"I want Llama3 to perform 10x with my private knowledge" - Local Agentic RAG w/ llama3

[@Jim-ey3ry]

This is prob one of the best RAG video I've seen, so many learnings in 20 mins

[@kenchang3456]

Man, your videos keep getting better every time I look. You have a great mind and your presentation is excellent. Thank you very much, again, for sharing!

[@magicismagic123]

he is much better than 99.9% wanna be over hyped ai gurus on youtubu, twitter and linkedin!

[@free_thinker4958]

@@magicismagic123 of course, jason is ahead of those fake ai gurus throwing bull***shit content only for views and buzz

[@LauraMoreno-z3d]

@@magicismagic123 hes lying to you, this solution isnt local

[@shyamvai]

One of the most informative RAG videos I’ve seen. Can’t wait to see more from your channel.

[@CynicalWilson]

Holy crap! This gave me such amazing background knowledge, love it! Now, what would be extra cool, would be if you could do a real "hands-on" type of workshop to go through it all by setting up the environment completely, including the actual training/RAG implementation of a set of various document types (PDF, excel, website etc..) to extend a locally running llama 3 instance 😊

[@JanMasata-b4m]

Did you find something like that?

[@JonathanCombs2023]

Thanks!

[@AIJasonZ]

Thanks Jonathan! ❤️

[@jamesrruff]

I appreciate your generosity in taking the time to break this down. Thank you.

[@FightFlixTv]

This is the best RAG video on the internet, awesome job, no fluff, high complexity but easy to understand, nice work

[@digitallifedigitalindia9023]

00:05 AI can revolutionize Knowledge Management 01:46 Llama3 can process precise knowledge with fast inference 05:27 Market strategy for AI startups 07:16 Convert PDF files to markdown format for enhanced accuracy and control 10:47 Finding the optimal chunk size through experiments 12:34 Hybrid search combines Vector search and keyword search for better results 16:12 Building a local agentic RAG with llama3 17:48 Running Llama3 model on local machine and using Visual Studio Code 20:53 Setting up key components for Llama3 performance 22:20 Creating a complex agentic RAG workflow for document retrieval and answering

[@kaushalbhavsarrocks]

Really well done, sir! To the point and informative. I wish people just made videos like you do. Hats off!

[@MrLiteratur]

Thanks, Jason, incredible as always! Would you consider sharing the code from the walkthrough? 🙏

[@AIJasonZ]

Thanks mate, appreciate it! Code is in the description link!

[@yashsrivastava677]

@@AIJasonZ Link is not there

[@loserc1854]

@AIJasonZ Link is not there 😭😿

[@anthonybisong6744]

This is the best RAG tutorial and training ever created. Thank you for sharing this great knowledge.

[@esiriel]

Interesting ! I enjoyed your full breakdown, under the hood - thank you. The Private part is very important but I didn't want to re-invent the wheel and deal with bugs... so I'm using Spheria AI for my life's knowledge base - full privacy and data ownership... Almost same as running on local, and their UX is actually great !

[@titusblair]

Yet again an amazing tutorial, thanks so much Jason!

[@fredygerman_]

You always amaze me by the amount of knowledge I get from your videos

[@scottmiller2591]

1) The link for the corrective RAG agent had an extra URL attached at the end which caused it to fail; manually tracing the link got me to the proper location 2) LlamaParse looks like a wonderful tool, since I have a lot of documents with equations, and I really need it to grab equations, if for no other reason than to return them. Unfortunately, LlamaParse requires an API key and seems to send PDFs off for processing, something that others have noted and there is an open issue from 2 weeks ago. As of 3 hours ago, it's still an open issue - clearly most companies don't want to send internal docs out of house. Hopefully this gets resolved soon. 3) Really liked your presentation - easy to follow every step with the provided materials.

[@dennou2012]

Hopefully we will have more better options for local use - shame it's not a local only pipeline yet

[@yunxinglu4020]

yes - I have found this issue too. LlamaParse seems use OpenAI llm to process the pdf and it leads to the privacy concerns.

[@SahlEbrahim]

i cant find this particular code. the code in the link uses open ai.

[@thekr0w561]

@scottmiller2591 Hey, do you have any suggestions for good local PDF Parsers?? LLamaIndex is amazing but as you pointed out, it is only accessed through API unfortunately...

[@scottmiller2591]

@@thekr0w561 I haven't tried either of the following, but they are the most recent contenders for reading PDFs with LaTeX math and tables (both on GitHub): 1. opendatalab/MinerU 2. facebookresearch/nougat

[@heliolucio7691]

This is the best RAG video that I saw, I current work with it so I can say: this video is GOLD, enjoy everybody! And thank you so much, man.

[@offeraviad]

Love the details!! great video!

[@tkp2843]

Firecrawl boosted our RAG accuracy at our company. fast + provided good markdown format. Llama parse also super helpful too! Amazing video Jason! This is gold! Edit: thanks for the likes :)

[@rafaelmiller9147]

The search api is just insane on firecrawl

[@brandonmchugh9821]

Omg, this is exactly the info ive been looking for. Great video. Insanely insightful.

[@starmap]

Great content! Thanks for putting in the effort. Will use this.

[@amitbuch]

Very thorough introduction. Very valuable inputs on refining and ranking of retrieval pipeline design.

[@jasonfinance]

Didn't know about the Agentic RAG techniques, thanks for sharing!! That's definitely a trade off between speed & quality, but good to have the option

[@Deeneeshsu]

You are doing great man. Keep it up ❤ love from Europe

[@NdxtremePro]

Thanks for this video! You explained the over arching idea very well, and thanks for the idea.

[@seba29]

you won a new subscriber with this superb video! thanks a lot for sharing all the know how

[@seventhapex]

dude... great video! Thanks for the knowledge!

[@MerleRichardson-z1d]

❤ your teaching style. Thanks you. I have subscribed and I will be following you.

[@realistindenial]

Bravo, well done! This video is not for the faint of heart, but it's great for those who are good at grasping technical concepts quickly and leveraging the information contained into real world usage. Thank you!

[@MyAmazingUsername]

Really great tutorial, teaches a lot in very short time! Thanks!

[@Saintel]

Great job!

[@beelzebub2808]

This is extremely helpful! Awesome!

[@Mystrykdlad]

This is one of the most detailed RAG video, I came across Hope I can create atleast one such rag model using this information Thanks a lot buddy 💥💥

[@dataanalysiscourse785]

Awesome content!

[@GlueTubber]

it's like this: you have trained yourself to be a computer programmer, but you still go to stack overflow to answer questions. Your programmer training is the baked in knowledge, stack overflow is your RAG.

[@bruinx1679]

Excellent video! I don't have much experience with RAG and this was sooo helpful!

[@alinada9496]

You said it all !!!!! , Thanks for this illustrative video

[@adityapanwar1220]

Wow, This turns me back to think that the RAGs i implemented before was just a mini brother of this. Amazing work buddy.

[@Entropy67]

Subscribed, dont have an AI company since I'm still a poor student... this video was very informative, the man speaks at two times speed just like my professor. I respect it 😁

[@guidoponzio6894]

Bro i been watching a lot of llm videos this past days, and by far this is the best i have seen. Thank you for your work

[@free_thinker4958]

You're the man 💯👏

[@beastmastern159]

Hi jason from spain good video

[@PIOT23]

What a great video! Thanks for sharing your knowledge

[@contractorwolf]

Jason, I watch a lot of AI videos but I learn the most from yours. I am actually excited everytime i see you have put another one out. Keep up the great work!

[@jackmermigas9465]

wow nice work thanks!

[@rab0309]

great video keep making these please.. only "criticism" / advice if you can call if that is to keep things focused on local / open source solutions as much as possible.. love the use of Ollama here for example.. things that perhaps don't require API keys, subscriptions, external integrations / dependencies help people like me understand more of what's going on in a workflow like this! thanks again!

[@thenickcornelius]

Came to train my 3 Llamas... Now I'm a full stack developer.

[@justinwong2442]

Well said, thank you for this video!

[@Paulo-ut1li]

That's the most useful RAG video on YT. Thank you!

[@omvrio-d2v]

MAAAAAAAAAAAN AMAZING VIDEO VERY INSIGHTFUL AND HELPFUL TO LEVEL-UP YOUR RAG IMPLEMENTATION. HIGHLY RECOMMEND.

[@MyWatermelonz]

I prefer finetuning to RAG first then RAG on top of the finetuned model. Just a simple QLORA is all you need. It really helps a ton.

[@helix8847]

How would you go about doing that, as in just do it backwards from the video?

[@Omar-p9r3c]

right when i needed it, thank you man! also, just finished watching and i understood the theory behind it but kinda got lost during the code explanation, i might watching again and again

[@ConsultingjoeOnline]

Great video. Thanks! A lot of very good tips!

[@edmundwong2671]

You're the best programming teacher.

[@gaijinshacho]

Great timing! Why do you always read my mind JASON!!?! lol

[@lamprime]

Is there a GitHub repo for the examples that you've demoed? Excellent video!

[@kartiknighania8588]

OG Jin Yang from Silicon Valley.. Amazing video 🎉

[@vjunloc1]

Yo Jin Yang, Great video man

[@HollyTroll]

thank you so much for the info

[@hhaaasshh]

many many thanks, bro!

[@jorper98]

Amazing info shared -. Thank you!

[@MrSuntask]

Great tutorial! Thank you

[@hyawey7430]

Thank you so much!

[@azathought_games]

Such a bait and switch. Thumbnail promises fine tuning tutorial. Delivers best improve-your-RAG video on the internet. Excellent work.

[@akash.vekariya]

Really the best RAG video on youtube so far

[@Max-hj6nq]

Solid video Jason

[@AdahAugustine-fy6xx]

Thanks... Awesome video

[@arianetrek7049]

The corrective RAG schema explains why AI often tries to bring results from the web even when you tell them not to in prompt. If it doesn't understand the source properly it will look elsewhere. This was insightful, thank you.

[@xcalibills]

thanks for sharing! 🐐🐐🐐

[@EveDe-ug3zv]

Great video Jason, I only missed routing as a technique to determine if your question should really go through the RAG. James Briggs has done a few good videos on “semantic routing”. Is your example notebook available somewhere?

[@christenjacquottet9799]

I'm wondering the same thing. Don't see a link to a github repo

[@sd5853]

I don’t understand everything but I can feel the gold penetrating my ears

[@p3nGu1nZz]

fantastic thank you for sharing

[@sperazza]

great video, thanks.

[@MrStevemur]

Thanks! It's so fascinating how these programs 'think.' Even if I don't install one, concepts like chunking seem to translate to humans as well.

[@liamlarsen9286]

awesome jason thank you

[@tunesafari8952]

Great video, thanks

[@tonygil8617]

Hi brilliant session , do you have a link for the notebook ?

[@carta-viva]

This was awesome!

[@sharex21]

I'm a simple man. I see a new AI Jason video, I click.

[@ConsultingjoeOnline]

Clicked that BELL too! 🔔

[@Franjabube]

SO GOOOOOOOOOOOOOOOD CONTENT !!!

[@PoGGiE06]

Great video, thanks. New subscriber (and like) here. I had a couple of questions though: why use langchain? It seems unnecessary from what I have read. Would also love a demo ipynb/copy of code.

[@jonm6834]

You got a sub. Finally, an AI channel that actually teaches.

[@MosheRecanati]

Where I can find the notebook that you're presenting in this great video?

[@Sashalii]

Man! You're much better than AI! 😀

[@asetkn]

Platform agnostic LLM space overview videos from Jason are the best on AI YT

[@szpiegzkrainydeszczowcow8476]

You are relevant, Subscribing to your channel!

[@Psychopatz]

This is a great trick, thanks

[@mrkubajski9528]

I have to say, it is great :D

[@MinoasPediadas]

Thank you for the explanations, very helpful. I would appreciate your thoughts on the following scenario: Let's say you have a pdf file that contains some criteria/requirements. Assume also you have a second pdf file which describes a project and also describes how the project will address the specific criteria/requirements defined in the 1st file. I was wondering if there is an LLM-based workflow that could examine how well the project description addresses the criteria in the 1st file. I was thinking of a process like this: 1. Get some ready-made LLM model like Ollama or BERT 2. Train it again with your 1st file as an input 3. Load the second file to a vectorDB and create a chain 4. Query the second file I'm not sure if this works though and I'm not sure how I can specify my queries to cross-examine SPECIFICALLY the second file against the SPECIFIC criteria of the 1st file. Would you have some kind of guidance for me?

[@VipulChaudhary1337]

Goddamn it Jian Yang

[@ujjwaltyagi9981]

Man we need a complete course from you on RAG

[@AbdulMajeed-lf5sq]

I watch lots of AI videos and 99% of them are just a waste of time. As an AI engineer, this channel is hands down the BEST yet KEEP UP👏🏼

[@gojagadish]

excellent !!

[@CaptainOverpants]

where can i get the notebook code?

[@LibertyRecordsFree]

Amazing lesson! I learned a lot in just 20 min!

[@freddy29228]

Thanks Jason, great video, this explains RAG pretty well. Subscribed!

[@walidr]

Llama parse is used via their api. You send data to their servers. So it’s not truly local.

[@adrowsypoet]

Doesn't it work offline tho? Couldn't you just keep it unconnected to the internet? Jw

[@walidr]

@ no. Llamaparse is an online service, running its own proprietary model in their online server.

[@abdallahelra3y118]

This is epic! keep up...

[@Sandheip]

Llama3 integrated with local agentic RAG to leverage private knowledge sounds powerful! The potential for enhanced performance is exciting. #AI #Llama3 #Innovation

[@faktogeek]

here come dat boi!!!!!!