A few people asked “why only vectorise one column instead of the whole csv?” Adding a few more explanation here: So vectorise is mainly for search, and the column to vectorise can be considered as “index” or “id” of the dataset; while the data it return will still be in question/answer pair; The reason I want to vectorise only one column is because: 1. It save cost - vectorise using embedding model which means every token we vectorise generate cost 2. It increase accuracy, in this case I want to only search for past customer email instead of sales response; search both column might return wrong answer “e.g. search for “interested in learning more”, it can return pair: “client: stop sending me emails; sales: understood, let us know if you are interested in learning more in future!” Hope this help!
@ozfish17 Жыл бұрын
It seems Embedding enriches your search query. how about answers? In your example, do you 'train' llm with Q&A pair?
@AIJasonZ Жыл бұрын
@@ozfish17 yep, it return both Q&A pair!
@Taskade Жыл бұрын
Jason, brilliant step-by-step guide on knowledge embedding! Your breakdown of the process was super insightful. I'm curious about how AI Agents in Langchain perform, especially in long-running scenarios. Hope you'll consider diving into that topic in the future. Keep up the stellar content!
@sandeepbansal1195 Жыл бұрын
So if you want the output response email to be generated by the LLM based on a specific tone, why wouldn't the 2nd column be a part of vectorizing the dataset?
@csss142 Жыл бұрын
Hey Jason! What would be the best way to do this with financial PDFs? I want to ask questions and get accurate insights from the large documents. Would using embeddings be best or the fine tuning from your other video? Thanks! @AIJasonZ
@psychxx7146 Жыл бұрын
Small channels like this are the ones that hold the most values.
@Helpsmallbusinesses Жыл бұрын
In 2 minutes and 54 seconds you explained what is vectoring better than any other video online. You made it easy. Thank you!
@funkyboodah10 ай бұрын
man you have a really rare ability to explain super complicated things in a very simple way and organize the information so it's even more clear. Bravo and thank you
@averagegamer9513 Жыл бұрын
Great video as always, Jason. Thank you for making one of the few channels with genuine AI tools video that actually demonstrate implementation and applications rather than hyping up the content through sweet talk then simply dropping an affiliate link.
@devklepacki Жыл бұрын
This! I feel so grateful that the KZbin algorithm blessed me with Jason's channel. Beautiful explanations and clear steps.
@koen.mortier_fitchen Жыл бұрын
Yeah, he's one if the real ones. I've asked him if he could add a github for the code. It's the only thing this channel lacks imo.
@frankchangshow Жыл бұрын
@@devklepackisame feelings here
@sidavidsin Жыл бұрын
Thank for sharing your knowledge with us, your channel is literally a gold mine of information. Keep doing what you doing, Jason!
@verasalem5071 Жыл бұрын
Love your content, very easy to digest and understand. The only recommendation I would give is to use other embeddings and LLM models besides OpenAI. Mid/Large sized companies cannot use OpenAI in their environment because of legal issues around OpenAIs data retention policy. Alot of companies want to develop their own implementations so including other models like Llama 2, Vicuna, etc would allow you to reach a bigger audience.
@AIJasonZ Жыл бұрын
yea great points, thanks for the recommendation! totally get that company dont want to send any data to OpenAI LOL
@Ascended23 Жыл бұрын
+1 for using more open models. I love your content and the approach you take to your videos. But even though I'm not a big company I just value using systems that are open instead of closed.
@humadi200110 ай бұрын
I've watched many video on this topic and I can say that your simple examples has covered most of what I need to know. Thanks Jason.
@_arman_ Жыл бұрын
Man... you have a serious gift for teaching! This is super helpful. Thanks.
@shivamroy1775 Жыл бұрын
Absolutely great video, I loved that you took the time to explain everything in theory and then went on to give a detailed walkthrough of the code. Please keep posting such videos !
@muhammadanasazambhatti2772 Жыл бұрын
Thank you very much! Nobody explained Embedding and Vectorization like this! Thank you again!
@normanluismadrid422 Жыл бұрын
this is virtual gold, mad props to jason for clearly describing complex topics and even showing practical application, saved me hours of research lol, it'd be great if you can touch up on the various services out there that offer AI services that embed, and how they compare in performance, pros / cons etc.
@fuxxs5994 Жыл бұрын
I really love your style, first explaining the theory and then demonstrating it by an example
@photon2724 Жыл бұрын
Anyone looking to make a great startup in AI,you have to jump on this!
@i_forget Жыл бұрын
Working on it!
@dragoon347 Жыл бұрын
Working on it now
@nguyenvanduc20008 ай бұрын
I have the same idea in mind. I have tons of product documents that I wish I could just ask an agent something about it instead of scrolling hundreds of word pages. I really appreciate your video man.
@devinoutfleet1998 Жыл бұрын
Bro... you are incredibly smart and are a great teacher. This is going to provide 10x value to my users
@rbdon5607 Жыл бұрын
Thanks! What do you see as the major pros and cons doing it through coding your own versus a platform such as Relevance AI?
@frankchangshow Жыл бұрын
I would love to know As well
@davidkwon1233 Жыл бұрын
one of the best channels out there, really appreciate your content!
@PlectrumShorts Жыл бұрын
Great tutorial! You covered a LOT of ground quickly, but thoroughly. Haha. Nice work.
@Optable Жыл бұрын
You have helped the community so much with this valuable content. Keep it up my friend, i'll be watching!
@farid310110 ай бұрын
I am really surprised that these tools can help so many businesses doing the low-cost and autonomous response specifically for customer service! Great video!
@_yasser6 ай бұрын
This is my new favorite channel. The topics are pretty dense and dry - but you make them super easy and fun to learn. Thank you!
@jasonfinance Жыл бұрын
the best video about embedding ive seen; thank you!
@VaibhavShewale Жыл бұрын
this is just awesome, now people who didnt had idea now dont only have idea but also reference
@growthub8541 Жыл бұрын
So helpful! I started using relevance ai because of your videos & just as a no-code developer been able to build some sick ass LLM chains with Zapier Custom HTTP Requests. I have my development team even using it & it’s definitely speeding up our velocity to iterate🙌🔥
@AIJasonZ Жыл бұрын
thats great to hear! 🤘
@camach28 Жыл бұрын
It would be amazing if you could make a video creating a knowledge base using long pdfs as source,, and use gpt as well to make an expert assistant in a topic.
@frankchangshow Жыл бұрын
Yes like if the data source is like a book and we want to search the contents in it giving relative data like “I remember this part of the book saying something like this… where was it?” … or “the book had this story … where was it and the main ideas”
@JJ-vq8mu Жыл бұрын
Great job and appreciate a lot on sharing your knowledge. Looking forward for Open LLM content.
@SaminYasar_ Жыл бұрын
Keep it up man probably one of the only channels with incredible value
@Gingeey23 Жыл бұрын
Great video Jason, however the biggest challenge for companies will be ensuring that commercially sensitive information isn't fed into hosted LLM models due to security concerns. Would be really interested to see how you would approach this challenge, and potentially try to deploy this tool locally? keep up the good work!
@AIJasonZ Жыл бұрын
Thanks mate! Yea I agree, I heard business talk about sensitive information a lot, especially ones with clients data; There are 2 ways I see it can be solved now: 1. Self host LLM, using Azure self host version or even using open source models; so you don’t send info to openai 2. Anonymoulyse your input/output data, so openai don’t have a clear idea that data A is from company A;
@devklepacki Жыл бұрын
If using hosted LLM like OpenAI's this would probably 1. require just a lot of manual work with clearing all the data or 2. first pushing the data through lighter local LLM with a task to clear any sensitive information (like they used one LLM to create training prompts for another LLM). Just a thought, tho
I really like your video. You knows how to reach the people attention. Please make more videos like this 😊
@stepkurniawan Жыл бұрын
yo bro.. i really like when you explain all the step-by-step and all relevant tools out there! thank you!
@TheDestint Жыл бұрын
This is super duper helpful man ! Great work and thanks !
@christhornham8 ай бұрын
Outstanding. Your ability to explain complicated topics is incredible. Thank you.
@michalf16 Жыл бұрын
Love your content good sir, tuned for all next videos you are the leader
@Ozla102 Жыл бұрын
The video is very inspiring and straightforward, a valuable lesson
@koen.mortier_fitchen Жыл бұрын
Thanks for your work Jason. You're one of the best, and I follow tons.
@wojpaw5362 Жыл бұрын
Absolutely outstanding. I liked, subscribed and shared. Best explanation of knowledge embedding I have come across!!!!
@AndrejsKarpovs Жыл бұрын
I have a couple of questions: 1) I have 0 knowledge about Vector databases, but don't you need to define some kind of access related information, connection string, username/password, etc. to use it? Did you define it in .env file? 2) How does this method compare to PEFT/LoRa? Does it basically achieve the same thing? It looks like embeddings can be a faster solution
@AIJasonZ Жыл бұрын
Hey mate! 1/ if you want to have the vector database stored on managed cloud solution like pinecone, then yes you can create account and use them; in this example I used Faiss, which is not a managed database solution; so it just store on your local machine 2/ so Lora or other fine tune solution as I mentioned at the beginning is more use case of getting LLM behave in certain way (e.g. digitise someone), while embedding is useful for knowledge retrieval (e.g. Q&A on your own data)
@Fiop22 Жыл бұрын
I haven’t watched the video, but to answer your first question if you’re using a cloud service like pinecone then yes. Alternatively, you can store the embeddings locally as a .csv for example and perform the lookup via cosine similarity with numpy for example.
@half_way_expert Жыл бұрын
Another great video! Thanks Jason, keep up the excellent work
@ludwigvanbeethoven61 Жыл бұрын
I wonder why those AI channels, like yours, are not exploding. This is so important for the future what you all are doing. Only a few people get this!
@kurtcampher4716 Жыл бұрын
thank you for this As a dev with no AI experience, you really make it easy to understand
@kiraakamaru Жыл бұрын
This is exactly what I was looking for, I have a question Jason: How can we secure our company personal data?
@Artificial_Noob Жыл бұрын
Great video man! I hope you can cover more "No Code Methods" for beginners like me that are not very technical! The last part of this video was GOLD for me. cheers!
@pietdebeer7972 Жыл бұрын
Same here
@aliyousefi9735 Жыл бұрын
you're the man Jason, great content!
@shethromesh Жыл бұрын
Loved to see similar demo of knowledge search with open source models not with openai models
@maciejbalasinski2419 Жыл бұрын
Thanks for No coding alteratives
@pietdebeer7972 Жыл бұрын
I'm blown away. Thank you!!
@rahuliyer6007 Жыл бұрын
Came here after the fine tune model video - looking for exactly this. Thanks!
@naimneman Жыл бұрын
Amazing video Jason! Pretty useful information. I would love to see a video about GPT4All as a personal assistance for everyday life.
@RichardGetzPhotography Жыл бұрын
Thanks!First, you have lorem ipsom text on your contact page (1) I have a lot of general documentation, not Q&A. Do you have a video of best practices for that workflow? (1b) I have a lot of docs (PDFs) that has text on how to do something and images of where to do it. Not so much Q&A. How affective is embedding at deriving answers from documents or should that be fine-tuned? (2) I had GPT write me an embedding script straight from python, can you do a video on that vs openAI embeddings or others? Best practices for embeddings? (2b) I presume I should take large docs and break that up into subjects (chapters) to embed?
@elijahbock4357Ай бұрын
Hi Richard, did you ever figure this out? I've spent weeks trying to do something similar to fine-tune a model to assess academic writing for APA format
@gautamdawar5067 Жыл бұрын
This is pure gold. Thank you so much!
@ridg2806 Жыл бұрын
Really high quality content, thank you Jason!
@manojnaidu6198 ай бұрын
Cannot be more valuable than this. Loved it 🎉
@kylelau1329 Жыл бұрын
have been waiting for this video, Thank you!
@chrisvienneau3366 Жыл бұрын
Great content and love the intros
@aliq67098 ай бұрын
This was super helpful. Thank you, Jason!
@manideepatalukdar9201 Жыл бұрын
Great video! Very simple to understand.
@KarlJuhl Жыл бұрын
Great resources Jason, I will add to the flood of comments - you are a great communicator and you move at a good speed. Thanks for sharing! It is interesting how many langchain UI apps are being built. Relevance AI looks to be the most integrated from end to end, with such an easy deploy process. I am curious to know your thoughts on using a UI tool like flowise or relevance AI versus custom programming.
@frankchangshow Жыл бұрын
I have the same question
@karankanchetty832010 ай бұрын
Great job. You deserve more subscribers.
@Scooterboy_and_others109 Жыл бұрын
At 7:35 in video you said you need not do TEXT Splitting (do it only if the input file content is huge) Is there a way to know (in advance) by some code if the threshold has reached and I need to do TEXT Splitting? In your case CSV file had only 219 rows, but how can I know 219 rows has NOT crossed that threshold limit?
@aibeginnertutorials Жыл бұрын
Hey Jason thanks for the always excellent presentations and information. The Streamlit and RelevanceAI information were interesting and useful. Relevance reminds me of another great product, Flowise.
@frankchangshow Жыл бұрын
I don’t know if I should use stack ai, relevance ai, or flow wise. Going into decision fatigue now
@JessyHoule Жыл бұрын
Thanks!
@shrvn110 Жыл бұрын
this dude is on FIRE 🔥
@robertcormia7970 Жыл бұрын
Very well done! Straightforward to follow!
@wiktormigaszewski8684 Жыл бұрын
anyone knows how the graphic on #4:05 is made? I see this style everywhere, so I assume there is some tool for styling such pretty graphics easily. Let me know!
@AssassinUK Жыл бұрын
This was 🔥🔥🔥. If I hadn't already subscribed, I would have. Excellent use case! Looking to impliment this using Flowise.
@AlessaOxygen-ot4rl Жыл бұрын
This is hilariously good. Thanks for this wonderful ressource!
@Grumptr0nix Жыл бұрын
This is exactly what I was looking for... I have a tremendous amount of assets (Requirements docs, project plans, etc) that we've created over and over for all our engagements, and I'm trying to find a way for us to stop reinventing the wheel. All of which are in our Google Drive, but I'm having trouble conceptualizing how I'd be able to turn that into vectored data (you talk about text splitter, but I'm still a bit confused about its application). Anyways, I'll do more research but this is amazing content. Thank you.
@Grumptr0nix Жыл бұрын
And for sure, the legal issues with our business data and OpenAI that is discussed in other comments have been a blocker for us as well, but at least there's options.
@patriciodiaz2377 Жыл бұрын
Thanks a lot for the info!! Greetings from Mexico 🤙
@rimilien5 ай бұрын
Thank you my friend! Awsome work!
@T0mstyle Жыл бұрын
Really like the video, but the prerequisite knowledge makes it hard to follow. I have no idea what an .env file is (6:50), so it would be great if you could hint at where I could start.
@IanTrolinger Жыл бұрын
this is the best video on your channel.
@nealshah58747 ай бұрын
This is the greatest video ever created
@ristopaasivirta9770 Жыл бұрын
My friend. You have an uncanny ability to teach AI science and concepts to us pepegs. This and your other videos are really good at explaining on how the neural networks work, not just how to do the thing.
@devklepacki Жыл бұрын
One more thing I didn't get is at the end, why vectorizing only one part of the data may give better results? Doesn't it need both questions and answers to connect the style properly?
@AIJasonZ Жыл бұрын
So vectorising is for the purpose of similarity search, almost like ID - “Find the most relevant data point”, but the data point still contains both question & answer; vectorising both columns can potentially reduce accuracy because imaging customer message is “interested in learning more”, but searching both customer message & response might return pair like: customer message “stop sending me emails”, our response “Understood, feel free to let us know if you interested in learning more in future”; Which is not a relevant scenario
@devklepacki Жыл бұрын
@@AIJasonZ Ah, understood, thank you a lot. So we only want to vectorize the data we actually want to search within! So we only have a new input with a customer message, we want to search for the same vectorized data inside old customer messages, and based on this a company message is retrieved and a new response is created by LLM. That's so nuanced. Thank you for sharing your knowledge and answering all the comments. At least what you have from them, is that you can see what people struggle with 😅
@elbaekk Жыл бұрын
I'm confused at around 15:30 in the video; how does it know how to respond if we only embed the questions/inquiries?
@AIJasonZ Жыл бұрын
So the purpose of embedding is just for search, but the data it return will still be the full question/answer pair; (almost considering the column to be embedded as “ID” or “index” for similarity search)
@TheRcfrias8 ай бұрын
hey @AIJasonZ, great video! I wonder if you could create another video where you could combine 1) Fine Tuning, 2) Knowledge base AND 3) API Data. The scenario is as follows: "I want to respond to a customer with my style of writing (Fine Tuning) about the services I provide (Knowledge Base) and my available schedule for a demo (Schedule API)". Is this something we can mix together? or how would we tell the model it should suggest a demo meeting?
@DeLeizard Жыл бұрын
Thank you for the super video. I'm learning LLM and am quite confused between knowledge base embedding, that was mentioned, vs prompt tuning. Could you tell me the difference?
@MrDe0 Жыл бұрын
This is GOLD !! Thank You !
@BillVoisine6 ай бұрын
Thank you Jason, this is awesome an very helpful!
@adityatiwari364617 күн бұрын
Perfect explanation sir , thanks a lot❤
@SwastiikP Жыл бұрын
Question: Can this be done with ohter LLMs like Falcon for example instead of using OpenAI API key [kinda new ai development and wanna try things out before paying for stuff]
@CyberSQUID9000 Жыл бұрын
More excellent content, thanks mate
@AzizKhoury Жыл бұрын
how do you prevent leaking private information that are in the emails? This is an issue with HIPAA and private health information (PHI).
@izzyc31417 ай бұрын
Yes please someone answer this bc ChatGPT is not HIPAA compliant
@andypejman Жыл бұрын
Do you only need to have one use case for the data or can you just upload a lot of data that could be used in different ways? For example, your use case was for responding to customer emails from what I understand, but what if you wanted to upload all of your organization's data and then ask it various questions or use it in various ways?
@himanshumishra6253 Жыл бұрын
hey, can you share the salse_response.csv file also, it's not in the git repo
@devklepacki Жыл бұрын
I'm 6 minutes in and found it confusing with your practical example. Wouldn't teaching LLM to generate based on previous company interactions be more suitable for fine-tuning? In the beginning, you said that the knowledge base is more for retrieving specific/hard data. How I see it - fine-tune LLM to talk in a style that a company wants (e.g. very official or casual), and then feed it data with embedding for it to be able to answer specific questions about e.g. some products' technical details.
@AIJasonZ Жыл бұрын
Hey man, you are totally right, you can use both finetune & embedding for the best results! in this case what I want it to do is more respond to message with the same logical argument + company knowledge (e.g. product details, pricing, etc.), and also company info & knowledge can be updated time to time, retrain the model every time won’t be an effective way; But you can totally do finetune -> teach voice & tone + embedding for knowledge retrieval
@devklepacki Жыл бұрын
@@AIJasonZ I see now! So you treated data inside emails regarding product details and pricing as the "hard data". Also what I understand is that with only fine-tuning it'd be hard for AI-generated responses to include things like Zoom invites links. Is this correct? But what if a company (e-commerce?) adds X amount of new products every week and AI must have access to all of the old and new products' technical data? Can we just vectorize each product when it's added and push it to the knowledge base? Sorry, I'm a noob on the topic! With what you just said in the comment it seems even more complicated and not so black and white. I'd have never thought about treating emails the way you (correctly) described.
@AlejandroPalacios-p4t4 күн бұрын
Grate video!! How would you apply this to a inventory dataset with several columns? Should only vectorize the ID column ?
@markieuanroberts Жыл бұрын
Awesome explanation, thanks.
@Juneg_Xiao10 ай бұрын
Hello sir! thank you for your sharing! I would like to ask what if I have a Claude API which means it is from Anthropic instead of Openai. How do I change the code to cooperate with that? Thank you very much!!!
@rolandcucicea600610 ай бұрын
hello anthropic doesn't have embeddings yet.
@Juneg_Xiao10 ай бұрын
oh okay, thanks! @@rolandcucicea6006
@ivant_true9 ай бұрын
you make really useful videos man
@davide.2349 Жыл бұрын
Jason you are awesome!
@xulipaTV Жыл бұрын
You are the man Jason!
@rverm1000 Жыл бұрын
great video! is that enough info to go out and start building a customer response ai for other people or businesses?
@AfeezAzizTechGenius Жыл бұрын
Hi Jason, is there an alternative for OpenAI Embeddings? Because if possible, id use opensource projects rather than using OpenAI.
@AC-sj7hu Жыл бұрын
Thank you for your video, also could you share a way to implement it in a website ? Not judt deploy lile independant page, jsut intrgrate with an existing website ? Thank you so much 😊
@groccy Жыл бұрын
Thank you for making these great contents, Jason! You literally created a gold mine for LLM practitioners. Really appreciated it! Any chance we can find your codes taught in this video online?
@AIJasonZ Жыл бұрын
Hah I had a hard time to define my audience, and LLM practitioner is kinda perfect! Sure thing, I will open up the GitHub link soon
@groccy Жыл бұрын
@@AIJasonZ Thanks. Can’t wait!
@satyamgupta2182 Жыл бұрын
Thank you so much for your video. Its very helpful. At the same time, is there a way to run this with Llama-2 or other open source LLM's? Edit: If security is my main concern, how do I go about embedding?