In this video, we will do a comparison between GEMINI and GPT-4 Beyond the benchmarks results reported in the technical report released with GEMINI. Watch this video to see how GPT-4 actually compares with GEMINI. 

Want to Follow:
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
▶️️ Subscribe: https://www.youtube.com/@engineerprompt?sub_confirmation=1


Want to Support:
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Support my work on Patreon: https://www.patreon.com/PromptEngineering

Need Help? 
📧 Business Contact: engineerprompt@gmail.com
💼Consulting: https://calendly.com/engineerprompt/consulting-call

Join this channel to get access to perks:
https://www.youtube.com/channel/UCDq7SjbgRKty5TgGafW8Clg/join

LINKS:
GEMINI Technical Report: https://tinyurl.com/4zd34pbu
GPT-4 Tests: 
https://chat.openai.com/c/bb60fd4c-a18b-49a4-b662-4019a7ea0831
https://chat.openai.com/c/5d8fb631-df92-4ec1-962b-7b84be84cfa0




All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

GEMINI vs. GPT-4 | Which One Is Actually Better? Testing Beyond Benchmark

Gemini Pro API access is here. In this video, we will look at how to get started with it and use its vision capabilities for absolutely free. 


LINKS:
Colab: https://tinyurl.com/bd3h2b4c
Google AI Studio: https://makersuite.google.com/
API Docs: https://ai.google.dev/tutorials/python_quickstart
Embeddings: https://ai.google.dev/docs/embeddings_guide
Safety Settings: https://ai.google.dev/docs/safety_setting_gemini

Want to Follow:
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
▶️️ Subscribe: https://www.youtube.com/@engineerprompt?sub_confirmation=1

Want to Support:
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Support my work on Patreon: https://www.patreon.com/PromptEngineering

Need Help? 
📧 Business Contact: engineerprompt@gmail.com
💼Consulting: https://calendly.com/engineerprompt/consulting-call

Join this channel to get access to perks:
https://www.youtube.com/channel/UCDq7SjbgRKty5TgGafW8Clg/join

Timestamps:
[00:00] Intro
[00:43] Gemini Pro API Pricing and Usage
[2:27] Getting Started with Gemini Pro
[3:12] Exploring Gemini Pro's Features
[05:46] Using Gemini Pro in Google Colab
[12:55] Gemini Pro's Chat Model
[15:26] Gemini Pro's Embedding Model
[17:21] Controlling Safety Settings in Gemini Pro
[19:04] Working with Gemini Pro Vision Model


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Getting Started with Gemini Pro API on Google AI Studio

Learn how to use the newly released Gemini Pro API with LangChain for building chatbots, multimodal applications and RAG pipeline. 

Want to Follow:
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
▶️️ Subscribe: https://www.youtube.com/@engineerprompt?sub_confirmation=1

Want to Support:
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Support my work: https://www.patreon.com/PromptEngineering

Need Help? 
📧 Business Contact: engineerprompt@gmail.com
💼Consulting: https://calendly.com/engineerprompt/consulting-call

Join this channel to get access to perks:
https://www.youtube.com/channel/UCDq7SjbgRKty5TgGafW8Clg/join

LINKS:
Google Colab: https://tinyurl.com/28bw3ntv
Gemini Pro API: https://youtu.be/64Ldwi9YU4I
Chat with your Documents: https://youtu.be/RIWbalZ7sTo
LocalGPT: https://youtu.be/lbFmceo4D5E


TIMESTAMPS: 
[00:00] Gemini Pro API with Langchain
[00:44] Setting Up the Environment
[02:06] Interacting with Gemini Pro API
[03:50] Using Gemini Pro API with Langchain Framework
[05:00] Working with Images 
[06:20] Creating Multimodal Systems with Gemini Pro API
[07:58] Creating a Chat with Document System
[08:39] In-Context Information Retrieval Approach
[12:56] RAC Pipeline Approach
[16:32] Conclusion


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

GEMINI Pro with LangChain | Chat, MultiModal and Chat with your Documents

CrewAI is an autonomous Agents framework that enable you to build a crew of agents to accomplish complex tasks. It's very similar to AutoGen in functionality. You will also learn how to use the free Gemini API from Google with CrewAI. 

🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

LINKS:
Google Colab: http://tinyurl.com/3hmzdxyp
CrewAI Github: https://github.com/joaomdmoura/crewai
CrewAI GPT: http://tinyurl.com/bdcmwnwn


Chapters:
[00:00] Introduction to Crew AI
[01:6] Creating a Chatbot with Crew AI
[01:55] Setting Up Crew AI in Google Colab
[04:19] Defining Agents and Tasks in Crew AI
[07:05] Creating a Crew and Assigning Tasks
[07:45] Understanding the Internal Working of Crew AI
[10:00] Final Thoughts on Crew AI

CrewAI - Your Own Team of Autonomous Agents

New Bard has surpassed GPT-4 on Chatbot Arena. 

🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼 Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

LINKS:
Leaderboard: https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard
https://twitter.com/lmsysorg/status/1750921228012122526
Different versions of Gemini: https://twitter.com/lmsysorg/status/1749818447276671255
Chatbot Arena: https://chat.lmsys.org/

TIMESTAMPS:
[00:00] What's New in Bard
[00:54] Understanding the Chat Arena Leaderboard
[02:40] Exploring Different Versions of Gemini Pro
[03:43] Bard Gemini Pro API had Internet Access
[06:35] Comparing Gemini Pro and GPT 4 Turbo


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

🔥 New Gemini Pro Better than GP-4? Huge Performance Boost on ⚔️ Chatbot Arena ⚔️

Google Gemma is here, their major open weights model to compete with Llama from Meta. 

🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  


LINKS:
Gemma: https://blog.google/technology/developers/gemma-open-models/
Getting Started Notebook: https://colab.research.google.com/github/google/generative-ai-docs/blob/main/site/en/gemma/docs/get_started.ipynb


TIMESTAMPS:
[00:00] Introduction to Gemma
[02:46] Technical Details and Performance of Gemma Models
[05:54] Training Techniques and Performance Comparison
[07:09] Licensing of Gemma Models

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Google Gemma Released | First look at the Technical Report

In this video, we will look at a comparison between Google's Gemma and Mistral-7B-Instruct LLMs on our custom tests. The tests will surprise you. 


🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  


LINKS:
Where to test Gemma:
Nvidia Playground: http://tinyurl.com/p6fyeh3n
Perplexity-labs: https://labs.perplexity.ai/
HuggingFaceChat: https://huggingface.co/chat/

TIMESTAMPS:
[00:00] Introduction
[00:29] Testing Gemma: Options and Comparisons
[02:04] Real Life Testing: Mathematical Reasoning
[03:45] Logical Reasoning
[06:20] Keeping track of multiple objects
[07:17] Ethical Boundaries of AI Models
[08:04] AI Alignment and Ethical Dilemmas
[09:34] AI Investment Advice
[10:44] Programming Abilities



All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

How Bad is Gemma Compared to Mistral?

In this video, we will have a first look at Gemini 1.5 Pro and use it as coding assistant. 

🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

LINKS:
Google AI Studio: https://aistudio.google.com/

Signup for Advanced RAG:
https://tally.so/r/3y9bb0


TIMESTAMPS:
[00:00] Gemini 1.5 Pro 1M Tokens
[02:35] Uploading files to Gemini
[03:45] Putting it to the Test


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini 1.5 Pro - Coding Assistant with 1M tokens

Just checked out Google's new Gemini Flash at Google I/O. It's a super-fast AI model designed for handling big tasks – think processing videos, audios, or huge codebases, all while keeping costs low. I put it through its paces against giants like GPT 3.5 and GPT 4.0, looking at performance, costs, and how it handles real-world tasks. I even tried confusing it with tricky questions and coding challenges in Google AI Studio. Spoiler: it's not perfect, but for speed and efficiency on a budget? Pretty cool stuff. Stick around to see how Gemini Flash holds up in the AI arena!


🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Advanced RAG:
https://tally.so/r/3y9bb0


LINKS:
https://aistudio.google.com/


TIMESTAMPS:
00:00 Introducing Gemini Flash: Google's Answer to GPT-4
00:53 Why Choose Gemini Flash? Performance and Cost Analysis
02:20 Hands-On Testing: Unveiling Gemini Flash's Capabilities
03:05 Exploring Safety Features and Customization
03:44 Prompt-Based Testing: Analyzing Model Responses
12:11 Advanced Testing: Contextual Understanding and Mathematics
15:30 Programming Challenges: Assessing Gemini Flash's Coding Prowess



All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

First Impressions of Gemini Flash 1.5 - The Fastest 1 Million Token Model

A sneak peek of voice-to-voice chat assistant. 


🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Advanced RAG:
https://tally.so/r/3y9bb0


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Creating J.A.R.V.I.S.

In this video, we look into the latest updates to the Gemini models, covering both the Pro and Flash versions. We'll explore practical use cases, focusing on building a customer support agent that performs sequential and parallel function calls. 

#gemini  #google  #deepmind  


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  


LINKS: 
https://tinyurl.com/266ru3hr

TIMESTAMPS:
00:00 Gemini Models Update Overview
00:23 Performance Improvements and Rankings
00:46 Gemini Flash: A Sweet Spot for Quality and Price
01:43 Understanding Function Calling
03:32 Building a Customer Support Agent
04:00 Setting Up the Environment
04:53 Implementing Basic Functions
06:55 Executing Function Calls
10:33 Handling Sequential and Parallel Function Calls
11:48 Advanced Function Call Management
18:24 Conclusion and Final Thoughts


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini Flash is SURPRISINGLY Good for Agents and Function Calling

In this video, I walk you through Mesop, Google's newly open-sourced tool for creating web UIs using pure Python. Similar to Streamlit or Gradio, Mesop lets you build responsive and beautiful UIs quickly. I'll show you how to install Mesop, explore its components, and even create a chatbot using the Gemini API. With powerful state management and flexible components, Mesop makes web development in Python a breeze. Tune in to learn how to get started with Mesop and enhance your projects!


#streamlit #webui

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

LINKS: 
Github: https://github.com/google/mesop
Docs: https://google.github.io/mesop/

TIMESTAMPS:
00:00 Introduction to Mesop
00:43 Getting Started with Mesop
01:10 Understanding Mesop Components
03:09 Building Basic Mesop Applications
06:41 Advanced Mesop Features
10:03 Creating a Chat Application with Mesop
12:52 Conclusion and Future Prospects

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Mesop: Google's UI Framework for Building Web Application

A Deep Dive in to the technical report of Gemma-2. 

LINKS: 
Blogpost: https://tinyurl.com/yc27j2de
LMSys Leaderboard: https://tinyurl.com/bde62dvf
Huggingface blog: https://huggingface.co/blog/gemma2
Where to Try: https://aistudio.google.com/


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


TIMESTAMPS
00:00 Introduction to Gemma 2
00:10 Benchmark Performance
01:25 Technical Report Insights
02:43 Understanding Knowledge Distillation
03:56 Training Process and Techniques
09:18 Prompt Templates and Chatbot Arena
11:54 Speculations and Ablation Studies
13:28 Using Gemma 2 Models
13:49 Conclusion and Next Steps

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Google Gemma-2: Technical Report Deep Dive

Google's Gemini API just added Code Execution (Interpreter). The API can now generate code, execute it on the backend and return you the result. This is really powerful!

LINK:
Code Execution: https://tinyurl.com/2vcdks79
Gemini API: https://tinyurl.com/z6kctkvk
Notebook: https://tinyurl.com/a8bjcz39 


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Google's Gemini API Features
00:11 Understanding Code Execution
00:39 Code Execution in Action: Examples
02:46 Comparing Code Execution and Function Calling
04:47 Limitations and Considerations
06:08 Hands-On with Code Execution
11:24 Advanced Use Cases and Examples
17:08 Pricing and Future Features
17:47 Conclusion and Next Steps

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Introducing Gemini API Code Interpreter (Execution)

Google's Gemini API now supports context caching, aimed at addressing limitations of long context LLMs by reducing processing time and costs. This video explains how to use the caching feature, its impact on performance, and implementation details with examples.

LINKS: 
Context Caching: https://tinyurl.com/4263z4da
Vertex AI: https://tinyurl.com/yex8ua5h
Notebook: https://tinyurl.com/2et8spkf
Pricing: https://ai.google.dev/pricing

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


TIMESTAMPS
00:00 Introduction to Google's Context Caching
00:48 How Context Caching Works
01:00 Setting Up Your Cache
03:07 Cost and Storage Considerations
04:46 Example Implementation
08:57 Creating and Using the Cache
11:06 Managing Cache Metadata
12:53 Conclusion and Future Prospects

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Making Long Context LLMs Usable with Context Caching

In this video, I review the new ColPali paper which suggests using vision models for document retrieval, offering both impressive results and explainability. We'll explore the current challenges with RAG systems, the new approach, the groundbreaking results, and even demo this model. Tune in to see how this innovative method outperforms existing methods and can transform your retrieval processes.


LINKS:
Paper: https://arxiv.org/pdf/2407.01449
Vespa Blog: https://blog.vespa.ai/retrieval-with-vision-language-models-colpali/
Try here: https://huggingface.co/spaces/manu/ColPali-demo
ColBERT VIDEOS:
https://youtu.be/kEgeegk9iqo
https://youtu.be/xTzUn3G9YA0

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


00:00 Introduction to ColPali: A New Approach to Document Retrieval
00:40 Challenges with Existing RAG Systems
02:02 Proposed Solution: Vision Models for Retrieval
02:34 Benchmarking and Performance
05:09 Detailed Architecture of ColPali
08:34 Retrieval Process Explained
13:28 Practical Implementation and Testing
17:05 Conclusion and Future Directions

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

ColPali: Vision Language Models for Efficient Document Retrieval

Google's new Gemma 2 2 billion model, the smallest and most powerful in its class.New release include Shield GEMMA and GEMMAScope, and you can run all of these on device. 

LINKS: 
Blogpost: https://tinyurl.com/3shdwc7w
https://www.interconnects.ai/p/gpt-4o-mini-changed-chatbotarena
https://huggingface.co/blog/gemma-july-update
Gemma-scope: https://tinyurl.com/vv8sdx4e
playground: https://www.neuronpedia.org/gemma-scope#microscope 
Colab: https://tinyurl.com/23akwzvc

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Google's Gemma 2 Model
00:21 Overview of Gemma 2 and Its Variants
01:28 Performance and Controversies
04:04 Technical Specifications and Testing
06:45 Exploring Shield Gemma and GemmaScope


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemma 2 2B: A Small Model Punching Above its Weight

Gemini 1.5 Pro just got a huge upgrade and is now the best model on the chatbot arena leaderboard. It has impressive performance and has a code interpreter behind the API, first of its kind!!!

LINKS: 
Colab: https://tinyurl.com/yu9jvx4y
Leaderboard: https://chat.lmsys.org/?leaderboard
AI Studio: https://aistudio.google.com/

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

TIMESTAMPS
00:00 Google Takes the Lead in LLM Race with Gemini 1.5 Pro
00:57 Exploring Gemini 1.5 Pro's Capabilities
01:25 Hands-On with Google AI Studio
01:35 Testing Gemini 1.5 Pro with Various Prompts
02:55 Understanding Tokenization and Its Impact
04:05 Advanced Prompt Testing and Safety Settings
05:49 Using the Gemini API for Code Execution
07:20 Code Execution Examples and Performance
11:30 Multimodal Capabilities and Image Understanding

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini 1.5 Pro Experimental - New Features with Major Upgrade

In this video, I will show you how to easily integrate AI into your business applications using GPTBots' no-code visual builder. With drag-and-drop functionality, pre-built templates, multiple API integrations, and powerful features, you'll create efficient business chatbots in no time. Check out the link in the description to get started!

GPTBots Platform: https://www.gptbots.ai/?utm_source=kol&kol=Prompt+Engineering

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h


TIMESTAMP:
00:00 Introduction to GPTBots
00:26 Getting Started with GPTBots
01:20 Creating a Simple Bot
02:25 Setting Up the Bot's Identity
03:14 Uploading Knowledge Base
04:32 Testing and Fine-Tuning the Bot
05:44 Integrating External Tools
07:53 Finalizing and Deploying the Bot
09:58 Advanced Features and Team Collaboration


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Custom Chatbots for your Business Needs - No Code Platform

Learn how to build anything with Gemini 1.5 Pro Experimental API. Build Search and RAG tools powering the ReAct Agent. 

LINKS: 
Check out Langtrace: https://langtrace.ai/
Colab: https://tinyurl.com/mr43dc7x
Tavily: https://app.tavily.com/home
AI Studio: https://aistudio.google.com/
Leaderboard: https://chat.lmsys.org/?leaderboard


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Google Gemini 1.5 Pro
00:27 Understanding Agents and Their Capabilities
01:20 Setting Up the Environment
01:44 Installing and Importing Necessary Packages
02:23 Configuring API Keys and LangTrace
04:19 Building the Agent with LangChain
04:54 Creating and Using the RAG Pipeline
08:29 Setting Up Tools for the Agent
10:10 Creating and Testing the Agent
13:41 Agent Performance and Observability


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini Agents are Surprisingly Good

In this video, I explore Google Gemini 1.5 Flash and its latest updates, which significantly enhance PDF processing. I'll show you how this multimodal model can efficiently handle tasks like text extraction, figure counting, and more, all without pre-processing. Plus, I compare it directly with GPT-4 to see how it stacks up. 

LINKS:
Colab: https://tinyurl.com/yeuja5xt
https://aistudio.google.com/
Blog: https://tinyurl.com/mr3fc3np
Context Cache: https://youtu.be/KvwJtleXCtU
Gemini Agents: https://youtu.be/28w5uFiX-po


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

TIMESTAMPS:
00:00 Introduction to Gemini 1.5 Flash for PDF RAG Systems
00:15 Major Announcements and Price Reductions
01:10 Fine-Tuning and PDF Vision Capabilities
02:41 Testing PDF Understanding in Google AI Studio
02:57 Comparing Gemini Flash with GPT-4
03:55 Extracting Information from PDF Files
05:26 Challenges with Traditional RAG Systems
05:54 Reference Extraction and Accuracy
10:16 Multimodal Capabilities and Figure Analysis
12:49 Table Extraction and Complex Data Handling
15:58 Interacting with Gemini Flash via API


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Will the New GEMINI PDF Feature Replace RAG?

Anthropic's new prompt caching with Claude can reduce costs by 90% and latency by 85%. This video explores its similarities and differences with Google's context caching in Gemini models, different use cases, and performance impacts. Learn about practical caching strategies, cost considerations, and whether context caching can replace Retrieval-Augmented Generation (RAG).

LINKS:
Blogpost: https://www.anthropic.com/news/prompt-caching
API Docs: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#caching-tool-definitions
Gemini Context Cache: https://ai.google.dev/gemini-api/docs/caching?lang=python
Notebook: https://github.com/anthropics/anthropic-cookbook/blob/main/misc/prompt_caching.ipynb

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


TIMESTAMPS
00:00 Introduction to Prompt Caching with Claude
00:29 Understanding Prompt Caching Benefits
01:32 Use Cases for Prompt Caching
03:04 Cost and Latency Reductions
05:14 Comparing Claude and Gemini Context Caching
07:45 Best Practices for Effective Caching
11:22 Code Example and Practical Implementation


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Is This the End of RAG? Anthropic's NEW Prompt Caching

Hey there! I introduce Verbi, a modular voice assistant I created with community support. We'll discuss setting up different models for transcription, response generation, and text-to-speech, and explore top API providers like OpenAI, Grok, Eleven Labs, and Cartesia.

LINKS:
Github: https://github.com/PromtEngineer/Verbi

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


00:00 Introduction to Verbi
00:54 Google's Gemini Live Announcement
01:34 Creating a Voice Assistant System
02:50 Introducing Project Verbi
04:35 Setting Up Project Verbi
10:28 Running and Testing Verbi

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Creating Low Latency Voice Agents - Open Source 🗣️🗣️🗣️

Learn how to deploy LLMs via On-Demand GPUs as well as Serverless API Endpoints on Runpod with vLLM. 

LINKS:
Colab: https://tinyurl.com/y82u8jbn
Byadli Github: https://tinyurl.com/mhp2kx86
ColBERT: https://youtu.be/kEgeegk9iqo
ColPali: https://youtu.be/rhJJynv47Pw
https://tinyurl.com/4zb78zcc
https://tinyurl.com/3j97zd9n


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

ColPali: Vision-Based RAG System For Complex Documents

Anthropic has launched a new retrieval mechanism called contextual retrieval, which combines chunking strategies with re-ranking to significantly improve performance. In this video, I explain how this technique enhances retrieval accuracy, including practical implementation steps and benchmark results. Learn how to optimize your RAG systems by adding contextual embeddings, keyword-based BM25 indexing, and re-ranking to achieve state-of-the-art results.


LINKS:
https://www.anthropic.com/news/contextual-retrieval
https://github.com/anthropics/anthropic-cookbook/blob/main/skills/contextual-embeddings/guide.ipynb
https://youtu.be/Fv_j52DDJUE
https://youtu.be/kEgeegk9iqo
https://youtu.be/DI9Q60T_054

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Contextual Retrieval
00:20 Understanding RAG Systems
00:55 Combining Semantic and Keyword Search
01:44 Challenges with Standard RAG Systems
02:48 Anthropic's Contextual Retrieval Approach
03:37 Implementing Contextual Retrieval
07:06 Performance Improvements and Benchmarks
09:02 Best Practices for RAG Systems
12:48 Code Example and Practical Implementation
15:21 Conclusion and Final Thoughts

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

The Best RAG Technique Yet? Anthropic’s Contextual Retrieval Explained!

In this video, we dive into Google's Notebook LM—a powerful AI research assistant that feels like it was built by a startup. Powered by the multimodal Gemini 1.5, Notebook LM goes beyond audio overviews to offer features like handling various file types (PDFs, websites, YouTube videos), generating insightful summaries, and analyzing documents collectively with a 2 million-token context window. We showcase practical examples, including prompt caching and retrieval-augmented generation (RAG) techniques, and explore its ability to create AI-generated podcasts that sound remarkably human. Plus, we discuss how it can craft timelines, study guides, and more to enhance learning and productivity. Join us as we explore this innovative tool's capabilities and potential to transform the way we interact with AI.

LINKS:
https://notebooklm.google/
RAG Videos: https://notebooklm.google.com/notebook/b40ee676-ca07-49d5-acf5-942304de3da5/audio
Prompt/Context Caching: https://notebooklm.google.com/notebook/0ebb3d9e-04f7-464c-91c8-9ab922822c5c/audio



💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

NotebookLM: Its More than AI Podcasts- Your Personalized AI Research Assistant

Can LLMs reason or they are just stochastic parrots which can only generate answers based on its training data. In this video, I test Google's new chatbot model, Gemini Experimental 1114, which currently tops the chatbot arena leaderboard. Using a set of modified thought experiments and puzzles, I explore whether this model can truly reason or if it's mainly relying on pattern recognition. 

LINKS:
https://github.com/cpldcpu/MisguidedAttention

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Gemini Experimental 1114
00:30 Testing Reasoning with Misguided Attention Prompts
02:00 Modified Trolley Problem
04:21 Barber Paradox Challenge
06:34 Schrodinger's Cat Variation
08:38 Monty Hall Problem Twist
11:23 River Crossing Puzzle
14:24 What does this mean? 

All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Can LLMs Reason? Why LLMs Struggle to Think Critically

In this video, I test Google's new Gemini Experimental AI model's reasoning capabilities with a series of modified classic problems, including the trolley problem, Monty Hall problem, and more. Despite its top leaderboard rankings, it struggles with logical deductions but performs decently in coding tasks. Tune in to see detailed tests and insights!


LINKS:
https://aistudio.google.com/
Misguided Attention: https://github.com/cpldcpu/MisguidedAttention

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


00:00 Introduction to Google's New Gemini Model
00:35 Testing Reasoning Capabilities
01:23 Modified Trolley Problem
03:12 Monty Hall Problem Variation
05:30 Barber Paradox
07:05 Schrodinger's Cat Paradox
08:52 Farmer, Wolf, Goat, and Cabbage Problem
09:52 Simple Jug Problem
11:09 Coding Example: Web Page with Jokes
12:18 Coding Example: Text-to-Image Generator


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

The New Gemini Experimental: Can it Pass the Reasoning Tests?

In this video, I dive into Google's latest AI release, Gemini 2.0, which is multi-modal and agentic. I'll show you its capabilities in text, image, video, and audio processing, as well as some of the new experimental projects like Project Mariner and Project Jules. Watch as I demonstrate its impressive performance and interactive features!


LINKS:
https://aistudio.google.com/
https://blog.google/products/gemini/google-gemini-ai-collection-2024/
Colab: https://tinyurl.com/2snxfk59

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Google Gemini 2.0
00:42 Key Features and Capabilities
01:51 Experimental Projects and Applications
03:34 Demonstration of Gemini 2.0
04:55 Interactive Examples and Use Cases
08:02 Building Applications with Gemini 2.0
11:26 Gemini 2.0 API


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini 2.0 Flash in Action: How Multi-Modal AI is Changing Everything

It's Day 11 of 12 Days of OpenAI, and Google just released Gemini 2.0 Flash Thinking Experimental! I dive into its features, showing how it reveals its thought process and dominates the Chatbot Arena leaderboard. Watch as I test it on tricky problems like the trolley problem, the barber paradox, and more. Stay tuned for coding tests in the next video! Subscribe for more insights.


LINKS:
https://aistudio.google.com/
https://github.com/cpldcpu/MisguidedAttention

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Gemini 2
01:52 Testing the Trolley Problem
05:48 Exploring the Barber Paradox
08:28 Schrödinger's Cat and Other Paradoxes


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini 2.0 Flash Thinking - Does it Pass the Misguided Attention Test?

In this video, I dive into Google's recent white paper on building agentic systems. Learn about the components of AI agents, the differences between agents and models, and key frameworks like React, Chain of Thought, and Tree of Thought. I also explain the importance of tools such as extensions, functions, and data stores, and how retrieval-augmented generation (RAG) is used to expand AI knowledge. 


LINKS:
White paper: https://tinyurl.com/mr4yvhy4
Anthropic Blog: https://www.anthropic.com/research/building-effective-agents
Agents Video: https://youtu.be/icRKf_Mvmt8


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Google's White Paper on Agentic Systems
00:24 Defining AI Agents
00:54 Components of an AI Agent
01:40 When to Use Agents vs. Workflows
02:38 Differences Between Agents and Models
04:32 Reasoning Frameworks for Agents
08:03 Tools for Enhancing Agent Capabilities
15:05 Enhancing Model Performance with Targeted Learning


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Google's Blueprint to Building Powerful Agents

Google Deepmind just updated a new version of the Gemini 2.0 Flash Thinking model which is currently on the top of the Chatbot Arena leaderboard. 


LINKS: 
https://aistudio.google.com/
https://x.com/OfficialLoganK/status/1881844578069999809
https://x.com/lmarena_ai/status/1881848934743904319


💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


All Interesting Videos:
Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr

Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw

Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw

AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Gemini 2.0 Flash - Major Reasoning Updates

🚀 Gemini 2.0 Pro Experimental is here, and it's Google's most advanced AI yet! But how does it perform in real-world reasoning tasks? In this video, I dive into early testing of Gemini 2.0 Pro, exploring its reasoning abilities, coding capabilities, multimodal features, and groundbreaking AI tools like code execution and Google Search grounding.


⚡ Model Features Covered:
🔹 Multimodal AI: Native image understanding & generation
🔹 2M token context window – one of the longest in the industry!
🔹 Grounding with Google Search for real-time, up-to-date information
🔹 Function calling for AI agents & structured output support
🔹 Benchmark speculations – is this Google’s strongest AI model yet?

📌 Related Topics & Keywords:
#Gemini2 #GoogleGemini #Gemini2Pro #AIReasoning #GeminiVsGPT4 #ArtificialIntelligence #MachineLearning #LLM #TechNews

🔥 If you found this video insightful, hit the like button and subscribe for more AI updates, model comparisons, and deep dives into the latest LLMs!

💬 What do you think about Gemini 2.0 Pro Experimental? Will it challenge GPT-4, Claude, or Mistral? Drop your thoughts in the comments below!


LINKS:
https://aistudio.google.com/
https://github.com/cpldcpu/MisguidedAttention


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

Timestamps:

00:00 Introduction to Gemini 2.0 Pro Experimental
00:24 Model Capabilities and Initial Impressions
01:44 Detailed Feature Breakdown
04:16 Coding Tests and Performance
08:27 Reasoning Capabilities and Thought Experiments
16:34 Conclusion and Final Thoughts

Gemini 2.0 Pro

🚀 Gemini 2.0 Flash vs. Flash-Lite – Which One Should You Use? 🚀

Google just expanded the Gemini 2.0 lineup, introducing Flash-Lite, a new, cost-efficient AI model. But how does it compare to Gemini 2.0 Flash? In this video, we put both models to the test with long-context retrieval, programming challenges, and structured output generation.

💡 What You’ll Learn:
✅ How Flash-Lite compares to Flash in performance & cost
✅ Speed & accuracy tests on real-world coding tasks
✅ Limitations of Flash-Lite vs. Flash in LLM applications
✅ Best use cases for each model in AI development & research

With Flash-Lite costing just $0.07 per million input tokens, it could be a powerful budget-friendly alternative for AI tasks that don’t require high-end reasoning. But is it good enough? Watch to find out!

LINKS:
https://aistudio.google.com/


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

Timestamps:
00:00 Introduction to Google's Gemini 2.0 Expansion
00:48 Overview of Flash, Flashlight, and Pro Models
02:21 Comparing Model Capabilities and Performance
04:56 Coding Task Comparisons
06:33 Advanced Coding Challenges
10:59 Final Thoughts and Use Cases

Gemini 2.0 Flash vs. Flash-Lite: Which One Should You Use?

Google has just released Gemini 2.0 Flash Experimental, and it’s one of the craziest AI advancements I’ve seen! This model not only generates images from text but also edits them seamlessly—all through simple prompts.


LINKS:
https://developers.googleblog.com/en/experiment-with-gemini-20-flash-native-image-generation/
https://deepmind.google/discover/blog/gemini-robotics-brings-ai-into-the-physical-world/
https://deepmind.google/
https://ai.google.dev/gemma/?utm_source=gdm&utm_medium=referral&utm_campaign=gemma_cta&utm_content=promo_banner
https://x.com/jerrod_lew/status/1899917022047478014
https://x.com/fofrAI/status/1899978347179839510/photo/1

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

💡 Don't forget to Like, Subscribe & Hit the Bell 🔔 for more AI deep dives!

Supercharge Your RAG Pipeline with DeepSeq R1: A Step-by-Step Guide

00:00 Introduction to GPT-4 Image Generation
00:13 Google's Gemini 2.0 Flash: A Game Changer
00:26 Testing Gemini 2.0 Flash with Image Descriptions
01:40 Editing Images with Text Descriptions
03:23 Using Gemini Flash for Colorization and Recognition
04:34 Advanced Image Manipulations with Gemini Flash
07:09 Getting Started with Gemini Flash API
07:42 Google's AI Innovations and Future Prospects
10:13 Conclusion and Final Thoughts

Google’s Gemini 2.0: AI Image Generation & Editing

Google Gemini vs. OpenAI: A Deep Dive into Advanced AI Research Tools

Google is making its premium AI features free, including Gemini's Deep Research. I compared it with OpenAI's Deep Research, focusing on their application in retrieval augmented generation (RAG) systems. Find out which tool offers better quality and value!

LINKS:
https://gemini.google.com/
https://chatgpt.com/share/67d3d1cc-fdc4-8001-b9f4-b9215d8d4979


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Google's New AI Features: Free for All
00:45 Deep Research: A Game Changer
01:16 Exploring Gemini's New Features
02:14 Hands-On with Gemini Deep Research
02:42 Comparing Gemini and OpenAI Deep Research
05:35 In-Depth Analysis of Gemini's Report
12:56 OpenAI's Deep Research Report Breakdown
22:37 Final Thoughts and Comparison
23:24 Conclusion and Future Content

Deep Research But Free

Google just released Gemma 3, their latest open-weight multimodal AI model, and it's making waves! 🚀 With four models ranging from 1B to 27B parameters, Gemma 3 is already ranking in the top 10 on the Chatbot Arena leaderboard. But is it truly the best open-weight model yet?

LINKS:
https://blog.google/technology/developers/gemma-3/
https://developers.googleblog.com/en/introducing-gemma3/
https://developers.googleblog.com/en/gemma-3-on-mobile-and-web-with-google-ai-edge/
https://ai.google.dev/gemma/docs/core/model_card_3
https://huggingface.co/collections/google/gemma-3-release-67c6c6f89c4f76621268bb6d
https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf
https://x.com/ArtificialAnlys/status/1900579291404046696/photo/1


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Gemma 3
00:47 Gemma 3 Model Family and Features
03:06 Training and Innovations
04:57 Model Availability and Hardware Requirements
07:15 Performance and Use Cases
08:34 Coding Capabilities and Limitations
10:46 Multimodal Capabilities

Google’s Gemma 3: The Best Open-Weight Model Yet?

Exploring Google's VO2: Next-Gen Text and Image to Video Model

Google has just launched their stunning video generation model VO2 in AI Studio! I'll walk you through the features, show example outputs, and share key prompting tips for generating high-quality videos using text or images. VO2 truly sets a new benchmark in video creation. Don't forget to download your videos and share your creative results!

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

💡 Don't forget to Like, Subscribe & Hit the Bell 🔔 for more AI deep dives!

Supercharge Your RAG Pipeline with DeepSeq R1: A Step-by-Step Guide




00:00 Introduction to Google's Video Generation Model
00:28 Exploring the Video Generation Tab
01:03 Generating Videos with VO2
01:41 Example Prompts and Outputs
02:44 Using Your Own Images
03:41 Accuracy and Quality of Outputs
06:20 Prompting Techniques for Best Results
07:53 Conclusion and Future Videos

Google Veo-2, Now Available in AI Studio

Assessing the Capabilities of Gemini 2.5 Pro: Function Calling and More

In this video, I dive into the capabilities of the new Gemini 2.5 Pro model. We explore its benchmarks, coding abilities, and its performance in function calling. I demonstrate building a text-to-SQL assistant, creating complex workflows like trip planning, and simulating business intelligence dashboards. Tune in to see why this model is a game-changer for coding and complex application development!


LINKS: 
aistudio.google.com
https://colab.research.google.com/drive/12_rCTOYs0i5p_G7XsVyR6_pQdBSLQH5s?usp=sharing

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Gemini 2.5 Pro
01:06 Testing Function Calling Capabilities
03:06 Setting Up the Google SDK
05:29 Basic Function Call Example
07:36 Parallel Function Calls
08:44 Building a SQL Assistant
12:13 Complex Function Calling: Trip Planning
16:05 Comprehensive Business Intelligence Dashboard
21:45 Final thoughts

Gemini 2.5 Pro Function Calling—All You Need to Know

Exploring the Power of Gens Spark: A Superior Alternative to MENA AI

If you're still waiting for an invite from MENA AI, check out Gens Spark, a new and impressive AI out of China. It uses a mixture of nine different LLMs and 80+ reliable tools to deliver high-quality results. The system excels in benchmarks, outperforming MENA AI and OpenAI's deep research. You can try it for free and experience its powerful functionalities, from generating videos to conducting complex research. Sign up now and see the future of AI in action!


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0



00:00 Introduction to Gens Spark: A New Alternative to MENA AI
04:14 How Gens Spark Works: Multi-Agent System and Tools
04:43 Benchmark Performance: Gens Spark vs. Competitors
05:12 Hands-On with Gens Spark: Real-World Examples
05:56 User Experience: Signing Up and Using Gens Spark
06:07 Advanced Features: Image and Video Generation
06:49 Deep Dive: Super Agent and Research Capabilities
09:02 System Overview: Tabs and Tools
11:15 Conclusion: Final Thoughts on Gens Spark

This Mixture-of-Agents System Outperforms Manus AI

What is Quasar Alpha?! A new mystery AI model just dropped on OpenRouter—and it’s absolutely cracked at coding. From building full websites in one shot to running advanced simulations, this thing is fast, creative, and scarily good.

In this video, I put Quasar Alpha to the test with a series of challenging prompts:

Build an encyclopedia from scratch
Animate TV channels with genre-inspired content
Simulate realistic physics in a single HTML file
Render a 3D interactive map of LA
AND MORE...

LINKS
https://openrouter.ai/openrouter/quasar-alpha
https://x.com/paulgauthier/status/1907996176605220995


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


TIMESTAMP
00:00 Introduction to the Project
00:20 Creating a TV with Channel Switching
00:59 Scientific Animation with JavaScript
01:35 3D Interactive Map of Los Angeles
02:03 Introducing Quasar Alpha
03:20 Testing Quasar Alpha's Coding Capabilities
05:57 Forest Fire Simulation
07:58 Central Limit Theorem Simulation
08:30 3D Interactive Map Revisited
10:05 Testing Multimodal Capabilities
11:01 Conclusion and Final Thoughts

Quasar Alpha: This Mystery Coding Model is So Cracked 🔥

Exploring Google's New AI Studio: Features, Models, and Video Generation Explained!


LINK:
https://aistudio.google.com/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


In this video, we dive into the complete redesign of Google's AI Studio, exploring new features including video generation. Learn about the three main options for using Google AI: the Gemini app, AI Studio, and Vertex AI, with a detailed focus on AI Studio's functionality. Discover the various models, hyper-parameters, and safety settings, and see how you can export interactions into working Python code. We also showcase how to compare different models and utilize tools like grounding with Google Search to reduce hallucinations. Finally, explore the latest addition - video generation, and some example starter apps for building real-world applications.

00:00 Introduction to Google's AI Studio Redesign
01:12 Overview of AI Studio and Available Models
02:06 Exploring Model Settings and Parameters
04:24 Comparing Different Models
06:56 Advanced Features and Tools
09:18 Generating Code and Using API Keys
18:37 Video Generation and Starter Apps
20:45 Conclusion and Final Thoughts

Google’s AI Studio in 22 Minutes

In this video, we will look at the Gemini 2.5 Flash which is the first Hybrid Reasoning model where you can literally toggle “thinking” on or off. I break down its insane cost‑performance ratio, 1 M‑token context window, and how it stacks up against GPT‑4 Mini and Claude Sonnet.

LINK:
https://aistudio.google.com/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

In this episode, we explore Google's release of the Gemini 2.5 Flash, a groundbreaking hybrid reasoning model. This model allows developers to toggle the 'thinking' mode and set a token-based thinking budget, making it versatile for different tasks. Notably, Gemini 2.5 Flash offers highly competitive pricing and outstanding performance-to-cost ratios compared to other models like OpenAI's 3.5 Sonnet and 4 Mini. We'll also discuss the model's benchmarks, features, and potential impact on AI development, ensuring you have all the details to make an informed choice.

00:00 Introduction to Google's Gemini 2.5 Flash
00:04 Hybrid Reasoning Model: A New Feature
00:41 Competitive Pricing and Market Position
01:16 Benchmark Performance and Comparisons
02:17 Google's Strategy: Performance to Cost Ratio
05:14 Fine-Grained Control Over Thinking Mode
09:51 Testing the Model: Practical Examples
12:37 Conclusion and Final Thoughts

Gemini  2.5 Flash - Hybrid Reasoning on Demand

In this video, we will look at the Gemini 2.5 Flash which is the first Hybrid Reasoning model where you can literally toggle “thinking” on or off. I break down its insane cost‑performance ratio, 1 M‑token context window, and how it stacks up against GPT‑4 Mini and Claude Sonnet.

LINK:
https://aistudio.google.com/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

In this episode, we explore Google's release of the Gemini 2.5 Flash, a groundbreaking hybrid reasoning model. This model allows developers to toggle the 'thinking' mode and set a token-based thinking budget, making it versatile for different tasks. Notably, Gemini 2.5 Flash offers highly competitive pricing and outstanding performance-to-cost ratios compared to other models like OpenAI's 3.5 Sonnet and 4 Mini. We'll also discuss the model's benchmarks, features, and potential impact on AI development, ensuring you have all the details to make an informed choice.

00:00 Introduction to Google's Gemini 2.5 Flash
00:04 Hybrid Reasoning Model: A New Feature
00:41 Competitive Pricing and Market Position
01:16 Benchmark Performance and Comparisons
02:17 Google's Strategy: Performance to Cost Ratio
05:14 Fine-Grained Control Over Thinking Mode
09:51 Testing the Model: Practical Examples
12:37 Conclusion and Final Thoughts

Gemini  2.5 Flash - Hybrid Reasoning on Demand

Qwen-3 model family is here and these are the first open-weight hybrid reasoning models. 

LINKS:
https://chat.qwen.ai/
https://qwenlm.github.io/blog/qwen3/
https://huggingface.co/spaces/Qwen/Qwen3-Demo


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Qwen-3
00:43 Overview of Released Models
01:04 Benchmark Performance Insights
03:12 Context Window and Architecture
04:49 Hybrid Thinking Mode Explained
07:21 Multimodal Capabilities and Coding
09:17 Synthetic Data and Training Process
11:37 Post-Training and Model Distillation
13:52 Using the Models in Workflows
14:59 Conclusion and Future Releases

Qwen-3 Is Here — The Llama-4 We’ve Been Waiting For!

In this video we will look at context caching for cost and latency reduction. We will look at Gemini API but same technique can be used with Anthropic and OpenAI. 

LINKS:
colab link: https://colab.research.google.com/drive/1lPfeAfXmS8TPclQ8Pd3odb0_7apTG4HU?usp=sharing
https://x.com/_philschmid/status/1917492129007292439
https://github.com/philschmid/gemini-samples/blob/main/examples/gemini-context-caching.ipynb
https://ai.google.dev/gemini-api/docs/caching?lang=python
https://youtu.be/tmiBae2goJM


RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0


In this video, discover how to significantly cut down your LLM API costs by using context caching. Learn how major API providers like Google, OpenAI, and Anthropic offer context caching to minimize API calls and reduce expenses. The video focuses on Google's implementation, explaining its benefits, usage, and cost-saving potential. You'll see a detailed tutorial on how to use context caching for large documents, in-context learning, and practical examples like MCP server creation. With insights into setup, token storage, cache management, and various functionalities, this guide will show you how to harness the power of context caching for optimal performance and cost-efficiency.

00:00 Introduction to Cost Reduction with Context Caching
00:22 Understanding Context Caching
01:06 Google's Implementation of Context Caching
03:04 Cost Benefits of Context Caching
04:13 Practical Example: Setting Up Context Caching
08:24 Advanced Techniques and Functions
09:16 Example: Caching GitHub Repo Contents
15:42 Conclusion and Additional Resources

Could This Gemini Trick Replace RAG?

Testing Google's Major Gemini 2.5 Pro Update: Web Dev Capabilities Put to the Test!

In this video, we dive into Google's latest update to the Gemini 2.5 Pro model, which boasts improved web development capabilities. We'll compare it against the previous version on various coding tasks, including creating a fantasy sports league manager and a simple encyclopedia. We also explore its speed, accuracy, and creativity with more complex prompts, such as simulating TV channels and generating animations. Finally, we discuss how these models handle larger codebases in real-world applications. Stay tuned to see if the new Gemini 2.5 Pro lives up to the hype!

LINKS: 
Leaderboard: https://x.com/OriolVinyalsML/status/1919770619182215440/photo/1

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Gemini 2.5 Pro Update
01:18 Setting Up the Comparison Test
01:31 First Test: Fantasy Sports League Manager
05:23 Second Test: Simple Encyclopedia
06:46 Third Test: Modern Landing Page
07:23 Fourth Test: TV Channel Selector
12:20 Fifth Test: JavaScript Animation
14:49 Final Test: Bouncing Balls in a Spinning Hexagon
17:19 Real-World Applications and Conclusion

Gemini 2.5 Pro's: The Best Coding Model Just got Better

Checkout Trae: https://tinyurl.com/yneuw25d

I’ve been exploring Trae (@trae_ai)—the free AI IDE that competes with Cursor—and I’m impressed by its custom agents and MCP integrations right inside Trae AI. In this video, I’ll walk you through setting up Trae AI, selecting powerful models like Gemini 2.5 Pro, and building specialized agents for everything from web search to terminal automation. 

 #TraeAI, #trae #AIforDev, #SmartCoding, #AIProgramming, #CodeBetter

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Trae AI
01:02 New Features and Customization
01:39 Supported Models and Custom Agents
02:22 Creating and Using Custom Agents with MCP
05:48 Example Project: Text to Image Generator
08:09 Testing and Debugging the Project
10:36 Privacy, Security, and Final Thoughts

Free Cursor Alternative? Trae AI Just Got Way Better

Checkout out Sam's Youtube Channel: https://www.youtube.com/ ⁨@samwitteveenai⁩ . We chatted at Google IO https://goo.gle/4kH6RLI

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

Timestamps:
00:00 Introduction and Frustrations with AI Providers
00:28 Recap of Google I/O Highlights
02:32 Gemini Models and Product Innovations
04:56 Agentic Coding and Future Developments
15:49 Exploring Mobile AI and Developer Potential
17:08 The Future of Model Capabilities
19:09 Innovations in AI Tools and Applications
24:06 Convergence and Future Trends in AI

From Models to Agentic Applications with Sam Witteveen

Anthropic released Claude-4 last week and its supposed to be the best coding model. I put it to the test and compared to O3, Gemini 2.5 Pro, Qwen and DeepSeek R1. The results will surprise you!

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

TIMESTAMP:

00:00 Introduction and Model Comparison Setup
00:36 Claude 4 Release and Benchmarks
02:44 Pricing Comparison
03:19 Testing Methodology
04:46 Model Capabilities and Tool Usage
06:15 Results Analysis
12:54 Conclusions and Recommendations

Best Coding Model? I Tested 5 Models.

Deepseek just released R1-0528, an upgrade to their previous R1 model. This is (potentially) based on the upgrade V3. 

Try it here: https://chat.deepseek.com/
Benchmarks: https://livecodebench.github.io/leaderboard.html
Huggingface: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

New DeepSeek R1 is Really, Really Good Coder

Google’s experimental Gemini Diffusion model—the first diffusion-based text generation model from a major frontier lab. In this video, we break down how it works, why it's blazing fast (800 tokens/sec!), and what it means for the future of LLMs. Is this the beginning of a new generation of language models?

LINKS: 
https://deepmind.google/models/gemini-diffusion/
https://www.inceptionlabs.ai/
https://www.leewayhertz.com/how-to-train-a-diffusion-model/
https://www.seangoedecke.com/limitations-of-text-diffusion-models/?utm_source=chatgpt.com
https://x.com/karpathy/status/1894923254864978091?lang=en

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Gemini Diffusion
00:23 Real-Time Speed Demonstration
00:39 Comparison with Other Models
01:15 Google's Experimental Release
02:20 Understanding Diffusion LLMs
03:18 Diffusion vs. Auto-Regressive Models
05:20 Examples and Applications
06:33 Future Possibilities and Limitations
07:23 Conclusion and Final Thoughts

Gemini Diffusion Is CRAZY Fast—But Not What You Think

In this video, we’ll take a look at how Gemini 2.5 Pro compares to OpenAI’s GPT-4o (O3) across multiple benchmarks, highlighting real-world use cases and performance. I’ll also cover major new releases from ElevenLabs and Qwen3, showing how these updates impact voice cloning and LLM capabilities. If you’re following the latest breakthroughs in AI, multimodal models, and speech tech, this roundup is packed with insights.

LINKS:
https://aistudio.google.com/
https://x.com/GoogleDeepMind/status/1930656247692325155/photo/1
https://x.com/elevenlabsio/status/1930689774278570003
https://elevenlabs.io/v3
https://x.com/Alibaba_Qwen/status/1930648422778118246
https://qwenlm.github.io/blog/qwen3-embedding/
https://x.com/OfficialLoganK/status/1930657743251349854
https://aider.chat/docs/leaderboards/


Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Major Releases
00:42 Gemini 2.5 Pro: A Deep Dive
07:49 Elevanlabs V3 Text-to-Speech Breakthrough
09:10 Qwen's Latest RAG Models

Gemini 2.5 Pro Beats O3 — Big Drops from ElevenLabs & Qwen

In this episode, we sit down with Karl, the leads the Cloud Product DevRel team at Google, to discuss the burgeoning role of AI agents in coding assistance and the evolving role of developers. We delve into Google's latest innovations in AI, particularly the Agent Development Kit (ADK), and talk about the practical applications and future of AI agents in helping developers build scalable solutions. We also explore the balance between AI automation and human input in development, and the new tools Google is providing to facilitate this synergy. Tune in to hear insights on the future of software development in the AI era.

Learn more about Google for Developers:  https://goo.gle/4kH6RLI

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0




00:00 Introduction and Episode Overview
00:42 Discussion on AI Agents
02:02 Evolution of AI Agents and Development Kits
04:38 User Interface and Developer Experience
05:32 Challenges and Opportunities with AI Agents
08:22 Future of Coding with AI Assistance
15:10 Google's AI Ecosystem and Developer Support
20:06 Evolving Role of Developers

AI Agents & The Future of Coding: A Conversation with a Googler

I had early access to Gemini-CLI, which is a free and open source alternative to Claude Code. This is a powerful CLI based Agent that you can run for free from @Google ​ 
 

Github Repo: https://github.com/google-gemini/gemini-cli
Blogpost: https://blog.google/technology/developers/introducing-gemini-cli-open-source-ai-agent/

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Gemini CLI
01:06 Setting Up Gemini CLI
02:32 Using Gemini CLI Commands
04:55 Creating a Text-to-Image Web App
05:40 Troubleshooting and Debugging
10:05 Token Usage and Optimization
11:29 Final Thoughts and Comparison

Gemini CLI — Google’s Free Open-Source Coding Agent

Kimi-K2 is a great coding model but they also have a great Deep researcher tool that is SOTA on a number of key benchmarks. In this video we explore how it was trained and how it compares to the other Deep researchers. 

https://moonshotai.github.io/Kimi-Researcher/
https://moonshotai.github.io/Kimi-K2/
https://cognition.ai/blog/dont-build-multi-agents#a-theory-of-building-long-running-agents
https://www.anthropic.com/engineering/built-multi-agent-research-system
https://www.kimi.com/chat/d1rduifahd86o5c4h6sg
https://www.kimi.com/preview/1981112a-6f41-87e6-bf31-807c600005bb

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Kimi Researcher
00:55 Single vs Multi Agent
02:04 Reinforcement Learning Approach
02:57 Emergent Capabilities
04:07 Context Management
06:16 Comparison of Deep Research Tools
07:15 Detailed Results from Various Tools
09:16 Kimi's Unique Features

Kimi K2 — The Deep Researcher Agent

Sources from the Pragmatic Engineer and A

https://newsletter.pragmaticengineer.com/p/the-pragmatic-engineer-2025-survey
https://artificialanalysis.ai/downloads/ai-adoption-survey/2025/Artificial-Analysis-AI-Adoption-Survey-H1-2025.pdf

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Survey Overviews: Pragmatic Engineer and Artificial Analysis
01:27 AI Tools Usage Insights
01:44 GitHub Copilot and Other Popular Tools
03:44 Programming Languages and Coding Tools
04:15 Disliked Tools and Version Control
04:47 Gemini's Unique Position
05:32 Model Usage Trends
06:16 API Providers and Market Share
06:59 Summary of Findings

Developers’ Favorite AI Tools in 2025

Gemini Deep Think is the model for the hardest and most challenging problems. A version of this recently won gold in IMO 2025. Thanks to the Google DeepMind, I had early access to the model and here I am sharing some of my thoughts on it. 

https://blog.google/products/gemini/gemini-2-5-deep-think/
https://deepmind.google/discover/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/
https://github.com/The-Pocket/PocketFlow

#EarlyAccess

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

Gemini Deep Think: Built for the Hardest Problems

In this quick tutorial I show you how Google’s open-source LangExtract converts messy PDFs, HTML, and DOC files into clean knowledge graphs that plug straight into Retrieval-Augmented Generation (RAG) workflows. Watch me run entity- and relationship-extraction with a long-context LLM like Gemini, build custom schemas, and visualize everything in seconds. If you’re working on AI agents, vector databases, or search pipelines, this is the fastest way to make your data Graph-RAG ready.

Website: https://developers.googleblog.com/en/introducing-langextract-a-gemini-powered-information-extraction-library/
Github: https://github.com/google/langextract

Website: https://engineerprompt.ai/

RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/courses/rag

Let's Connect: 
🦾 Discord: https://discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon: https://www.patreon.com/PromptEngineering
💼Consulting: https://calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: http://tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off).  

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Lang Extract
00:39 Overview of Lang Extract Capabilities
01:21 Setting Up Lang Extract
03:03 Basic Example: Entity Extraction
05:48 Advanced Example: Relationship Extraction
10:02 Creating Knowledge Graphs
11:29 Conclusion and Additional Resources

LangExtract: Turn Messy Text into Graph-RAG Insights

<p>In this quick tutorial I show you how Google’s open-source LangExtract converts messy PDFs, HTML, and DOC files into clean knowledge graphs that plug straight into Retrieval-Augmented Generation (RAG) workflows. Watch me run entity- and relationship-extraction with a long-context LLM like Gemini, build custom schemas, and visualize everything in seconds. If you’re working on AI agents, vector databases, or search pipelines, this is the fastest way to make your data Graph-RAG ready. Website: https://developers.googleblog.com/en/introducing-langextract-a-gemini-powered-information-extraction-library/ Github: https://github.com/google/langextract Website: https://engineerprompt.ai/ RAG Beyond Basics Course: https://prompt-s-site.thinkific.com/courses/rag Let's Connect: 🦾 Discord: https://discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: https://ko-fi.com/promptengineering |🔴 Patreon: https://www.patreon.com/PromptEngineering 💼Consulting: https://calendly.com/engineerprompt/consulting-call 📧 Business Contact: engineerprompt@gmail.com Become Member: http://tinyurl.com/y5h28s6h 💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off). Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 00:00 Introduction to Lang Extract 00:39 Overview of Lang Extract Capabilities 01:21 Setting Up Lang Extract 03:03 Basic Example: Entity Extraction 05:48 Advanced Example: Relationship Extraction 10:02 Creating Knowledge Graphs 11:29 Conclusion and Additional Resources</p>

GEMINI vs. GPT-4

Chapters

Course Chapters