Yeyu Lab

@UCFosLT-CZzauB5gXQPc2a0g - 4.9K subscribers

Hi there, I am Yeyu (Wenbo) Huang. 🏂 www.yeyulab.com Your subscription and support fuel my creations and helps me share more exclusive codes, tricks, demos, and tutorials that take you to embark on this innovation journey!🚢

Home Videos Live Playlists

Dolphin v2: Free Alternative to Document Parsing Understanding APIs of GPT, Claude, Gemini...

Dolphin v2: Free Alternative to Document Parsing Understanding APIs of GPT, Claude, Gemini... Yeyu Lab

1.2K views - 4 weeks ago

Context Engineering for AI Agents: A Guide for SKILL-Based Implementation

Context Engineering for AI Agents: A Guide for SKILL-Based Implementation Yeyu Lab

513 views - 1 month ago

How to Architect Context-Aware Multi-agents Using Google ADK with Practice

How to Architect Context-Aware Multi-agents Using Google ADK with Practice Yeyu Lab

1.1K views - 1 month ago

How to Build a Real-time Graph-RAG Agent for Super-Fast Knowledge Search and Updates

How to Build a Real-time Graph-RAG Agent for Super-Fast Knowledge Search and Updates Yeyu Lab

1.2K views - 3 months ago

How to Build Multimodal Live Agents for Proactive Monitoring with ADK, Gemini 3 and Live API

How to Build Multimodal Live Agents for Proactive Monitoring with ADK, Gemini 3 and Live API Yeyu Lab

2K views - 3 months ago

How to Build Realtime Voice RAG Agents with ADK Web UI and File Search

How to Build Realtime Voice RAG Agents with ADK Web UI and File Search Yeyu Lab

2.4K views - 3 months ago

How to Create a No-Code Visual Workflow Builder for AI Agents

How to Create a No-Code Visual Workflow Builder for AI Agents Yeyu Lab

796 views - 3 months ago

Use Google's ADK to Build a Multi-Agent System with Live Voice and Rich Content Output

Use Google's ADK to Build a Multi-Agent System with Live Voice and Rich Content Output Yeyu Lab

2.4K views - 4 months ago

Upgrade Your Gemini Realtime Assistant with Live Illustrations Using Nano Banana

Upgrade Your Gemini Realtime Assistant with Live Illustrations Using Nano Banana Yeyu Lab

816 views - 5 months ago

How to Build a Custom Storybook Generator that Replicates Gemini's Storybook

How to Build a Custom Storybook Generator that Replicates Gemini's Storybook Yeyu Lab

645 views - 6 months ago

How Easy to Build a Real-Time Multimodal AI Assistant with LiveKit

How Easy to Build a Real-Time Multimodal AI Assistant with LiveKit Yeyu Lab

12.3K views - 6 months ago

How to Build Modular and Streaming Gemini Applications with GenAI Processors

How to Build Modular and Streaming Gemini Applications with GenAI Processors Yeyu Lab

878 views - 7 months ago

It's SO Easy to Use ElevenLabs to Build a Multimodal Voice Agent

It's SO Easy to Use ElevenLabs to Build a Multimodal Voice Agent Yeyu Lab

1.4K views - 7 months ago

Building a Gemini Powered Chrome Extension with Live Voice Assistant

Building a Gemini Powered Chrome Extension with Live Voice Assistant Yeyu Lab

2.2K views - 8 months ago

How to Create Realtime Multimodal Apps with Gemini in Google AI Studio by Javascript

How to Create Realtime Multimodal Apps with Gemini in Google AI Studio by Javascript Yeyu Lab

3.6K views - 8 months ago

Building a Realtime Multimodal App Locally Deployed with Phi-4 and Kokoro

Building a Realtime Multimodal App Locally Deployed with Phi-4 and Kokoro Yeyu Lab

2.1K views - 9 months ago

Gemini Live API FINALLY Breaks Realtime Session Limits! - And Other Gemini's Important Updates

Gemini Live API FINALLY Breaks Realtime Session Limits! - And Other Gemini's Important Updates Yeyu Lab

4.9K views - 10 months ago

Building a Gemini Realtime Learning Assistant with Long-Term Memory

Building a Gemini Realtime Learning Assistant with Long-Term Memory Yeyu Lab

3.7K views - 11 months ago

Clone the Gemini Multimodal Realtime App Locally with Gemma 3, Whisper, Kokoro

Clone the Gemini Multimodal Realtime App Locally with Gemma 3, Whisper, Kokoro Yeyu Lab

3.3K views - 11 months ago

Build a Fully Local Multimodal Realtime App with Open Source Models

Build a Fully Local Multimodal Realtime App with Open Source Models Yeyu Lab

5.3K views - 11 months ago

Building a Multimodal Realtime App With Gemini 2.0 API and Next.js: Audio, Video, and Transcript

Building a Multimodal Realtime App With Gemini 2.0 API and Next.js: Audio, Video, and Transcript Yeyu Lab

5.9K views - 1 year ago

Gemini 2.0: How to Build a Serverless Android App with Real-time Streaming by Multimodal Live API

Gemini 2.0: How to Build a Serverless Android App with Real-time Streaming by Multimodal Live API Yeyu Lab

2.9K views - 1 year ago

How to Build a Realtime Gemini 2.0 Mobile App for Voice Chat with Camera and Images

How to Build a Realtime Gemini 2.0 Mobile App for Voice Chat with Camera and Images Yeyu Lab

5.5K views - 1 year ago

Talk to Your Documents: Create a Real-Time RAG Assistant with Gemini 2.0 Multimodal Live API

Talk to Your Documents: Create a Real-Time RAG Assistant with Gemini 2.0 Multimodal Live API Yeyu Lab

6.1K views - 1 year ago

How to Build a Real-Time Gemini 2.0 Learning Assistant with an Interactive Canvas

How to Build a Real-Time Gemini 2.0 Learning Assistant with an Interactive Canvas Yeyu Lab

2.8K views - 1 year ago

Hot Update! Build a Realtime Screen Sharing Assistant with VOICE and TEXT by Gemini 2.0

Hot Update! Build a Realtime Screen Sharing Assistant with VOICE and TEXT by Gemini 2.0 Yeyu Lab

4.8K views - 1 year ago

How to Build a Real-time Screen Sharing Assistant with Gemini 2.0 Multimodal Live API

How to Build a Real-time Screen Sharing Assistant with Gemini 2.0 Multimodal Live API Yeyu Lab

9.6K views - 1 year ago

Build a Real-time Voice & Video Chat App with Function Calling by Gemini 2.0 Multimodal Live API

Build a Real-time Voice & Video Chat App with Function Calling by Gemini 2.0 Multimodal Live API Yeyu Lab

6.2K views - 1 year ago

Use Gemini 2.0 to Build a Realtime Chat App with Multimodal Live API

Use Gemini 2.0 to Build a Realtime Chat App with Multimodal Live API Yeyu Lab

11.7K views - 1 year ago

How to Use Llama3.3 to Build a Local Agent Workflow

How to Use Llama3.3 to Build a Local Agent Workflow Yeyu Lab

3.3K views - 1 year ago

How to Create a Stunning Web UI for CrewAI App with Taipy

How to Create a Stunning Web UI for CrewAI App with Taipy Yeyu Lab

1.8K views - 1 year ago

(Updated) How to Create an Interactive Web UI for CrewAI Applications

(Updated) How to Create an Interactive Web UI for CrewAI Applications Yeyu Lab

7.6K views - 1 year ago

How to Fine-tune the Llama 3.2 for Reasoning Capabilities at Lowest Cost

How to Fine-tune the Llama 3.2 for Reasoning Capabilities at Lowest Cost Yeyu Lab

1.5K views - 1 year ago

Advanced Swarm Tutorial: RAG Agent, Orchestration and Web UI

Advanced Swarm Tutorial: RAG Agent, Orchestration and Web UI Yeyu Lab

1.1K views - 1 year ago

How to Build a Web UI for an OpenAI's Swarm Application

How to Build a Web UI for an OpenAI's Swarm Application Yeyu Lab

1.3K views - 1 year ago

Introducing AgentKit: A Lightweight, Easy-to-Learn Multi-Agent Framework

Introducing AgentKit: A Lightweight, Easy-to-Learn Multi-Agent Framework Yeyu Lab

668 views - 1 year ago

How to Implement Function Calling for Llama 3.2 1B/3B Lightweight Models

How to Implement Function Calling for Llama 3.2 1B/3B Lightweight Models Yeyu Lab

4.1K views - 1 year ago

How to Use Llama 3.2 to Create Vision Apps and Multimodal Agents in AutoGen

How to Use Llama 3.2 to Create Vision Apps and Multimodal Agents in AutoGen Yeyu Lab

2.8K views - 1 year ago

How to Make AutoGen Agents Always Generate Structured Data by Using Instructor

How to Make AutoGen Agents Always Generate Structured Data by Using Instructor Yeyu Lab

1.1K views - 1 year ago

What prompt techniques we can learn from the drama of Reflection 70B

What prompt techniques we can learn from the drama of Reflection 70B Yeyu Lab

267 views - 1 year ago

Exploring Llama-Agents with Code Walkthrough

Exploring Llama-Agents with Code Walkthrough Yeyu Lab

324 views - 1 year ago

Use Mesop to Develop UI for CrewAI App

Use Mesop to Develop UI for CrewAI App Yeyu Lab

876 views - 1 year ago

Create a Multi-Agent App with Mesop UI

Create a Multi-Agent App with Mesop UI Yeyu Lab

3.3K views - 1 year ago

How to Build an Image Creator Agent for the AutoGen Application

How to Build an Image Creator Agent for the AutoGen Application Yeyu Lab

581 views - 1 year ago

How to Create APIs for AutoGen

How to Create APIs for AutoGen Yeyu Lab

1.5K views - 1 year ago

How to Create an Interactive Web UI for CrewAI Applications By Panel

How to Create an Interactive Web UI for CrewAI Applications By Panel Yeyu Lab

8.7K views - 1 year ago

How to Implement a Simple UI for CrewAI applications

How to Implement a Simple UI for CrewAI applications Yeyu Lab

6.8K views - 1 year ago

Best Groq Practice - Making a Voice Assistant with Human Reaction Speed

Best Groq Practice - Making a Voice Assistant with Human Reaction Speed Yeyu Lab

1.7K views - 1 year ago

AutoGen + Custom Model + Gemma (or Any Model), Here is the Ultimate Solution

AutoGen + Custom Model + Gemma (or Any Model), Here is the Ultimate Solution Yeyu Lab

1.8K views - 1 year ago

AutoGen + Ollama + Gemma: How to Create LLM Agents Locally

AutoGen + Ollama + Gemma: How to Create LLM Agents Locally Yeyu Lab

2.2K views - 1 year ago

Is Gemma Capable of Building Multi-agent Applications in AutoGen?

Is Gemma Capable of Building Multi-agent Applications in AutoGen? Yeyu Lab

917 views - 2 years ago

2-bit Quantization is Magical! See How to Run Mixtral-8x7B on Free-tier Colab

2-bit Quantization is Magical! See How to Run Mixtral-8x7B on Free-tier Colab Yeyu Lab

875 views - 2 years ago

OpenRouter - Use The LLM Inference API with the Lowest Cost

OpenRouter - Use The LLM Inference API with the Lowest Cost Yeyu Lab

6.7K views - 2 years ago

CrewAI - A Smartly Designed Multi-agent Framework for LLM App Development

CrewAI - A Smartly Designed Multi-agent Framework for LLM App Development Yeyu Lab

3.7K views - 2 years ago

AutoGen Technique - Use `Description` Field to Manage the Conversation Between Multiple Agents

AutoGen Technique - Use `Description` Field to Manage the Conversation Between Multiple Agents Yeyu Lab

1.3K views - 2 years ago

AutoGen + Function Calling + Open Source LLMs, Here is How

AutoGen + Function Calling + Open Source LLMs, Here is How Yeyu Lab

7.6K views - 2 years ago

Use Open Source LLMs in AutoGen powered by Fireworks AI, without GPU/CPU

Use Open Source LLMs in AutoGen powered by Fireworks AI, without GPU/CPU Yeyu Lab

2.3K views - 2 years ago

How to Use Open Source LLMs in AutoGen Powered by vLLM

How to Use Open Source LLMs in AutoGen Powered by vLLM Yeyu Lab

5.6K views - 2 years ago

AutoGen + Panel Ep.3 - Web UI for Multi-agent with Document Retrieval

AutoGen + Panel Ep.3 - Web UI for Multi-agent with Document Retrieval Yeyu Lab

6K views - 2 years ago

Create Full Function UI for AutoGen Powered by Panel (Human Input Enabled)

Create Full Function UI for AutoGen Powered by Panel (Human Input Enabled) Yeyu Lab

8.9K views - 2 years ago