Tutorials Microsoft Agent Framework with Ollama Tutorial
Introduction to LLMs
Introduction to LLMs: free step-by-step lesson with examples, common mistakes, and interview tips — part of Microsoft Agent Framework with Ollama Tutorial on Toolliyo Academy.
On this page
Microsoft Agent Framework with Ollama Tutorial · Lesson 2 of 100
LLMs
Foundations & Ollama → .NET & Agents → RAG & Ops → Projects
Foundations & Ollama · 1 — Local model · ~6 min · Foundations — AI & Agents
What is this?
An LLM (large language model) predicts the next tokens of text. It does not “know” your database unless you give context (prompts, tools, or RAG).
Why should you care?
Every chat screen, summarizer, and agent you build sits on an LLM. Understanding tokens and context windows stops bad designs.
See it live — copy this example
Run CLI steps in a terminal. Run C# samples in a .NET 8 console or Web API project with Ollama running on localhost:11434.
# After Ollama is installed (next module):
ollama run phi3:mini
>>> Explain what an LLM is in two sentences.What happened?
- ollama run starts a chat with a small model.
- You type a prompt; the model streams a reply.
- phi3:mini is light enough for many laptops.
Practice next
- Install Ollama when you reach that lesson.
- Pull phi3:mini.
- Ask it to define LLM.
- Change temperature in the Modelfile later.
- Compare phi3 vs llama reply length.
Remember
LLMs generate text from patterns. Context must be provided. Start with a small model.
Token budget
Support replies must stay short for agents.
Outcome: You prompt for two sentences, not essays.
Interview prep for this lesson
Practice these questions aloud after reading—each links to a full structured answer.
Sign in to ask a question or upvote helpful answers.
No questions yet — be the first to ask!