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

Подписаться 111 тыс.

Просмотров 237 тыс.

50% 1

Advanced RAG 101 - build agentic RAG with llama3
Get free HubSpot report of how AI is redefining startup GTM strategy: clickhubspot.com/4hx
🔗 Links
- Follow me on twitter: / jasonzhou1993
- Join my AI email list: www.ai-jason.com/
- My discord: / discord
- Corrective RAG agent: github.com/langchain-ai/langg...
- LlamaParse: github.com/run-llama/llama_parse
- Firecrawl: www.firecrawl.dev/
- Jerry Liu build production-ready RAG: • Building Production-Re...
⏱️ Timestamps
0:00 Intro
1:33 How to give LLM knowledge
3:05 Problem with simple RAG
5:55 Better Parser
9:01 Chunk size
11:40 Rerank
12:39 Hybrid search
13:10 Agentic RAG - Query translation
14:35 Agentic RAG - metadata filtering
15:52 Agentic RAG - Corrective RAG agent
17:33 Install LLama3
18:00 Code walkthrough
👋🏻 About Me
My name is Jason Zhou, a product designer who shares interesting AI experiments & products. Email me if you need help building AI apps! ask@ai-jason.com
#llama3 #rag #llamaparse #llamaindex #gpt5 #autogen #gpt4 #autogpt #ai #artificialintelligence #tutorial #stepbystep #openai #llm #chatgpt #largelanguagemodels #largelanguagemodel #bestaiagent #chatgpt #agentgpt #agent #babyagi

Наука

Опубликовано:

13 июн 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 206

@Jim-ey3ry Месяц назад

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

@kenchang3456 Месяц назад

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 Месяц назад

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

@CynicalWilson Месяц назад

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 😊

@shyamvai Месяц назад

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

@jaanifilmwala Месяц назад

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 11 дней назад

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

@titusblair Месяц назад

Yet again an amazing tutorial, thanks so much Jason!

@FightFlixTv Месяц назад

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

@starmap Месяц назад

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

@tkp2843 Месяц назад

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 Месяц назад

The search api is just insane on firecrawl

@scottmiller2591 Месяц назад

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 Месяц назад

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

@yunxinglu4020 Месяц назад

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

@MyAmazingUsername Месяц назад

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

@fredygerman_ Месяц назад

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

@contractorwolf 26 дней назад

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!

@heliolucio7691 20 дней назад

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.

@PIOT23 Месяц назад

What a great video! Thanks for sharing your knowledge

@jasonfinance Месяц назад

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

@seventhapex Месяц назад

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

@bruinx1679 23 дня назад

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

@beelzebub2808 28 дней назад

This is extremely helpful! Awesome!

@user-rj1eu6kp3u Месяц назад

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

@jorper98 Месяц назад

Amazing info shared -. Thank you!

@alinada9496 19 дней назад

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

@renderwood Месяц назад

Keep this up. This answered to loads of questions I have had previously, and were not answered in any of the HuggingFace tutorials!

@dataanalysiscourse785 Месяц назад

Awesome content!

@priyankajain1691 Месяц назад

Amazing tutorial! Thank you

@adityapanwar1220 13 дней назад

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

@free_thinker4958 Месяц назад

You're the man 💯👏

@guidoponzio6894 15 дней назад

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

@MrSuntask Месяц назад

Great tutorial! Thank you

@Entropy67 Месяц назад

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 😁

@Max-hj6nq Месяц назад

Solid video Jason

@justinwong2442 12 дней назад

Well said, thank you for this video!

@gaijinshacho Месяц назад

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

@rab0309 Месяц назад

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!

@Paulo-ut1li 3 дня назад

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

@jayco10125 Месяц назад

I am literally using this technique now in my internship for a project. I went through so many approaches and ended up on my version of this one. Wish you released this video about 2 months ago lol

@jackmermigas9465 27 дней назад

wow nice work thanks!

@Hash_Boy Месяц назад

many many thanks, bro!

@carta-viva 9 дней назад

This was awesome!

@puzitrajSinghKR Месяц назад

Thanks!

@lamprime 20 дней назад

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

@MyWatermelonz Месяц назад

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 Месяц назад

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

@azathought_games Месяц назад

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

@tunesafari8952 Месяц назад

Great video, thanks

@MrStevemur Месяц назад

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.

@arianetrek7049 Месяц назад

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.

@AdahAugustine-fy6xx Месяц назад

Thanks... Awesome video

@szpiegzkrainydeszczowcow8476 Месяц назад

You are relevant, Subscribing to your channel!

@asetkn Месяц назад

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

@liamlarsen9286 Месяц назад

awesome jason thank you

@kartiknighania8588 Месяц назад

OG Jin Yang from Silicon Valley.. Amazing video 🎉

@LibertyRecordsFree Месяц назад

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

@thenickcornelius 28 дней назад

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

@ujjwaltyagi9981 17 дней назад

Man we need a complete course from you on RAG

@sd5853 Месяц назад

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

@sharex21 Месяц назад

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

@Psychopatz 25 дней назад

This is a great trick, thanks

@jonm6834 Месяц назад

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

@ConsultingjoeOnline Месяц назад

Clicked that BELL too! 🔔

@98hghghg98 Месяц назад

great video jason! quick question, im wondering if a knowledge graph in place of vector database would be better since it mitigates the lost in the middle problem?

@EveDe-ug3zv Месяц назад

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 28 дней назад

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

@tonygil8617 Месяц назад

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

@FernandoOtt Месяц назад

Awesome content Jason. A Question. I need to create an AI psychologist and store college data, but this college data is a guide of what to speak, not the content itself. In that case, what is the best approach, RAG or Fine-tuning?

@mrkubajski9528 Месяц назад

I have to say, it is great :D

@abdallahelra3y118 Месяц назад

This is epic! keep up...

@mathavansg9227 Месяц назад

Best video💯

@Joe-bp5mo Месяц назад

This answer a lot of questions why my chat with PDF doesn't work, llama parser & firecrawl looks so freaking good!

@gojagadish 17 дней назад

excellent !!

@hamameskini8993 3 дня назад

good job broo

@nitesh795 15 дней назад

Great video Jason, but do you have a workflow video for a windows wsl setup?

@PoGGiE06 26 дней назад

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.

@faktogeek Месяц назад

here come dat boi!!!!!!

@EverythinTechnology Месяц назад

I thought we were gonna fine tune llama3 😢 but the fire crawl implementation looks unreal I’ll have to check that out and add it to my rags. I don’t know how well it’ll work for RAGs but people have extended the context window like crazy and still can do the needle in haystack to around 130k. If you have 64gb on the Mac you can try out the 256k context window Llama 3 released by Eric Hartford. Would love to see a side by side with both of them using the same embeddings.

@Truzian Месяц назад

would be great to get a video on best methods for data extraction from these pdfs

@MosheRecanati 11 дней назад

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

@freddy29228 Месяц назад

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

@shimin3356 Месяц назад

Hey Jason thanks for the video, I think it helps a lot. Can I apply on GPT as well?

@shephusted2714 Месяц назад

too many api calls here - do it local with no api calls - better and the model has to be able to crawl more doc formats - people will probably do p2p, real time and uncensored models for 'real' open source ai that has no limiting factors like api calls or tokens - this is where things need to go in order to take off, gain relevance and leverage economies of scale, of course cxl and better i/o will help but those are on the way. real open source ai will hit smb mkt in about 4-5 years and there will be more innovation and discovery - exciting times as we all watch the development curve

@ex3aliber Месяц назад

Amazinnnnggggg🎉🎉🎉🎉

@nrusimha11 Месяц назад

Thank you. Can you say a little about your hardware setup for this work? This information is missing from a lot of online sources.

@jasonkergosien3159 9 дней назад

Great video! Maybe I missed it. Is there a link to the python notebook?

@mateuszzemke9194 26 дней назад

great content! why wouldn't you use groq to speed up the agent response?

@RenAok Месяц назад

Very usefull, thank you! Is it posible for the model to retrieve images or graphs from a PDF, or it's only text?

@biiiiiimm Месяц назад

What about preparing data, for exemple as question / response, the response would be used to generate embedding and the response would be the data retrieved ?

@junmagic8847 Месяц назад

amazing as always. could you share the notebook please

@kaankorkmaz8180 2 дня назад

Checking if the LLM hallucinated by using an LLM... how can we rely on this? Thanks for the great overview.

@mikezooper Месяц назад

Interesting. Someone needs to create a wrapper which works out the best way to answer questions / queries, based on the input and question/query. I think intelligence of system could then be increased.

@sayfeddinehammami6762 Месяц назад

Good rag video, the thumbnail taking about "training llama3" is hurting my brain tho

@nikhilmaddirala 18 дней назад

Do you think this could be combined with the "group of agents" framework you described in a previous video?

@drakouzdrowiciel9237 Месяц назад

thx

@eventsjamaicamobileapp1426 Месяц назад

Great video. How do I add PDF documents and llama_parse to the python notebook?

@sinasec Месяц назад

Great thanks. Can we get the repo and link to the colab notebook?

@CecilMerrell Месяц назад

I like using gemini for getting quick up to date answers, and chat gpt for stuff that doesn't require up to date stuff

@Seymur-cg5do 11 дней назад

where can i get the notebook code?

@chiluone 17 дней назад

Can we have access to the jupyter notebook for closer inspection and deeper learning? :)

@Dom-zy1qy Месяц назад

4:36 Someone walks into the void and disappears

@uptonster 25 дней назад

great video! Is there a github location with the code?

@ConsultingjoeOnline Месяц назад

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

@gdr189 Месяц назад

Hi, what are the areas current LLMs excel at? I am new to this world of AI, but not IT (familiar with infra). It is good that people are trying out things to see what it can do. But my naïve thoughts are that as a language tool, it just looks for patterns of words that appear close together, and knows enough of the formation of language that it produces text that is not only readable, but also relevant. But this surely must have limits, if it does not actually understand? Would it be serving up answers from a well vetted and written sources such as internal KMS by using this RAG method? Our team was thinking about it use for education / learning - perhaps tied into custom flashcard and evaluation of human provided answers. Alongside the still very useful text summarisation, alternative wording suggestions.