OpenAI Embeddings and Vector Databases Crash Course

Поділитися
Вставка
  • Опубліковано 21 лис 2024

КОМЕНТАРІ • 199

  • @photorealm
    @photorealm 7 місяців тому +16

    That was the first video that actually gave me a understanding of how vector DB's kind of work. Thank you for sharing.

    • @goldenant9450
      @goldenant9450 Місяць тому

      Key word being, "kind of" 😂😂

  • @SuperITPRO
    @SuperITPRO Рік тому +56

    My ADHD normally overrides my concentration. Your tutorial pace, live coding, and narrative made me complete my 1st Open AI coded app - thank you!

    • @zzej
      @zzej Рік тому +1

      Same

    • @nicholastroyandersen9505
      @nicholastroyandersen9505 Рік тому +4

      Don't use ADHD as an excuse, it ain't no sickness, just personality. Take it and make it your best quality.

    • @ScherrerMadness
      @ScherrerMadness Рік тому

      @@nicholastroyandersen9505it’s…. Not a personality, lmfao. It’s a very clear set of learning disabilities centered around working memory, executive function, and tuning out

    • @davidabellangarrido2056
      @davidabellangarrido2056 Рік тому

      same and without knowing english

    • @pauls064
      @pauls064 9 місяців тому

      @@nicholastroyandersen9505it’s literally a neurological condition that can be seen on scans and measured… ignorant comment

  • @nickfleming3719
    @nickfleming3719 Рік тому +120

    That isn't a vector database. It's a relational database with vectors stored on a text column. In practice, you will have thousands of embeddings and performance will tank with this setup

    • @trevorbaier7072
      @trevorbaier7072 Рік тому +5

      What's a more ideal solution for storing vectors?

    • @brookster7772
      @brookster7772 Рік тому +9

      From my investigation, Redis is an excellent vector store to be used in both development and production especially when it’s a local Dockerized instance

    • @SussyBacca
      @SussyBacca Рік тому +7

      Mongodb atlas is awesome for vectors. They have a new vector feature called knnbeta

    • @ParthSaneHD
      @ParthSaneHD 11 місяців тому +4

      Pinecone works too!

    • @amdenis
      @amdenis 11 місяців тому +1

      You are correct, but you know that! It’s indexing is not fast enough for many serious AI projects, and its single threaded architecture does not scale. Under the hood there are many other non-vector legacy issues.

  • @aiadvantage
    @aiadvantage Рік тому +21

    Super high quality video right here. Good job Adrian

    • @AdrianTwarog
      @AdrianTwarog  Рік тому +3

      Hey I've seen your stuff too, it's great, thanks for the nice words!

  • @nickkondoori7550
    @nickkondoori7550 Рік тому +18

    Incredible teaching skills. First time ever, I loved someone who can teach "ME" the way I always wanted. Thousand thumbs up Adrian!!

  • @MohamadBahri-h3k
    @MohamadBahri-h3k Рік тому +22

    I have seen multiple tutorials, this is by far the best and most concise, great work man

  • @LeoCB
    @LeoCB Рік тому +2

    I just bought 2 Udemy courses, and after 5 hours, none of them talk so well about this. I appreciate it, and I will buy your book. Thanks for your content.

  • @adamduvick
    @adamduvick Рік тому +9

    Let me see if I understand what’s going on here:
    1) you have data you want to search semantically
    2) you create a vector database capable of storing & querying data semantic search queries
    3) you use OpenAI to process your data & convert it to vectors which can stored in your database
    4) you store the data along with the OpenAI generated vectors
    5) now you can search the data
    Is that all it is? I thought you were then going leverage this database to give chatgpt “long term memory” ( 0:20 ). What you’ve showed seems nice, but I don’t really see the point since most people/companies who have enough data that would need to be queried in this way would not be able to give it away to OpenAI to process.

    • @goldenant9450
      @goldenant9450 Місяць тому

      what'd you mean "give it away to OpenAI" is everything shared with OpenAI accessible by the internal team or something? I'm pretty sure you can opt out of using your data to train their AI..at least that's the case with that chatbots.

  • @rasmuspiirtola4397
    @rasmuspiirtola4397 Рік тому +1

    Rarely comment, but damn, you did a perfect job - I am at 8:01, haven't watched the video but had to pause and comment - until 8:01, everything was perfect; how you explain concepts and utilize tools ensures that we understand the concept in practice with ease! Great job, continue making videos; you should do consulting if you don't already do so. It's easy money with little hours with your skills and knowledge!

  • @tech.bharat18
    @tech.bharat18 3 місяці тому +1

    This is by far the most easiest & concise explanation. Thanks for creating this video

  • @CodexCommunity
    @CodexCommunity Рік тому

    This is the best video on openai embeddings I have ever seen, I am also a bit biased!

  • @codinginflow
    @codinginflow Рік тому +1

    This was a great overview Adrian!

  • @abijithpradeep7478
    @abijithpradeep7478 Рік тому +3

    For those who already had an OpenAi account and you are facing an error while posting the HTTP request, its because your free credit has expired. You will have to add a payment method or createa new account to get free credits agin and then everything will work fine according to this tutorial.

  • @krisograbek
    @krisograbek Рік тому +8

    Adrian, your channel is a gem! I love the way you explain complex topics and the pace of your videos! Greetings from Poland!

  • @brookster7772
    @brookster7772 Рік тому +1

    Bare metal, removing all higher level obstructions going right down to the core. I love it the best understanding of what embedding’s earlier that I have seen great job.

  • @LindsayHiebert
    @LindsayHiebert Рік тому +15

    Excellent overview! Very concise, clear and relevant! Great job! Thank you Adrian! 😊

  • @AbhinavKumar-jt8kx
    @AbhinavKumar-jt8kx 4 місяці тому

    This is awesome, perfect video for non-beginner developers to quickly grasp.

  • @karthikg752
    @karthikg752 Рік тому

    The voice recording and explanation is really clear - surprising how tone and voice plays a major role in understanding. Was watching another video which was equally good but somehow the slang and recording made it a bit difficult to understand. Thanks

  • @Glow0110
    @Glow0110 Рік тому +6

    Would be great to see a follow up video of practical applications using this.

    • @atursams5501
      @atursams5501 Рік тому

      The practical application are varied:
      sentiment analysis
      term search
      Classification

  • @andrey20111988
    @andrey20111988 5 місяців тому +1

    Also you can use in postman "Test", which can help you create a script to create a string with requested input and response data. Automate it! (If you need)

  • @phil97n
    @phil97n Рік тому +3

    Awesome thanks.
    Been studying calculus and linear algebra before I dive deep into AI. I will definitely be dealing with vector databases very soon and looking forward to it.

  • @RajShekarsdreamzzz
    @RajShekarsdreamzzz Рік тому +1

    Very Good session Adrain... your way of teaching is keeping the people glued... Keep it up

  • @MaverickCoder-mz6hp
    @MaverickCoder-mz6hp 4 місяці тому

    Nice high quality video with clear explanation of concepts. This video is engaging for learners. I would say one of the best videos out there on vector embeddings. Good Job Adrian

  • @anrk97
    @anrk97 Рік тому +3

    Love your thumbnails. Keeps getting better with each video 👍

    • @AdrianTwarog
      @AdrianTwarog  Рік тому +2

      Thanks, I try to make them as clear to what they video represents as possible!

  • @curtisblake261
    @curtisblake261 11 місяців тому +1

    I like this video and I don't mind all the upselling. My only complaint is that if I pause the video for too long, it automatically sends me to another video in the series, which makes it hard to get back to where I was. You might assume it is user error, but it isn't. The automatic transferal and loss of context happens constantly with this UA-cam video, and I've never had the problem with any other UA-cam tutorial. I'm fine with the monetizing and upselling since it helps reward the content creator, I just wish it wouldn't keep making me lose my place in the tutorial.

  • @coinexponent1884
    @coinexponent1884 Рік тому +6

    Learn vector embeddings using first principles. Always engaging, and very rewarding for the learner. Thank you!

  • @pajisounds
    @pajisounds Рік тому +6

    Nice video, it would have been nice with a demonstration at the end or intro, keep up the good work.

    • @AdrianTwarog
      @AdrianTwarog  Рік тому

      Oh good suggestion, I’ll do that next time!!

  • @satish1012
    @satish1012 3 місяці тому

    Great
    So bascially if i have create LLM for my company who has multiple documents , content i need to do it
    1. Pass all the documents and get Embeddings from OPEN AI
    2. Store all the Embeddings in a DB
    3. Create an app to to search vector DB
    But my question is how it can think and reason. The above approach has great for search capability but how it think like Summaration , comprehension etc

  • @Danimsalinas
    @Danimsalinas 2 місяці тому +1

    Omg, thanks for this video, very straight forward and easy to understand. Thanks!

  • @dipayanroy964
    @dipayanroy964 7 місяців тому

    I wish everyone could have presented like you, simply Super. Looking forward for more in similar way

  • @araujoao
    @araujoao Місяць тому

    Thanks for Sharing. This was a great video that clearly illustrate vectorsdb, embeddings, and searching.

  • @daygo619ca
    @daygo619ca Рік тому +1

    This tutorial was incredible - completely glued to it

  • @oscargalvez7
    @oscargalvez7 Рік тому +3

    Amazing tutorial! The way you explain is so easy and understandable!

  • @edoson01
    @edoson01 Рік тому +1

    Blows my mind you've spent 18m talking about the How and 30sec about the why and what.

  • @JeremyArtero
    @JeremyArtero Рік тому

    This course is gold! Thanks! I have done similar steps on Astra db and it was smooth

  • @AmanBansil
    @AmanBansil 9 місяців тому

    Absolutely LOVE this. you're so clear and concise.

  • @saik6730
    @saik6730 Рік тому

    Best AI video ever . Made it easy to understand with 2 simple concepts . Thanks man!

  • @ravindrasingh2411
    @ravindrasingh2411 9 місяців тому

    Adrian, this is beautifully explained. Absolutely loved it :)

  • @FahadKiani1
    @FahadKiani1 Рік тому +4

    Will you create a second part of this video where PDF's are uploaded and then analyzed?

  • @chrismalingshu
    @chrismalingshu Рік тому +3

    [Question] When input hello earth, "Hello World" scored 0.89, meanwhile "OpenAI Vectors and Embeedings are Easy!" scored 0.74. Which is quite close to the top rank text. But syntactically first and second returned text are very different. Somehow I expect the second text might scored 0.5 and below.
    Could you please share your thoughts on this Adrian?
    Thank you!

    • @daffertube
      @daffertube Рік тому

      You would need to ask someone who built the transformers at openai.

  • @munishtyro
    @munishtyro 5 місяців тому

    Simple, concise, and has everything in it. Thank You

  • @rkjellbe
    @rkjellbe Рік тому

    Finally, found a video with the appropriate detail. For me! 😊 Thank you!

  • @kfliden
    @kfliden 7 місяців тому

    Wow, thanks I'm finally starting to get embeddings!

  • @MDMUNIFHASAN-sr2jk
    @MDMUNIFHASAN-sr2jk 24 дні тому

    nice tutorial, i have a question for code completion which extension you use?

  • @robertcormia7970
    @robertcormia7970 11 місяців тому

    Well done, succinct, and excellent explainations of complex topics.

  • @chrislannon
    @chrislannon 9 місяців тому

    Nice work! Thanks so much for this awesome demo.

  • @mohamadchahin3040
    @mohamadchahin3040 Рік тому +6

    Bro do your research first before saying only open ai has a great way to do embeddings theres a million libraries that exactly do that from sbert to fast text to glove etc... embeddings are an old concept

  • @sany2k8
    @sany2k8 Рік тому

    Great content 👍👍👍, waiting for more OpenAI, AI related content

  • @ZaidKhanPathan
    @ZaidKhanPathan Рік тому

    Wow! Easy, clear and to the point.

  • @ismailm123
    @ismailm123 2 місяці тому

    Brilliant super simple and very easy to understand.

  • @cmdrls212
    @cmdrls212 6 місяців тому

    This is great. I had to learn this in a crunch and I grok it now.

  • @Art-kz6zf
    @Art-kz6zf Рік тому +1

    How efficient is the vector search if you need to go through all of the records every time you search? Shouldn't there be some dedicated field type for embeddings other than blob?

  • @gman2036
    @gman2036 9 місяців тому

    Loved this tutorial Adrian, very straight forward and it worked the first time not like some others I've tried. Now for my question. I'm seeing this on February 2024. I did not know CHATGPT, BARD and those other AI apps until they hit the common pool that I must swim in. I take it that vectoring documents has been going on for awhile, outside of the math world. I knew of vectoring back from college in linear algebra. If this is the case, what I'm trying to do will not be new. I'm trying to vectorize my documents in order to practice doing this kind of work. So, are there IT companies out there doing this type of work already and can you name a few? How far have they gotten? Has someone already done the library of Congress for instance?

  • @adavis912
    @adavis912 10 місяців тому

    Great tutorial!!! I will be buying your book.

  • @satanrasool1802
    @satanrasool1802 Рік тому

    Love it.. it was far simpler than I thought..

  • @atursams5501
    @atursams5501 Рік тому

    Great work! How do you make these nice presentations with the fancy arrows?

  • @matickovac
    @matickovac 7 місяців тому

    Great work presenting this!
    Do you happen to know how similar or different this is from what Elasticsearch does when performing full-text search?

  • @MikevanDam-j9g
    @MikevanDam-j9g 5 місяців тому

    This tutorial is well explained. Thanks for that. But could you explain how to do this on scale? Is it possible to have a no code tool that companies can use to store their data in a vector database? Also, retrieving this info later?
    It seems that there must be easier solutions for this right? (while also keeping it safe to use).

  • @defaultdefault812
    @defaultdefault812 Рік тому +4

    Well done, Langchain already exists...

  • @meirgoldenberg5638
    @meirgoldenberg5638 Рік тому +2

    How in the world did it get 0.74 score (which pretty high on the scale for 0 to 1!) for the similarity of "Hello Earth" and "OpenAI vectors and embeddings are easy"? Is there anything in common between the two?

  • @pablochacon7641
    @pablochacon7641 Рік тому

    Very interesting video, but what are the prerequisites to understand & actually implement this ?

  • @e-Course.
    @e-Course. Місяць тому

    Very interesting video , thank you

  • @mohammadbarzegari8737
    @mohammadbarzegari8737 Рік тому

    Perfect learning ❤🎉 master of learning ❤❤❤❤

  • @GenZManhood
    @GenZManhood Рік тому +2

    I get this message when I run the API. Do you need to pay OpenAI for it to work? Thanks! "error": {"message": "You exceeded your current quota, please check your plan and billing details.",

  • @PeterAdiSaputro
    @PeterAdiSaputro Рік тому

    In the past, I learned Support Vector Machines for doing classification. At that time, I struggled to learn the concept, although I finally was able to implement it into a program using codes made by another party. The introduction of this video suddenly revived the memory and helped me better understand the concept of SVMs that I learned years ago.
    Is Postman completely free and can be used without any restrictions or limitations ? Is Single Store also completely free without any restrictions or limitations ?

  • @demetriusmds
    @demetriusmds Рік тому

    Excellent. Thank you. Helped a lot.

  • @grantomohundro3298
    @grantomohundro3298 Місяць тому

    Great tutorial man! thank you!

  • @karsonkalt7607
    @karsonkalt7607 Рік тому

    Fantastic tutorial and explanation!!

  • @MannyBernabe
    @MannyBernabe 9 місяців тому +1

    excellent. thx!

  • @nadershalabi6241
    @nadershalabi6241 6 місяців тому

    Thank you! Great walk through

  • @m67esteban
    @m67esteban Місяць тому

    thank you very much! super useful!

  • @sunnysk43
    @sunnysk43 Рік тому

    Absolutely amazing! Thank you so much for your work!

  • @joostschuur
    @joostschuur Рік тому

    How would I go about weighing the results by other meta data? Say I have a bunch of videos, and I'm searching the title/description, but want to give some amount of preference to newer videos too.

  • @nrusimha11
    @nrusimha11 Рік тому

    Crisp and to the point, thank you. Can I ask how you made the slides like the one at 0:52?

  • @alexsalgado
    @alexsalgado Рік тому

    Excellent content, what changes for audio search?

  • @fkxfkx
    @fkxfkx Рік тому +1

    Bought the book. It ended on page 54, is there anything after 54 to 58?
    Last example was open ai fine tuning.
    It leaves the ft up on open ai site.
    How long will it be available there?
    Can it be brought down locally and be used in the future as local in combination with cloud model?

    • @AdrianTwarog
      @AdrianTwarog  Рік тому

      I’ll double check, and any updates will automatically be enabled on Gumroad!

    • @Ricocase
      @Ricocase Рік тому

      ​@@AdrianTwaroghow to automate text importation with sql? Must one enter each text blob manually?

  • @corejava5730
    @corejava5730 Рік тому

    Very well explained, Thanks Adrian !! I have astaffing firm and I have a database of more than a million resumes. I m planning to create a resume search application for my recruiters. Do you think I should be using combination of Embeddings and Vector Database for above use case.

  • @Ricocase
    @Ricocase Рік тому

    Cool course. How does one connect it to a basic website?

  • @pranavkm4513
    @pranavkm4513 Рік тому +1

    wow great video sir. Helped a lot. may i know what extension is being used in 16:40 ?

  • @Aayush-k3d
    @Aayush-k3d 4 місяці тому

    Very well explained

  • @RiazSyed-n1x
    @RiazSyed-n1x 11 місяців тому

    great explanation ! thanks !!

  • @amdenis
    @amdenis 11 місяців тому

    Redis is viable for certain scale-limited AI applications, but DL indexing can take 10’s to 100’s of times longer than a true multi-threaded vectorized db, because its architecture is limited to only a single thread execution, making it impossible to scale.
    However, I would hope that most serious AI developers know enough or would do a lot more research than following the advice of some random YT video.
    Sadly, AI education is still fairly limited as institutions are still trying to catch up- and even then, there is a lot for new grads to learn before they start to reach a real, productive stride.

  • @Kennethlumor
    @Kennethlumor Рік тому +1

    Actually I'm in level 200 in university of Ghana 🇬🇭 studying computer science and website technology. We where ask to create such a navigation bar. But upon searching I realized you are the only one that create such an amazing navigation bar from scratch. So please help me

  • @ewhite_dipi
    @ewhite_dipi Рік тому

    what are the prerequisites to understand the content in this video? And where can I learn them?

  • @fintech1378
    @fintech1378 Рік тому +1

    technically, a vector is the 1d matrix that contains the embedding, which may be in the form of a set of scalars

  • @aillusions
    @aillusions 2 місяці тому

    interesting that expected vector array was places into SELECT section rather than WHERE section

  • @SimonCicero-g8n
    @SimonCicero-g8n Рік тому

    Perfect explaination!

  • @omangramoswaane2211
    @omangramoswaane2211 Рік тому

    Nice video. I love your work.

  • @noubgaemer1044
    @noubgaemer1044 10 місяців тому

    thanks for the tutorial can we use our own LLM like private GPT or Text-generation Web UI instead of OPENAI

  • @SahilPatoliya-x7l
    @SahilPatoliya-x7l Рік тому

    thanks for this video video is really helpfull

  • @coding-master-shayan
    @coding-master-shayan Рік тому +2

    How can I train my own ai using tensorflow to generate I images and text

  • @BryanChance
    @BryanChance 11 місяців тому

    Does the chuck size have an affect on the quality or accuracy of the search result? Let's say I split a document into words AND in 200 word chucks. The vector results are stored in a vector db.

  • @Joshua.Medellin
    @Joshua.Medellin Рік тому

    I'm a little confused.. If I created embeddings and which I'm assuming is essentially training the openai model on a specific topic for my company. Would it be able to answer questions only on the specific topic it was trained for?

  • @Dydent10
    @Dydent10 4 місяці тому

    Brilliant stuff!

  • @MRGCProductions20996
    @MRGCProductions20996 9 місяців тому

    isnt calculating the modulus of the subtraction of the vectors a more accurate way to find similarities?

  • @KlrStng
    @KlrStng Рік тому

    Does your book explain what kind of database that Single Store is using, and what their proprietary function "json_array_pack" is actually doing? I would like to try this out but don't want to use a service like Single Store as I prefer to just use an AWS RDS database instead (or anything that I can have full control over, or even host myself), but that function is not a real SQL function and I don't understand exactly what is going on in the background here. It looks like the Single Store function is doing some kind of encrypting of the json array data, but it's unclear in their documentation. On a different note, is converting text to vector data more efficient and more accurate for searching than something like a simple SQL "like" query, or fulltext searching? How about compared to something like SphinxSearch or AWS Elastisearch?

  • @rafaelmartinsdecastro7641
    @rafaelmartinsdecastro7641 Рік тому

    This is great stuff, thanks.

  • @mokiloke
    @mokiloke Рік тому +1

    Mine seemed to only come up with a paid postman version. Maybe its based on location?

  • @KJB-Man
    @KJB-Man Рік тому +1

    OK, it is a good video on using OpenAI to create embedding via an API. But lets say, next week. Open AI's building are destroyed by a meteor! Now, I still want to create embeddings on my dev server. Is there a software I can download and run locally that I can use until a meteor crashed on my house?

  • @psyduck4763
    @psyduck4763 Рік тому

    Hey man, what are those fonts you've used in this video?