Data Centric Courses

Meta-Prompting Technique for Building High-Level AI Agents

Explore meta-prompting techniques to build flexible AI agents. Learn implementation, web search integration, and evaluate strengths and weaknesses of this powerful prompt engineering approach.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

AI Agents: Limitations in Intelligence and Planning - A Chess Experiment

Explore AI agents' limitations through chess tests, revealing planning effectiveness and crucial considerations for AI development.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

LangGraph AI Agent Upgrade: Integrating Groq, Gemini, and Chainlit Front End

Upgrade a LangGraph AI agent with Groq, Gemini, and Claude integrations, fix bugs, and create a stylish Chainlit front-end for web searching capabilities similar to Perplexity.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

LangGraph Simplified: Master Custom AI Agent Creation - Web Search Agent Tutorial

Simplify LangGraph concepts and create a custom web search AI agent through a Python tutorial. Learn core principles and practical implementation for AI development.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Comparing Open Source AI Agents to Perplexity AI - Testing Codestral, GPT4o, and Mixtral

Benchmark open-source AI models against Perplexity AI using a custom web search agent. Compare Codestral, Mixtral, and GPT4o performance in handling complex queries and multi-hop questions.

• YouTube
• 1 hour 37 minutes
• Self-Paced
• Free Video

Comparing LLAMA 3, Phi 3, and GPT-3.5 Turbo AI Agents for Web Search Performance

Benchmark open-source AI models against Perplexity AI in web search performance. Compare Llama 3 70b, GPT-3.5 turbo, and Phi-3 medium using a custom web search agent.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Comparing Ollama Local WebSearch Agent with Llama 3 8B to Perplexity AI

Benchmark Llama 3 8b local web search agent against Perplexity AI. Compare performance, explore capabilities, and analyze results across diverse test questions.

• YouTube
• 50 minutes
• Self-Paced
• Free Video

Building a Custom AI Agent with Llama 3 70B and Runpod - Compatible with Hugging Face LLMs

Develop a custom AI agent using Llama 3 70b on Runpod with vLLM. Learn deployment, memory management, and integration techniques for scalable AI projects.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

Build Your Own Local "Perplexity" with Ollama - Deep Dive

Develop a custom web search agent running locally using Ollama and Llama 3. Learn to build, test, and compare with different models in this comprehensive technical deep dive.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

Agency Swarm: Developing a Web Search Agent and Comparison with CrewAI and AutoGen

Explore Agency Swarm's framework for developing AI agents, comparing it to CrewAI and AutoGen. Learn to create a web search agent and discover the tool's innovative features.

• YouTube
• 48 minutes
• Self-Paced
• Free Video

Building Custom AI Agents: Beyond CrewAI and AutoGen

Develop a custom web search AI agent in Python. Learn why building your own agents can be more effective than using existing frameworks for AI and multi-agent workflows.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Why I'm Staying Away from Crew AI - A Critical Analysis

Explore limitations of Crew AI for production, understand multi-hop questions, and learn alternative approaches for building AI applications. Gain insights on future multi-agent frameworks.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Why Retrieval Augmented Generation (RAG) is Overrated

Explore the limitations of Retrieval Augmented Generation (RAG), including hallucinations, complexity, and cost. Learn practical approaches to make RAG more effective in AI applications.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

AutoGen: Hype vs. Reality - Limitations for Real-World Applications

Explore AutoGen's capabilities and limitations in multi-agent workflows, distinguishing hype from reality. Gain insights into its potential and current constraints for real-world applications.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

Deploy Mixtral - Quick Setup for LangChain, AutoGen, Haystack, and LlamaIndex

Learn to deploy Mixtral quickly using Runpod and vLLM, create an OpenAI-like endpoint, and integrate it with LangChain for a chatbot. Explore setup for other frameworks like AutoGen and Haystack.

• YouTube
• 23 minutes
• Self-Paced
• Free Video