Sam Witteveen Courses

Exploring Gemini 1.5 Pro: Large Context Window and Multimodal Capabilities

Explore Gemini 1.5's capabilities with a 1 million token context window through demos on document querying, code writing, and multimodal processing of video and images.

• YouTube
• 13 minutes
• On-Demand
• Free Video

Image Annotation with LLaVA and Ollama

Learn to annotate images using LLava 1.6 and Ollama. Explore file handling, image loading, API integration, and data management in this practical tutorial on building an image captioning application.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Gemini 1.5 Pro for Video Analysis - Exploring AI-Powered Video Understanding

Explore Gemini 1.5 Pro's video analysis capabilities through a practical demonstration, showcasing its ability to summarize, extract information, and generate content from a 50-minute talk.

• YouTube
• 19 minutes
• On-Demand
• Free Video

LangGraph Crash Course - Building LLM Agents with Code Examples

Explore LangGraph for building LLM agents: learn about StateGraph, nodes, edges, and practical implementations with code examples and tutorials.

• YouTube
• 39 minutes
• On-Demand
• Free Video

Ollama: Libraries, Vision Models, and OpenAI Compatibility Updates

Explore Ollama's new features: Python and JavaScript libraries, vision models, and OpenAI API compatibility. Hands-on demo showcases practical applications and integration possibilities.

• YouTube
• 18 minutes
• On-Demand
• Free Video

Moshi: Advanced AI Conversational System - Overview and Setup

Explore Moshi, an advanced AI conversational system. Discover its speech processing capabilities, real-time interactions, and unique components. Learn about its development, technology, and local setup process.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Explaining OpenAI's O1 Reasoning Models - Analysis and Demonstration

Explore OpenAI's o1 models: their reasoning capabilities, trade-offs, and performance in various tasks. Includes demos and pricing information for practical understanding.

• YouTube
• 27 minutes
• On-Demand
• Free Video

CrewAI August Update: Planning Steps, Training, and Advanced Features - Explained

Explore CrewAI's latest updates: enhanced planning, agent training, and advanced features for improved AI performance. Practical demo and code examples included.

• YouTube
• 23 minutes
• On-Demand
• Free Video

Prompt Poet - Character AI's Framework for Assembling ML Chat Prompts

Learn Character AI's Prompt Poet framework for efficient prompt assembly and injection. Explore its application in LLM chat formats and discover techniques for enhancing AI interactions.

• YouTube
• 20 minutes
• On-Demand
• Free Video

AgentWrite with LangGraph - Converting and Extending LLM Agents

Learn to convert AgentWrite to a LangGraph agent, exploring dataset generation, flow, prompts, and potential extensions for enhanced AI writing capabilities.

• YouTube
• 19 minutes
• On-Demand
• Free Video

LongWriter: Generating Extended Text with Large Language Models

Explore LongWriter: an innovative model for generating extensive text in a single pass, with demos, paper insights, and practical applications using various LLMs.

• YouTube
• 13 minutes
• On-Demand
• Free Video

Microsoft's Phi 3.5 - Latest Small Language Models Overview

Explore Microsoft's latest Phi 3.5 models, including Mini, MoE, and Vision variants. Learn about their capabilities, performance, and practical applications through demonstrations and code examples.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Getting JSON Output from Gemini

Explore techniques for generating structured JSON outputs with Gemini API, including image-based JSON extraction and Pydantic class integration for enhanced data handling.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Agentic Information Extraction with Structured Outputs in JSON

Explore OpenAI's new feature for guaranteed structured JSON outputs in LLMs, with a demo and discussion on its applications, availability, and limitations.

• YouTube
• 16 minutes
• On-Demand
• Free Video

Unveiling Meta's Impressive CV Model - SAM 2: Segment Anything in Images and Videos

Explore Meta's advanced CV model SAM 2, featuring unified architecture for image and video segmentation. Learn its capabilities through demos and code samples for enhanced visual understanding.

• YouTube
• 12 minutes
• On-Demand
• Free Video