Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Build a Local RAG Reasoning Agent with Qwen 3, using a Vector Database with Web Search for fallback. You can also choose Gemma 3 or DeepSeek R1. 100% free, local, and Opensource.

Unwind AI

18,221 subscribers

52,006 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

9 Comments

Unwind AI1 year ago

Opensource code: Step-by-step tutorial:

GitProtect.io2 years ago

Automated GitHub, GitLab, Bitbucket and Jira backups, security compliance, data migration and every-scenario-ready Disaster Recovery for 360 cyber resilience. Schedule a custom demo or try 14 days for free.

Kairos Data Labs1 year ago

This is awesome! Thanks for sharing!

Unwind AI1 year ago

you're welcome

Gargi1 year ago

Sweeet!

Unwind AI1 year ago

yess

@ReneKriest1 year ago

Nice job. 👍🏻 Out of curiosity: how does your stack compared against Haystack ? That’s my fav at the moment for local RAG systems.

Marble681 year ago

Pretty cool little project.

Daniyal Shaik(✸,✸)1 year ago

Nerd mode: ACTIVATED 🤓 Local AI that actually respects my privacy? Shut up and take my GitHub stars! 🚀

Related Videos

I built a Deepseek R1 RAG Reasoning Agent running locally on my computer. It's an Agentic RAG reasoning agent that can think, reason and fall back to web search if needed. 100% Opensource code with step-by-step tutorial.

I built a Deepseek R1 RAG Reasoning Agent running locally on my computer. It's an Agentic RAG reasoning agent that can think, reason and fall back to web search if needed. 100% Opensource code with step-by-step tutorial.

Shubham Saboo

124,490 views • 1 year ago

I built a local RAG App with Hybrid Search using Llama 3.2 and PostgreSQL. 100% free and opensource.

I built a local RAG App with Hybrid Search using Llama 3.2 and PostgreSQL. 100% free and opensource.

Shubham Saboo

48,598 views • 1 year ago

DeepSeek RAG Agent : 100% Local using ollama Code below 👇 💡 RAG AI Agent with Reasoning DeepSeek 🌐 Local using @Ollama ✨ Few lines of Code PraisonAI 🔍 UI using Streamlit 💪 Nomic Embed Text for embedding 🧠 Deep Contextual Awareness

DeepSeek RAG Agent : 100% Local using ollama Code below 👇 💡 RAG AI Agent with Reasoning DeepSeek 🌐 Local using @Ollama ✨ Few lines of Code PraisonAI 🔍 UI using Streamlit 💪 Nomic Embed Text for embedding 🧠 Deep Contextual Awareness

Mervin Praison

59,593 views • 1 year ago

10. RAG app using DeepSeek-R1 (100% local)

10. RAG app using DeepSeek-R1 (100% local)

Poonam Soni

513,429 views • 1 year ago

Voice RAG Agent using OpenAI Agents SDK and Qdrant as the vector database. 100% Opensource Code.

Voice RAG Agent using OpenAI Agents SDK and Qdrant as the vector database. 100% Opensource Code.

Shubham Saboo

28,219 views • 1 year ago

I just built a RAG Agent with web search using Cohere's ⌘R 7B model. 100% Opensource Code with step-by-step tutorial.

I just built a RAG Agent with web search using Cohere's ⌘R 7B model. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

47,032 views • 1 year ago

Hugging Face just dropped AI sheets to build and enrich datasets without writing a single line of code. Works with Qwen, Kimi, Llama 3 and other opensource LLMs. 100% Free, local and Opensource.

Hugging Face just dropped AI sheets to build and enrich datasets without writing a single line of code. Works with Qwen, Kimi, Llama 3 and other opensource LLMs. 100% Free, local and Opensource.

Shubham Saboo

65,257 views • 10 months ago

I built a multi-agent Deep Research team using Qwen 3 that can generate consulting style reports as Google docs. It has 3 AI Agents working together as a team: 1. Research Question Agent 2. Web Search Agent 3. Google Docs Compilation Agent 100% Opensource Code.

I built a multi-agent Deep Research team using Qwen 3 that can generate consulting style reports as Google docs. It has 3 AI Agents working together as a team: 1. Research Question Agent 2. Web Search Agent 3. Google Docs Compilation Agent 100% Opensource Code.

Shubham Saboo

25,071 views • 1 year ago

AgenticSeek is an opensource alternative to $200/month Manus AI agent. It runs entirely on your computer, letting local reasoning LLMs like DeepSeek R1 browse the web, write code, and execute tasks while keeping all your data private. 100% free and without internet.

AgenticSeek is an opensource alternative to $200/month Manus AI agent. It runs entirely on your computer, letting local reasoning LLMs like DeepSeek R1 browse the web, write code, and execute tasks while keeping all your data private. 100% free and without internet.

Unwind AI

57,425 views • 1 year ago

Just built a chat with Excel app using Qwen 3 LLM (100% local):

Just built a chat with Excel app using Qwen 3 LLM (100% local):

Avi Chawla

63,949 views • 1 year ago

Build a local LLM app with RAG to chat with Google Drive data using Mistral or Llama-3 running locally on your computer without wiring a single line of Python Code (100% free and without internet):

Build a local LLM app with RAG to chat with Google Drive data using Mistral or Llama-3 running locally on your computer without wiring a single line of Python Code (100% free and without internet):

Shubham Saboo

189,592 views • 1 year ago

12. A multi-agent YouTube video analyst, powered by DeepSeek-R1 (100% local):

12. A multi-agent YouTube video analyst, powered by DeepSeek-R1 (100% local):

Poonam Soni

427,945 views • 1 year ago

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Sigma Browser

113,142 views • 1 month ago

DeepSeek released R1, the best open-source reasoning model that is on par with OpenAI's o1! I have built a RAG app to chat with your PDF files using the DeepSeek R1 model, running locally on your computer. 100% Open Source

DeepSeek released R1, the best open-source reasoning model that is on par with OpenAI's o1! I have built a RAG app to chat with your PDF files using the DeepSeek R1 model, running locally on your computer. 100% Open Source

Sumanth

678,561 views • 1 year ago

Software Engineering AI Agent on your machine connects with your apps and tools to automate engineering tasks. It can work with OpenAI, Claude Sonnet 3.5, Gemini and local Llama 3. 100% Opensource and free.

Software Engineering AI Agent on your machine connects with your apps and tools to automate engineering tasks. It can work with OpenAI, Claude Sonnet 3.5, Gemini and local Llama 3. 100% Opensource and free.

Shubham Saboo

169,161 views • 1 year ago

Chinese AI lab just killed Photoshop with its opensource AI image editing model. Qwen Image can perfectly edit any image while keeping everything else pixel-perfect. 100% free, local and Opensource.

Chinese AI lab just killed Photoshop with its opensource AI image editing model. Qwen Image can perfectly edit any image while keeping everything else pixel-perfect. 100% free, local and Opensource.

Shubham Saboo

101,849 views • 10 months ago

Claude can now do web search! 🤯 Build using Model Context Protocol and Exa's web search API. It is completely free and opensource. Link below 👇

Claude can now do web search! 🤯 Build using Model Context Protocol and Exa's web search API. It is completely free and opensource. Link below 👇

Exa

93,169 views • 1 year ago

Autonomous AI Agent framework uses Qwen 3 with MCP to build and deploy a documentation website from GitHub repository. All of this from a simple prompt in just 2 minutes. 100% Opensource.

Autonomous AI Agent framework uses Qwen 3 with MCP to build and deploy a documentation website from GitHub repository. All of this from a simple prompt in just 2 minutes. 100% Opensource.

Shubham Saboo

22,103 views • 1 year ago

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

Victor

260,273 views • 1 year ago