AI Bites Courses

Building a Local Voice Assistant Like Alexa Using LLMs and Python

Learn to build a voice-controlled AI assistant using Python, Streamlit, LangChain, and Ollama in under 100 lines of code. Create your own local version of Alexa through hands-on coding.

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

Meta MovieGen: Understanding Video Generation Model Architecture and Training

Dive into Meta's MovieGen AI model's architecture, training pipeline, and innovative features for revolutionary video generation, including temporal auto-encoding and superresolution techniques.

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

Kolmogorov-Arnold Networks: Understanding KAN Architecture and Comparison with MLPs

Dive into Kolmogorov-Arnold Networks (KAN), a groundbreaking alternative to Multi-Layer Perceptrons, exploring its architecture, implementation, and potential advantages in neural network development.

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

Building a RAG Application Using LangFlow and Streamlit - A Minimal Coding Tutorial

Master building a RAG-powered chat application using LangFlow and Streamlit, focusing on minimal code implementation and creating an AI system capable of explaining other AI models.

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

Fine-tuning Gemma Models with PEFT and LoRA Using HuggingFace Datasets

Master parameter-efficient fine-tuning techniques for Gemma 2B model using PEFT and LoRA, with hands-on code implementation and custom dataset creation for optimized model training.

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

OpenAI Swarm Framework: Understanding Routines, Handoffs, and Agents with Code Examples

Dive into OpenAI's Swarm framework to understand routines, handoffs, and agents through practical code examples and implementation strategies for building sophisticated AI solutions.

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

Improving RAG Pipelines with Contextual Information Retrieval

Master advanced RAG techniques by exploring hybrid approaches combining semantic embeddings with TF-IDF and BM25, plus learn about Anthropic's Contextual Retrieval method for enhanced performance.

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

Qwen 2.5 Coder: Building Coding Agents Through Reasoning and Code Generation

Discover how Qwen2.5 Coder combines reasoning with code generation capabilities, exploring its architecture, training methodology, and performance metrics for building advanced coding agents.

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

OpenAI O1 Preview: Understanding AI Reasoning Models and Chain of Thought

Explore OpenAI's groundbreaking o1 preview model and its advanced reasoning capabilities for solving complex puzzles, mathematical problems, and coding challenges through detailed examples and practical applications.

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

Model Router: Choosing the Right AI Model Using NotDiamond API

Discover how to effectively select and implement AI models using NotDiamond's model routing API, comparing top models like GPT-4, Claude 3, and Gemini for optimal task-specific performance.

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

Segment Anything 2 (SAM2) - Video Segmentation Model Overview and Architecture

Dive into Meta's SAM2 technology, exploring how this advanced model extends image segmentation capabilities to videos through memory encoding, attention mechanisms, and the groundbreaking SA-V dataset.

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

Chunking Strategies for Retrieval Augmented Generation (RAG) with LangChain and LlamaIndex

Master text chunking techniques for RAG systems using LangChain and LlamaIndex, covering fixed-size, recursive, document, and semantic approaches to optimize LLM performance.

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

XLSTM: Understanding Extended LSTMs with sLSTM and mLSTM Architecture

Delve into the evolution of LSTM networks, exploring how XLSTM's innovative sLSTM and mLSTM components enable parallel processing and compete with transformers in sequence-related tasks.

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

Making LLMs Fully Utilize Context - A Data-Driven Approach

Discover how to enhance LLM context utilization through Microsoft's data-driven approach, exploring information-intensive training methods and practical solutions for improved context awareness and reasoning capabilities.

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

Optimizing LLM Pipelines with DsPy - Part 2

Dive into optimizing LLM pipelines by implementing multi-hop question-answering with DsPy framework, featuring Baleen pipeline and Bootstrap Few Shot algorithm optimization techniques.

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