English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 45 lectures (3h 19m) | 2.07 GB
Run custom LLMs privately on your system—Use ChatGPT-like UI—Hands-on projects—No cloud or extra costs required
Are you concerned about data privacy and the high costs associated with using Large Language Models (LLMs)?
If so, this course is the perfect fit for you. “Mastering Ollama: Build Private LLM Applications with Python” empowers you to run powerful AI models directly on your own system, ensuring complete data privacy and eliminating the need for expensive cloud services.
By learning to deploy and customize local LLMs with Ollama, you’ll maintain full control over your data and applications while avoiding the ongoing expenses and potential risks of cloud-based solutions.
This hands-on course will take you from beginner to expert in using Ollama, a platform designed for running local LLM models. You’ll learn how to set up and customize models, create a ChatGPT-like interface, and build private applications using Python—all from the comfort of your system.
Why is this course important?
In a world where data privacy is growing, running LLMs locally ensures your data stays on your machine. This enhances data security and allows you to customize models for specialized tasks without external dependencies or additional costs.
You’ll engage in practical activities like building custom models, developing RAG applications that retrieve and respond to user queries based on your data, and creating interactive interfaces.
Each section has real-world applications to give you the experience and confidence to build your local LLM solutions.
What you’ll learn
- Install and configure Ollama on your local system to run large language models privately.
- Customize LLM models to suit specific needs using Ollama’s options and command-line tools.
- Execute all terminal commands necessary to control, monitor, and troubleshoot Ollama models.
- Set up and manage a ChatGPT-like interface, allowing you to interact with models locally.
- Utilize different model types—including text, vision, and code-generating models—for various applications.
- Create custom LLM models from a Modelfile file and integrate them into your applications.
- Build Python applications that interface with Ollama models using its native library and OpenAI API compatibility.
- Develop Retrieval-Augmented Generation (RAG) applications by integrating Ollama models with LangChain.
- Implement tools and function calling to enhance model interactions for advanced workflows.
- Set up a user-friendly UI frontend to allow users to interface and chat with different Ollama models.
Table of Contents
Introduction
1 Introduction & What Will Your Learn
2 Course Prerequisites
3 Please WATCH this DEMO
Development Environment Setup
4 Development Environment Setup
Download Code and Resources
5 Download Source code and Resources
Ollama Deep Dive – Introduction to Ollama and Setup
6 Ollama Deep Dive – Ollama Overview – What is Ollama and Advantages
7 Ollama Key Features and Use Cases
8 System Requirements & Ollama Setup – Overview
9 Download and Setup Ollama and Llam3.2 Model – Hands-on & Testing
10 Ollama Models Page – Full Overview
11 Ollama Model Parameters Deep Dive
12 Understanding Parameters and Disk Size and Computational Resources Needed
Ollama CLI Commands and the REST API – Hands-on
13 Ollama Commands – Pull and Testing a Model
14 Pull in the Llava Multimodal Model and Caption an Image
15 Summarization and Sentiment Analysis & Customizing Our Model with the Modelfile
16 Ollama REST API – Generate and Chat Endpoints
17 Ollama REST API – Request JSON Mode
18 Ollama Models Support Different Tasks – Summary
Ollama – User Interfaces for Ollama Models
19 Different Ways to Interact with Ollama Models – Overview
20 Ollama Model Running Under Msty App – Frontend Tool – RAG System Chat with Docs
Ollama Python Library – Using Python to Interact with Ollama Models
21 The Ollama Python Library for Building LLM Local Applications – Overview
22 Interact with Llama3 in Python Using Ollama REST API – Hands-on
23 Ollama Python Library – Chatting with a Model
24 Chat Example with Streaming
25 Using Ollama show Function
26 Create a Custom Model in Code
Ollama Building LLM Applications with Ollama Models
27 Hands-on Build a LLM App – Grocery List Categorizer
28 Building RAG Systems with Ollama – RAG & LangChain Overview
29 Deep Dive into Vectorstore and Embeddings – The Whole Picture – Crash course
30 PDF RAG System Overview – What we’ll Build
31 Setup RAG System – Document Ingestion & Vector Database Creation and Embeddings
32 RAG System – Retrieval and Querying
33 RAG System – Cleaner Code
34 RAG System – Streamlit UI
Ollama Tool Function Calling – Hands-on
35 Function Calling (Tools) Overview
36 Setup Tool Function Calling Application
37 Categorize Items Using the Model and Setup the Tools List
38 Tools Calling LLM Application – Final Product
Final RAG System with Ollama and Voice Response
39 Voice RAG System – Overview
40 Setup EleveLabs API Key and Load and Summarize the Document
41 Ollama Voice RAG System – Working!
42 Adding ElevenLab Voice Generated Reading the Response Back to Us
Wrap up
43 Wrap up – What’s Next
Resolve the captcha to access the links!