A classic AI framework to define an agent’s task environment is PEAS. It stands for:
- Performance
- Environment
- Actuators
- Sensors
PEAS for Agent AI
The R in RAG
In my previous post we looked at saving to the vector store. In this short post we’ll look at retrieving that information.
The simple search is a good starting point and depends on writing a good prompt, but we can do better.
- One problem in searching is that we often retrieve redundant data. For example, the basic search might retrieve ten very similar chunks. Maximal Marginal Relevance first builds a set of results that are relevant but also diverse. It then iterates through the relevant documents looking for ones that are as different as possible. As you might expect, this gives you a diverse set of relevant documents.
Deeper into RAG
In the previous post we walked through creating a RAG example, line by line. Let’s take a closer conceptual look at the steps involved in creating a RAG
- Load your source documents, being careful to keep the meta-data
- Split your document into semantically meaningful chunks
- Convert your text to vector representations in an embedding model
- Store your vector representations in a vector database
- Retrieve the data you need
Posted in Essentials
Leave a comment
RAG In Detail
In my previous post I walked through a RAG example but glossed over the details. In this post I’ll back up and walk through the program line by line.
The key steps in RAG are
- Load the data
- Split the text into smaller chunks to fit within context limits
- Create a Document object
- Embed the document in vectors that represent semantic meaning
- Store the document—typically in vector stores. These are databases designed to store embeddings and provide fast semantic retrieval
- Invoke a retriever to query the back end to return the most relevant Document object
- Create a prompt for the LLM
RAG – A Quick Example
In the previous blog post, we imported a few Python modules and configured our AI key, using Colab.
In this blog post we’ll use Retrieval-Augmented Generation (RAG) to extend an LLM that we’ll get from OpenAI. I’ll use a number of features from the libraries we imported with only a cursory explanation and will come back to them in upcoming blog posts to examine them in more depth. But I want to get to RAG right away because it is rapidly becoming central to AI and because it is cool.
LLMs are incredibly expensive to create and train, and it isn’t feasible to train them on everything. Besides that, much data is proprietary. It may be that you want an LLM that handles (to use the canonical case) your HR policies. Clearly no commercial LLM knows about those policies, nor should they. And equally clearly, you’re not going to train an LLM from scratch. What you want to do is to combine your own corpus of data (HR policy papers, etc.) with an existing LLM, and that is exactly what RAG is for.
In this simple example, we’re going to take a scene or two from Romeo and Juliet and feed it to gpt-40-mini; one of many LLMs available for use at minimal cost (we’ll get into how cost is computed in an upcoming post).
The first thing we’ll do after configuring the OPEN_API_KEY will be to get a TextLoader to import the text file with the scenes from Romeo and Juliet
Continue readingCreating Our Python AI Project
As noted in a previous blog post, we’ll be building our project on two platforms: Python and .NET (C#). For Python, we’ll build on Colab. For now, you can use a free account.
The first step is to get an OpenAI key, as described in this previous blog post (scroll to the bottom). Note, these are not free, but we’re talking a few dollars for this entire series of posts.
Continue readingMads Torgersen
Mads (Lead Designer of C#) joins me to discuss C# and AI as well as what to expect in C# 15.
Posted in Essentials
Leave a comment
Distributed Computing & Docker
Joe Dluzen joins me to discuss, in depth, distributed computing and Docker.
Posted in Essentials
Leave a comment
Microsoft Agent Framework – Part 0
I’ve been looking at a number of different ways to build Agents. I’ve settled on two and will be documenting what I learn as I go:
- Building from first principles based on my course on Agentics at Johns Hopkins
- Building using Microsoft’s new Agent Framework
The advantage of the first is that you understand the underlying mechanisms in more depth; the advantage of the second is that a lot of the plumbing is done for you and you become more productive more quickly.
I will do the .NET work in C#, and probably do all the other work in Python. See my blogpost on why Python.
I will, to a degree, be documenting what I learn as I learn it, without infringing on copyright, of course.
Continue reading
Posted in Essentials
Leave a comment
AI: The Near Term
As promised, I’ll be posting slides and commentary from my recent user-group presentation on AI (Boston Code Camp). One of my first slides talked about the near-term evolution of AI, defined as either 1-2 years or 6 months, depending on who you believe.
I divided the slide into two parts: good news and bad. The good news is the promise of enormously increased productivity, which may well lead to a higher standard of living across the board. Further, as AI progresses, we may see accelerated breakthroughs in many fields, most notably medicine and genetics.
Posted in Essentials
Leave a comment
MCP In Depth
In a special videoCast, Lance McCarthy of Progress Software dives deep into MCP, not only explaining what it is for and how it works, but demonstrating, in code, how it is done.
MCP (Model, Context, Protocol) is an open standard that lets AI models (read copilot, ChatGPT, etc.) connect to external tools. These tools can be databases, code you write, code you connect to, other AIs, etc. etc. It is the universal API for Agents.
Posted in Essentials
Leave a comment
Get on the bus, or get run over by it
On March 28 I’m presenting on Fundamentals of AI to the Boston Code Camp. While I will cover what you need to know about the various aspects of using and creating various AI components, the key message is it is time. It is time to start developing and honing your AI skills, or as I say in the title, you will be run over by the AI bus.
After the presentation, I’ll cover a lot of that material here, but to get us started let’s talk about the two ways you’ll care about AI.
- Using AI to aid you in your coding
- Creating applications that incorporate AI
Posted in AI
Leave a comment
