Vector Databases simply explained! (Embeddings & Indexes)

Подписаться 133 тыс.

Просмотров 277 тыс.

50% 1

Vector Databases simply explained. Learn what vector databases and vector embeddings are and how they work. Then I'll go over some use cases for it and I briefly show you different options you can use.
Resources:
- Gentle introduction: frankzliu.com/blog/a-gentle-i...
- What is a vector database: www.pinecone.io/learn/vector-...
Get your Free Token for AssemblyAI👇
www.assemblyai.com/?...
00:00 - Intro
00:44 - Why do we need vector databases
01:29 - Vector embeddings and indexes
02:58 - Use cases
03:45 - Different vector databases
Vector Database Options:
- Pinecone
- Weaviate
- Chroma
- Redis
- Qdrant
- Milvus
- Vespa
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬
🖥️ Website: www.assemblyai.com
🐦 Twitter: / assemblyai
🦾 Discord: / discord
▶️ Subscribe: ru-vid.com?...
🔥 We're hiring! Check our open roles: www.assemblyai.com/careers
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#MachineLearning #DeepLearning

Опубликовано:

1 июн 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 129

@ChrisBrogan Месяц назад

I just watched an IBM explanation of vector databases and came away lost. Then I watched yours, and got it right away. Point goes to you. ;)

@lesegotsheole6008 7 дней назад

New to this world of machine learning I have to say job well done on explaining in simple terms. This was insightful and had pleasure watching it. Thanks!

@bobsavage3317 Год назад

Yes, a video describing available VDBs in terms of, e.g. Open/Closed, simplicity of operation, and user interaction patterns (quality/expressiveness of API) would be great!

@ProSaladToss Год назад

Seconded

@assethotorch2395 Год назад

ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-Yo-AzVpWrRg.html You may find it helpful to start with the time frame of the video above!!

@RomeoKienzler 10 месяцев назад

Also important how to extend the vdb with custom distance functions

@jolly2002me Год назад

Yes please, more on this topic, I would appreciate it.

@HeyImAK Год назад

👆

@mohamedbilal5634 9 дней назад

Explanation On point !!! Thanks

@MyWissam 11 дней назад

Yes for a comparison video.

@brunomesquitazamberlan8876 Месяц назад

Very useful. Now I can imagine what is a vector database. Thanks

@leftright1606 10 месяцев назад

Yes, looking forward to a more in-depth video.

@muhammadmursalin8915 Месяц назад

Thanks, describe very simply what the vector database is and its uses.🥀

@nickstaresinic9933 Год назад

The concise, high-level explainer that I needed. Thanks.

@DanielTorres-gd2uf Год назад

Let's see the more in depth comparison! Also would love to know your take on where it will go? Are they able to automatically generate vectors for your multimodal data already? Are there known companies using vector databases currently? Are there lightweight alternatives to the services you offered? (ie. a numpy verision of a vector database?)

@4XLibelle 2 месяца назад

Excellent overview. Many thanks!

@SoharabHossain Месяц назад

Brief and to the point. Great video.

@otto.bjorkland Год назад

It would be great if you explained how to use vector databases to give LLM's long term memory! 🙏

@matt_88 Год назад

Definitely! I'd love to see comparable benchmarks for common LLM and other tasks (i.e. transfer learning, use-cases in the context of fine-tuning, etc)

@caiyu538 Год назад

Thank you Patrick.

@jonmichaelgalindo 3 месяца назад

Straight forward and simple. Thanks! 😊

@vincerocchi9083 Год назад

Love your work Patrick. Definitely would like to see more on vector databases, especially when you would use one over an array or other options and the pros and cons of some of the types you mentioned (I.e. Pinecone, Milvus, etc.)

@bindass1000 4 месяца назад

Super helpful!

@bjugdbjk 10 месяцев назад

Definitely need a comparisio video and small example code for the top 3 Vector DB's used !! By the way ,Fantastic walk through of the concept !!.

@ilikegeorgiabutiveonlybeen6705 23 дня назад

yeah nitty gritty indexing options overview and use cases for said options would be higlhy appreciated

@user-hf3rq7qe9v 5 месяцев назад

Thank you, nice and short overview to get an idea of what a vector db is.

@ThomasLapperre 7 месяцев назад

This was a very clear explanation. Thank you!

@maneeshs3876 11 месяцев назад

Nice summary on Vector databases. A comparison of Graph and Vector databases with specific use cases would also help. Thank you

@karthickmj6312 8 месяцев назад

Thank you so much, Patrick. Would love to watch a video detailing and comparing all VDBs.

@user-gh4id3gg4q 5 месяцев назад

An in-depth comparison would be great!

@alexfowler1683 10 месяцев назад

Great video, thanks! Short and exactly on point -- much appreciated. Yeah, it'd be cool to see more in-depth comparison of the dbs.

@rezaru2000 3 месяца назад

Thanks, this is what I needed to understand the overall idea of vector db.

@08ae6013 Год назад

Thank You... It's a great explanation on Vector database. Please make a in depth videos on Pinecone & Redis vector databases

@kevinli3767 3 месяца назад

This is a really good explanation and visualization

@VastCNC Год назад

Would definitely be interested in more details, especially on self hosted VDBs

@ksnydertube 10 месяцев назад

Thank you for this video - just what I needed! If you haven't done one already, please do an explainer comparing. 🙏

@soubinan Год назад

Great video! thank you! A big YES for a Vector DB dedicated video Btw I am happy I have found this channel, let's subscribe !

@nikilragav 3 месяца назад

This is a great explanation. But the indexing part is what I was looking for. Nearest neighbor search is already a hard problem in Computer Graphics and gaming (to detect collisions. E.g. if you ever play Madden and do a slow-mo replay, you'll see that the receiver never actually touches the ball. or E.g. cloth simulations for a cape often "clip" into the 3d model of the person wearing the cape).

@sanjeevKumar-eg6hp 5 месяцев назад

thanks for a such a detailed and easily understandable knowledge

@fnmby 2 месяца назад

Please continue..)

@ayoubthegreat 11 месяцев назад

I love the video. One critique would be to set up further away from the background to possibly reduce the reverb you're getting

@saimanikanta7360 9 месяцев назад

yup!! looking forward to a detailed analysis and comparison

@nickmhc 9 месяцев назад

A breakdown of differences between vector databases would be nice. But also a comparison to graph databases like neo4j and TitanDB et al would help this n00b

@katsunoi 6 месяцев назад

nice video - thanks!

@p.j.816 5 месяцев назад

This was a really good video! Thanks so much :)

@asifmian43 9 месяцев назад

I would love to see a comparison of the different Vector Databases!

@ser1ification Год назад

Thank you, more please :)

@realjackofall Год назад

Simply explained. Thanks!

@olivierrochon3858 6 месяцев назад

Perfectly clear. Thanks!

@divakaratanjore1059 11 месяцев назад

Awesome explanation! Thank you

@nsitkarana Год назад

to the point and concise explanation !!

@Maisonier Год назад

Yes please a video about that. Liked and subscribed

@TeamUpWithAI 9 месяцев назад

Thanks for putting this together! :)

@camilaferraz8153 Год назад

That was very helpful! Thank you!

@jaylee7864 Год назад

Thanks for the Video. you are awesome and very easy to understand what they are. I think Pinecone is quite popular so if there is a video about it, it would be great. Cheers

@anirudhgangadhar6158 10 месяцев назад

Great intro to VD! Would love to see a more in-depth video on some real-world use cases :)

@mbrochh82 Год назад

comparison video for the mentioned VDBs at the end would indeed be awesome!

@khari_baat 9 месяцев назад

Good informative video. Thanks!

@beemerrox Год назад

Good explanation. Thumbs up 👍

@slawikus1982 8 месяцев назад

Thanks for a nice video! Would be great to learn more on how one could use Redis and PostgreSQL as vector databases. Additionally, more examples and use cases for vector databases would be cool.

@SubirSengupta1 Год назад

I would love to see a comparison of the different VDB's and perhaps your thoughts on which one or two are the best. Thanks for a great video.

@Anonymous-lw1zy Год назад

Yes please, a VDB comparison would be great, and please include FAISS and other self-hosted options.

@davidlepold Год назад

It could be interesting to see a case of adding a vector dbase to an existing sql database, if it can replace it, or if a parallel approach might be interesting, using them side by side, each taking advantage of strenghts. etc.

@ducbuivan9378 Месяц назад

thank you

@VaibhavPatil-rx7pc 11 месяцев назад

Cool, please explain more details about each vector db thanks

@dabravo100 Год назад

Great video… please go on with the next one

@hughesadam87 9 месяцев назад

Great video thank you!

@MartinQLynx 9 месяцев назад

Supabase also joined the vector DB club a while ago.

@hughster657 Год назад

Why isn't KX mentioned in this overview? They have a very strong vector database and support time-series data as well. Formula 1, manufacturing, utilities, and all the banks use them.

@ednavas8093 8 месяцев назад

Incredible video

@jessem2176 10 месяцев назад

I would love to see.. what is the Best Vector database... ease of use vs performance. and why. This way we can stop guessing which one to try to use and just know this one is by Standard the best.

@ryansteiger6960 11 месяцев назад

Thanks for the video 👍

@WmSadler Год назад

woud love to see detailed comparison of the vector databases

@hammanadamafarukabubakar8365 Год назад

Great one

@RanitDA Год назад

Good topic 🎉

@lancerkind 3 месяца назад

I would enjoy seeing a comparison among these different vector databases. Today I just picked the one that’s most convenient. But there’s probably a better rationale for choosing among them. The other topic I’d like to see is sustainability. For example, if I’m adding a new vector to the database once a week what will happen after 10 years? Is that a sustainable growth when I have a 1016 element vector everyweek of the year or do I need to do something to re-index the database so that my performance doesn’t drop after a number of years? The data I’m creating now would be relevant for many decades.

@ilikegeorgiabutiveonlybeen6705 23 дня назад

good video

@pascalmartin1891 10 месяцев назад

I remember working on a vector database in the mid 1980s. That was a Pick system, mostly used for accounting, warehouse management and the like. Re-innovation. 😁

@SonGoku-pc7jl 7 месяцев назад

thanks, you have a video for the comparate diferences quality between?

@SonGoku-pc7jl 7 месяцев назад

you can make a mor explication of diferences and optimitzacions cases :) thanks!

@harshjain3122 Год назад

This is like that scene from the Matrix where Neo stops the bullets and he sees the Matrix(humans, objects alike) as lines of code. We are now converting objects like banana and apples into a bunch of numbers which even we can no longer understand looking at them via the vector embedding.

@PaperTigerLive Год назад

Very helpful animations:) How did you do them with exalidraw, if I may ask?

@user-ng3to6lh7z Год назад

It would be great to see a comparison of the vector database companies

@darrylcatay2295 Год назад

I say what Bob says. Thanks Bob.

@smartfusion8799 Год назад

Yes please, i habe to decide soon which database, redisearch is cloud only, pinecone too i think

@user-zn1kl4hq4j 9 месяцев назад

Could you provide an overview on the comparison of different Vector Database providers and how to decide which is better?

@johnshaff Год назад

Vector DB’s do not get around LLM context size limitations, but it seems like that’s the hot use case for them. Embeddings are not useful until they’ve been transformed though a neural network. I keep looking at these weird use cases like Langchain and I’m baffled people accept their wide margin of failure.

@adityadubey7509 8 месяцев назад

helpful >>

@thantzinoo938 Год назад

i would love to know more

@UDAY-pv5il 7 месяцев назад

Great content.I noticed the Elastic name is missing from the list of vector databases. Could you please include it in the list?

@vamc256 10 месяцев назад

Please explain further, any one of the vector databases with an example for each Weaviate, Pinecone..

@angeloinvestor 10 месяцев назад

You would need to upload ur own embeddings to these db though? Or do they calculate it for you in a multimodal way? Pinecone seems like the former? If so, why not just host locally in your Postgres?

@AndrewPrice2704 Год назад

Yes please!

@liperuf Год назад

yes please!

@pavlotriantafyllides5687 11 месяцев назад

Would love an explanation of indexing and how to use this with an LLM

@DanielNiklaus Год назад

Yes, please.

@decodingdatascience 7 месяцев назад

🎯 Key Takeaways for quick navigation: 00:41 📊 Vector databases store Vector embeddings for fast retrieval and similarity search. 01:07 📝 Unstructured data like images, text, and audio can be challenging to store in relational databases, making vector databases valuable. 02:02 🔍 Vector embeddings allow for finding similar items by calculating distances and performing nearest neighbor searches. 03:10 🗂️ Vector databases have various use cases, including equipping language models with long-term memory, semantic search, similarity search, and recommendation engines. 03:50 💽 Examples of vector database options include Pinecone, Chroma, Redis, Cool, Trans, Milvus, and Vespa AI, each with its strengths and capabilities.