CrewAI RAG Deep Dive [Basic & Advanced Examples]

🤖 Download the Source Code Here:

Don't forget to Like and Subscribe if you're a fan of free source code 😉

📆 Need help with CrewAI? Join our FREE Skool Community:

In this tutorial, I guide you through mastering Retrieval Augmented Generation (RAG) with CrewAI. We’ll start with the basics and move to advanced applications, including setting up a crew for home inspection reports and diving deep into YouTube scraping with Firecrawl. This video is packed with real code examples, and all the source code is available for free!

📰 Stay updated with my latest projects and insights:

Checkout my other AI Tutorials:

Links called out in video:

Timestamps:
00:00:00 Introduction
00:01:22 What is RAG? How does it work? Why is it important?
00:04:48 Real world examples
00:07:22 Code Overview
00:08:46 RAG Basic Example - Overview
00:11:39 RAG Basic Example - Code Walkthrough
00:15:55 RAG Basic Example - Run Crew
00:20:34 RAG Basic Example - Customize RAG Models & Embeddings
00:25:23 RAG Advanced Example - Overview
00:30:24 RAG Advanced Example - Code Walkthrough
00:32:08 Fetch Latest YouTube Videos for Channel - Build Custom Tool
00:38:40 Enable YouTube API in Google Cloud Platform
00:40:45 Scrape YouTube Videos - RAG
00:44:21 Initial RAG Retrieval From YouTube Videos
00:49:47 Follow-up RAG Retrieval
00:52:24 Fallback RAG Retrieval - Firecrawl
00:57:04 RAG Advanced Example - Run Crew
01:04:37 CrewAI - Replay (New Feature)
01:09:29 Outro

[lakshent]

Brandon, your teaching style is one of the best I have ever seen! Your content is beyond "excellent"! Providing these tutoials free to all via the internet is one of the most noble deeds I have seen! Lots of respect, love, admiration and best wishes!

[lucatamburrano]

This video is one of the most interesting and well done I've ever seen.. I created my first crew before watching this video. Now I understand my mistakes and start touching the real power of agents Thank you!!.

[agent_mo]

Hey Brandon, I'm blown away by the detail and effort you put into this! 🌟 It’s clear a ton of hard work went into making this, and I just wanna say I really appreciate it.

[andydataguy]

Great to see you doing incrementally more advanced stuff 🙌🏾

Would love to see you do a video about the production side of a crewAI app such as data persistence, frontend, and deployment. Could be simple with streamlit and codesandbox.

Or whatever you're into (perhaps some sponsors)

[vastvitamins]

10 out of 10 hands down you are giving the most value on the internet

[amk]

woow, i just have finished your langchain video, and it was amazing, was looking for crew ai videos and now you dropped this, thank you again brandon for these amazing content..

[robel_asefa]

Loving this video so far! Had to pause at the 3-minute mark to hit that like button and say keep it up! 😂🤗

[davecastillo]

Outstanding Brandon. Thank you for one of the highest quality instructional videos I’ve ever seen. Please keep them coming!

[akmlatc]

Great explanation on crew ai! wondering if just running the firecrawl agent would find all the info without the rest of the crew. Most agents seem

[ITVIGNESHWARAN]

Please use opensource models rather than paid while these tutorials

[gulammohamed]

Very well thought out and choreographed explanations. Thanks.

[frag_it]

I am loving these tutorials I would like to see you do in depth on using vllm as an api point for serving llm using azure kubernates cluster it would be soo useful to the community as we can then use quantized models of llama3 70b with very cheap gpu to help serve applications. I would be just amazing for the community then you can use that to help make agents with lang graph tutorials bro I would love it

[Arkantosi]

Great work, but I wish you would code this (and other projects) out while talking. Seeing the workflow and folder structure etc. is quite rewarding.

[d.d.z.]

Thank you Brandon. So valuable, so helpful. ❤

[KumR]

Hi Brandon - Can we create an agent to login to a website and look for info ?

[ophelia]

Thanks for yet another great tutorial!

[webbee]

Excellent explanation + demo! Great work, I can understand how much effort needed to compile all this, so thanks! One feedback, the diagrams are not clear and vert hard to see. Can you please change the text, color, background, or size in such a way that makes it more clear.

Why do we need to add the tool to both "task" and "agent". Can't we just have in task?

Thank you.

[creatiiveart]

​ @bhancock_ai this is awesome! CrewAI just announced framework 0.51.0 with new features. Can you please create a new video with new version and new features?

[sunderrajan]

Great video and you are awesome as always. Can I use crewai to compare two identical pdf documents and generate the differences?

[barrybahrami]

how can I setup crewai to use an external chroma?