recommender systems
  • Hybrid search
  • Facial similarity search
  • Anomaly detection

LangChain, glue to put it together

  • Models, prompts, and parsers
  • Memory
  • Chains
  • Q&A
  • Evaluation
  • Conversational bot

Architecture, testing, and continuous improvements

  • Overview of Amazon, Azure, and Google clouds of RAG
  • Evaluating and debugging Generative AI
  • Practical examples and demos

Practical use case

  • How to make sure your data stays private and under your control
  • Preparing reports for executives
  • Employee turnover and how to capture their experience and know-how
  • Automating daily tasks: pull stats, post them to Slack
  • Integrating Kanban into your workflow with AI