Uploaded October 2026 | Updated November 2026, 1 hour ago
This video is sponsored by TripleTen, a professional education platform designed to help tech professionals and career changers move into higher-paying tech and AI roles.
Explore two TripleTen programs for experienced engineers:
AI Systems Engineering (22 weeks)
tripleten.com/systems-engineer/?utm_source=youtube&utm_medium=video&utm_campaign=techwithtim
AI and Machine Learning (20 weeks)
tripleten.com/ai-machine-learning/?utm_source=youtube&utm_medium=video&utm_campaign=techwithtim
Both are for engineers with 2+ years of recent, hands-on production experience and require a short skills audit before you can enroll. Both also include career coaching and mentorship to help you stand out in the job market.
Ask a normal AI model “what’s the alarm code at my cafe?” and it has no idea, because your handbook, notes, and PDFs were never part of its training data. It either refuses or makes something up. RAG fixes that, and it’s a lot simpler than most people make it sound. In this video I build a complete RAG system from scratch in plain Python and under 50 lines of code. No LangChain, no pre-built vector database, no closed-source models, and everything runs locally on your own computer, so it’s free and completely private.
🚀 Tools I Use
Get 10% off with code techwithtim
Openclaw setup: hostinger.com/techwithtim
VPS setup: hostinger.com/techwithtim10
Wispr Flow (Best AI Dictation): ref.wisprflow.ai/TechWithTim-oct26
🎞 Video Resources 🎞
Get all of the code in this video: aiagentbuilders.co/yt-resources/rag-from-scratch
⏳ Timestamps ⏳
00:00 | Overview
00:26 | The Problem
01:18 | What is RAG
02:03 | How it Works
03:01 | TripleTen
04:48 | Step 0 - Models
13:14 | Step 1 - Chunking
16:25 | Step 2 - Embedding
18:31 | Step 3 - Searching
21:47 | Step 4 - Calling the LLM
25:13 | Next Steps
Hashtags
#RAG #Python #Ollama
UAE Media License Number: 3635141
This video is sponsored by TripleTen, a professional education platform designed to help tech professionals and career changers move into higher-paying tech and AI roles.
Explore two TripleTen programs for experienced engineers:
AI Systems Engineering (22 weeks)
tripleten.com/systems-engineer/?utm_source=youtube&utm_medium=video&utm_campaign=techwithtim
AI and Machine Learning (20 weeks)
tripleten.com/ai-machine-learning/?utm_source=youtube&utm_medium=video&utm_campaign=techwithtim
Both are for engineers with 2+ years of recent, hands-on production experience and require a short skills audit before you can enroll. Both also include career coaching and mentorship to help you stand out in the job market.
Ask a normal AI model “what’s the alarm code at my cafe?” and it has no idea, because your handbook, notes, and PDFs were never part of its training data. It either refuses or makes something up. RAG fixes that, and it’s a lot simpler than most people make it sound. In this video I build a complete RAG system from scratch in plain Python and under 50 lines of code. No LangChain, no pre-built vector database, no closed-source models, and everything runs locally on your own computer, so it’s free and completely private.
🚀 Tools I Use
Get 10% off with code techwithtim
Openclaw setup: hostinger.com/techwithtim
VPS setup: hostinger.com/techwithtim10
Wispr Flow (Best AI Dictation): ref.wisprflow.ai/TechWithTim-oct26
🎞 Video Resources 🎞
Get all of the code in this video: aiagentbuilders.co/yt-resources/rag-from-scratch
⏳ Timestamps ⏳
00:00 | Overview
00:26 | The Problem
01:18 | What is RAG
02:03 | How it Works
03:01 | TripleTen
04:48 | Step 0 - Models
13:14 | Step 1 - Chunking
16:25 | Step 2 - Embedding
18:31 | Step 3 - Searching
21:47 | Step 4 - Calling the LLM
25:13 | Next Steps
Hashtags
#RAG #Python #Ollama
UAE Media License Number: 3635141









![AI Can Finally Get Past Login Screens (Safely)
#sponsored Claude can now log into your accounts without ever seeing your passwords. In this video I set up 1Password for Claude and put it to work on real tasks: checking an Amazon order and canceling a subscription. When Claude takes control of a browser tab, 1Passwords Agentic Mode activates, Claude requests the credential, I approve with Touch ID, and 1Password fills it directly into the page. Claude never receives the password. It never leaves my vault.
This is 1Passwords first version of secure agent access. Its early, and it doesnt cover every agent or use case yet, but the architecture is what matters: AI agents can now take real actions, and this removes the authentication barrier without removing your control.
This video is sponsored by 1Password.
Learn more about 1Password for Claude: https://1password.com/blog/1password-for-claude?utm_medium=paid_video&utm_source=youtube&utm_campaign=evergreen_none_bl_1password-for-claude_ss&utm_content=main_tech-with-tim_082426
Check out @1PasswordVideos
What functionality do you want this integration to have next? What would you hand off to Claude if logins werent a problem? Let me know in the comments.
Video Resources
1Password for Claude blog post: [https://1password.com/blog/1password-for-claude?utm_medium=paid_video&utm_source=youtube&utm_campaign=evergreen_none_bl_1password-for-claude_ss&utm_content=main_tech-with-tim_082426]
⏳ Timestamps ⏳
00:00 | Overview
00:38 | The Problem
01:37 | What 1Password for Claude Is
02:21 | Setup & Connection
04:11 | Demo & Use Cases
06:30 | Why the Architecture Matters
Hashtags
#sponsored #1Password #Claude #AIAgents
UAE Media License Number: 3635141 AI Can Finally Get Past Login Screens (Safely)](https://i.ytimg.com/vi/ibpSIF3aeGc/mqdefault.jpg)
