What is LangChain?

Поділитися
Вставка
  • Опубліковано 14 лис 2024

КОМЕНТАРІ • 112

  • @alexiscao8749
    @alexiscao8749 8 місяців тому +160

    After watching a ton of courses on coursera developed by prestigious universities, and tech companies like google, meta, etc., I found IBM' courses are the best: comprehensive, clear and concise! Thank you

    • @coderider3022
      @coderider3022 4 місяці тому +3

      Hipsters in their bedrooms telling you a few examples are enterprise production ready.

    • @ranjeet_sohanpal
      @ranjeet_sohanpal 4 місяці тому +1

      Completed their data science specialization. It was great and covered the entire workflow of a Data Scientist.

  • @tubero911
    @tubero911 8 місяців тому +59

    Just want to thank the wonderful presenters for this excellent series and IBM for its commitment, innovation, and broad contribution to education in this field.

    • @softvision3000
      @softvision3000 8 місяців тому +1

      What innovation you're talking? The community innovation?

  • @ghaith2580
    @ghaith2580 2 місяці тому +5

    I can't put into words how much I loved this video , as a complete novice into langchain I now know more than I expected to , everything is now clear in my mind , thank you from the bottom of my heart

  • @HitteshAhuja
    @HitteshAhuja 4 місяці тому +8

    Probably the only channel that doesnt 'plugin' their app or service ( read Google) to explain a topic !

  • @supankanlavanathan463
    @supankanlavanathan463 7 місяців тому +12

    - [00:00] 🛠 LangChain Overview
    - LangChain is an open-source framework for developing applications utilizing large language models (LLMs).
    - Components of LangChain include abstractions, LLM modules, prompts, and chains, streamlining the programming of LLM applications.
    - [01:26] 🔄 Abstractions in LangChain
    - Abstractions in LangChain simplify complex NLP tasks by representing common steps and concepts necessary to work with language models.
    - These abstractions can be chained together to create applications, minimizing the amount of code required.
    - [02:22] 🔗 Components of LangChain
    - LangChain comprises LLM modules, prompts, and chains, enabling developers to integrate different models and execute sequential functions to achieve desired tasks.
    - Components like prompts formalize the composition of instructions given to LLMs, facilitating the development process.
    - [03:47] 📊 Data Handling in LangChain
    - LangChain supports various data handling mechanisms, including document loaders and text splitters, enabling access to external data sources and efficient text processing.
    - Vector databases and memory utilities enhance data retrieval and management within LangChain applications.
    - [06:09] 🤖 LangChain Use Cases
    - LangChain facilitates diverse applications such as chatbots, summarization, question answering, data augmentation, and virtual agents.
    - Integration with existing workflows and robotic process automation (RPA) enhances the functionality of LangChain.

  • @tyronefrielinghaus3467
    @tyronefrielinghaus3467 8 місяців тому +3

    martin KEEN(nominative determinism at work?) is my all-time fav IBM presenter! THis one no exception Great, clear expo of LangChain..

    • @charltonh2012
      @charltonh2012 7 місяців тому +1

      As soon as I saw him start writing backwards, I lost all concentration on the presentation and was wondering "how did he do that", and was figuring it out instead of listening to the content.

  • @vectorautomationsystems
    @vectorautomationsystems 8 місяців тому +11

    Pure gold! Thanks a lot for this. Best regards from Nairobi, Kenya

    • @Cyberkspace
      @Cyberkspace 8 місяців тому

      hey i want you to contact me

  • @nditahsamweld346
    @nditahsamweld346 6 місяців тому +7

    Best description of LangChain I have watched

  • @seatube327
    @seatube327 8 місяців тому +8

    Great video! I just published a chat bot for home brewers, but it’s a bit basic so a friend of mine recommended using langchain to have it provide better responses and take meaningful actions. This was really helpful for me to get started, thank you!

    • @emc3000
      @emc3000 8 місяців тому

      Ooooh share a link if you can!

    • @thatwasavailable
      @thatwasavailable 6 місяців тому

      Yeah could you share

  • @unirico279
    @unirico279 2 місяці тому +1

    Great work! The best video to understand LangChane in only a few minutes.Thank you!

  • @muhammadhilal5807
    @muhammadhilal5807 2 місяці тому

    This video made it easier for me to understand the LangChain, and also the elements I will be learning during RAG.

  • @softvision3000
    @softvision3000 8 місяців тому +3

    LangChain exists a long time and its community is huge. Nice to finally get an intro from IBM about that long existing technology and community product.

  • @umutcandogan3242
    @umutcandogan3242 3 місяці тому +1

    thanks steve kerr for the lesson!

  • @mpicuser
    @mpicuser 2 місяці тому

    This video helped me understand better about Langchain.

  • @JoseWaihiga
    @JoseWaihiga 2 місяці тому

    Thank you for a very instructional video. I loved the format :)

  • @ScenicLensNH
    @ScenicLensNH 8 місяців тому

    Great topic and great presentation of it -- a good breakdown of what it is and the use-cases it tries to fulfill. I like how you filled in some of the text instead of writing it out -- saves a lot of time. Thanks.

  • @toenytv7946
    @toenytv7946 8 місяців тому

    Way to break down the chain. Well done.

  • @shockawe3773
    @shockawe3773 8 місяців тому

    A complex topic explained clearly.

  • @mjacfardk
    @mjacfardk 8 місяців тому +1

    Thank you, Great tutorial, and easy to understand manner. We would like to ask you to explain about Lang chain concepts like indexes and chains.
    thank u again.

  • @i2c_jason
    @i2c_jason 3 місяці тому

    What a great summary, thank you.

  • @antoniopavoni4639
    @antoniopavoni4639 6 місяців тому

    Thank you very much for this introduction! I found it really useful and helps me navigate all the information and new programs around AI. Would you be able to provide few examples on what can we built on langchain ?

  • @prasadjayanti
    @prasadjayanti 2 місяці тому

    Good summarization !

  • @Nick_With_A_Stick
    @Nick_With_A_Stick 8 місяців тому +1

    Ibm explaining langchain. I guess langchain is getting production ready. During the start langchain was a bit rough.

  • @carlosenriquecastanedaguti8130
    @carlosenriquecastanedaguti8130 2 місяці тому

    Excellent explanation, thanks very much. It was very useful

  • @liampgordon
    @liampgordon 4 місяці тому

    Thank you for these videos. They are super helpful.

  • @sailize
    @sailize 8 місяців тому

    great work for this complicated frame work!

  • @Ramkumar-uj9fo
    @Ramkumar-uj9fo 2 місяці тому

    You're pointing out that while humans, even those in scientific fields, might not prefer to use complex models like graph theory for direct communication, they prioritize these methods when designing machine communication systems. This reflects the focus on efficiency and precision in machine interactions, which differs from how humans naturally communicate.
    ChatGPT ❤🎉

  • @akankshasinha946
    @akankshasinha946 Місяць тому

    Great explanations

  • @CaptainPanick
    @CaptainPanick 8 місяців тому +7

    Am I the only one who wonders how this presentation actually works? Is he writing on a mirror? If he wrote on glass while standing behind it, it would be in reverse for us... How does some of the words autocomplete? How does it glow? Is it magic?

    • @Nick_With_A_Stick
      @Nick_With_A_Stick 8 місяців тому +1

      It’s actually a thing they invented to do this, I wondered the same thing and the actual ibm channel responded with a link to how they do it. Pretty sure it’s the video flipped horizontally. While he writes on a glass ( I cant remember anymore it was a long time ago the ibm channel responded)

    • @DmitryVatolin
      @DmitryVatolin 8 місяців тому

      I think he writes on a glass, and the camera is behind the glass. When the video is shot, it's mirrored so that left becomes right, and the right becomes left. Glowing is not a problem, there are fluorescent paints.

    • @AbhijithMulavana
      @AbhijithMulavana 8 місяців тому +1

      The setup's left side view will be like:
      Person |Glass| Camera
      Glass will be big enough to cover the frame as in the video. Face is illuminated by lights fixed on the glass's frame. This will avoid reflections which would have been seen on the glass if illuminated from the front side.
      He writes on the glass with chalk pen. Video will be recorded on to the camera. This footage will have the letters written on the glass aa inverted horizontally. Then this footage is flipped horizontally by editing software.

    • @renato5668
      @renato5668 8 місяців тому

      I was wondering that. If I had to do something like that, I would place him behind a glass wall, turned to the camera which on the other side of the glass. Then mirror the recorded video. But maybe they do it differently

    • @bydcn
      @bydcn 7 місяців тому

      I think he did write in a reverse way!

  • @KevinKunst
    @KevinKunst 6 місяців тому

    This was super useful and easy to understand, thank you so much for posting!

  • @genAI-business-forge
    @genAI-business-forge 3 дні тому

    Very helpful

  • @user-jy4lk4uj5r
    @user-jy4lk4uj5r 8 місяців тому

    As always informative and entertaining at the same time. Would be great if you could show us some demo applications as well as some high level sample integration code or component. Thanks.

  • @henryebube3576
    @henryebube3576 7 місяців тому

    Best explanation. Please can IBM provide end to end AI courses that can make us market ready for AI job or creating AI start up. So many noises out there

  • @tiagopalabarauna5719
    @tiagopalabarauna5719 4 місяці тому

    Nice content, really appreciate it.

  • @ridhampatoliya4680
    @ridhampatoliya4680 16 днів тому

    great video

  • @santoshjayanth2342
    @santoshjayanth2342 8 місяців тому +1

    Can we expand the capacity of input prompt using langchain if yes can you suggest any methods??

  • @RamonLopesFaustino
    @RamonLopesFaustino 6 місяців тому

    Thanks for sharing your knowladge with us. Thanks from Brazil.

  • @gristlelollygag
    @gristlelollygag 3 місяці тому

    Great video!

  • @utkbella
    @utkbella 6 місяців тому

    Best explanation.

  • @mzimmerman1988
    @mzimmerman1988 7 місяців тому

    very helpful, thanks!

  • @khalidelgazzar
    @khalidelgazzar 8 місяців тому

    Great explaination. Thank you

  • @AndresF
    @AndresF 5 місяців тому

    Really Nice IBM, thank you!

  • @kannansingaravelu
    @kannansingaravelu 7 місяців тому

    How does langchain stack against llama index? Which is most preferred?

  • @shivamsharmaji
    @shivamsharmaji 6 місяців тому

    What a great explainer video.

  • @adrivelascodev8153
    @adrivelascodev8153 4 місяці тому

    this is really cool and useful

  • @Shankarpalya12345
    @Shankarpalya12345 3 місяці тому

    00:01 LangChain is an orchestration framework for large language model applications.
    00:58 LangChain is a fast-growing open-source project with utility in streamlining LLM applications.
    02:05 LangChain standardizes llm interface
    03:05 LangChain enables sequential chains of functions in applications.
    04:06 LangChain's document loaders work with third-party applications for importing data sources.
    05:11 LangChain solves the issue of retaining conversation memory
    06:14 LangChain offers chatbot integration and text summarization capabilities.
    07:15 LangChain enables autonomous actions with language models and RPA.

  • @MrLargonaut
    @MrLargonaut 6 місяців тому

    Just to clarify, LangChain ~= JSON but for LLMs?

  • @KumR
    @KumR 8 місяців тому +1

    In the same program can we query one LLM (Like Llama2) , get response & use that response in a chain and pass that to another LLM (like google gemini)... All the in same program?

    • @KumR
      @KumR 4 місяці тому

      any answer?

  • @Oppen_AI
    @Oppen_AI 6 місяців тому

    Most people use langchain to extend memory on LLMs, do you have an alternative for that?

  • @reda6154
    @reda6154 8 місяців тому

    Very well explained ! Thx

  • @m.arslankhan7449
    @m.arslankhan7449 6 місяців тому

    wao great presentation

  • @leandroszkutnik9467
    @leandroszkutnik9467 7 місяців тому

    Can you use this tools to create a chatbot for internal databases and taking care of the data privacy? For example, I have my documents with private information and I want to use Langchain to ask question about it... Can I create it with langchain without exposing my data?

  • @lLvupKitchen
    @lLvupKitchen 6 місяців тому +1

    Um.. why is brulosophy guy on IBM's channel explaining langchain??

  • @spiral.technology9864
    @spiral.technology9864 8 місяців тому

    thank you

  • @050zaher
    @050zaher 4 місяці тому

    thnx

  • @jayachristina
    @jayachristina 5 місяців тому

    brilliant!

  • @RaymondPeckIII
    @RaymondPeckIII 4 місяці тому +5

    The big question I come away with is: Does the presenter really write all the notes backwards?! :-)

    • @RaymondPeckIII
      @RaymondPeckIII 4 місяці тому

      Nah, they flip the video.

    • @anderivative
      @anderivative 4 місяці тому

      how is this not the most distracting awesome thing??

    • @danielleon1301
      @danielleon1301 Місяць тому

      So in reality we are seeing the presenter mirror picture?

    • @baluandhavarapu
      @baluandhavarapu Місяць тому

      Nope, they'd flip the camera recording

  • @SusanJacobs-n2s
    @SusanJacobs-n2s 8 місяців тому

    cool video)

  • @xyashhxx
    @xyashhxx Місяць тому

    is he is writing in inverted form ?

    • @livinagoodlife
      @livinagoodlife Місяць тому

      Likely writes normal for himself then video is inverted horizontally

  • @redthunder6183
    @redthunder6183 6 місяців тому +1

    honestly, I dont really like lang chain, I'd rather write the code myself to do this because its pretty trivial. seems more like something for non-techinical people who arent in tech

  • @mateusdavo
    @mateusdavo 7 місяців тому

    That's it folks.. It's happening.. I'm scared about what this technology can do

  • @leanguardia
    @leanguardia 6 місяців тому

    Does he write inversely on the board?

    • @helLf1nGerTA
      @helLf1nGerTA 5 місяців тому

      No, the video is mirrored

  • @hartmannr76
    @hartmannr76 6 місяців тому +2

    Hold up... Am I watching a video on LLMs from the same guy that I've learned about home brewing from?!?!?

  • @sprincy02
    @sprincy02 Місяць тому

    Langchain yeahh :D

  • @fluffyunicorn7155
    @fluffyunicorn7155 8 місяців тому +60

    I was a little scared that this would be a blockchain thing.

    • @JuShepp
      @JuShepp 8 місяців тому +6

      Scared ? Lol

    • @bloodline39
      @bloodline39 8 місяців тому +9

      Scared?? Weak soul spotted

    • @TheManOfTheHourEveryHour
      @TheManOfTheHourEveryHour 7 місяців тому +2

      It could be used for that. Get that schmoney.

    • @livinagoodlife
      @livinagoodlife Місяць тому

      blockchain technology is great. Open your eyes.

  • @itzJee1
    @itzJee1 2 місяці тому

    how he is writing ? is he writing on a glass plank in reverse manner (OR) he is using any digital board like system >>>>>? 🤯🤯🤔🤔

  • @akankshasinha946
    @akankshasinha946 Місяць тому

    💗

  • @dixztube
    @dixztube 8 місяців тому +1

    Is he right or left handed

  • @sk3ffingtonai
    @sk3ffingtonai 8 місяців тому

    👏👏

  • @Abhishek-kg3je
    @Abhishek-kg3je 8 місяців тому +2

    So this is what Ole is upto after leaving Man Utd

    • @65juhani
      @65juhani 4 місяці тому

      Better than going back to Molde.

  • @godned74
    @godned74 Місяць тому +1

    1:11 WTF? did he just .......

  • @tomkober
    @tomkober 8 місяців тому

    LanguageModelChaingang ;)

  • @RichardGonzalez-v6y
    @RichardGonzalez-v6y Місяць тому

    Thompson Angela Walker Ronald Lopez Robert

  • @MrPrince750
    @MrPrince750 5 місяців тому

    The presenter resembles the former man utd midfielder nemanja matic.

  • @gossipGirlMegan
    @gossipGirlMegan 7 місяців тому

    why?why?why?Why IBM know everything but lose AI age?

    • @ChinemeremDivine
      @ChinemeremDivine 6 місяців тому

      IBM will soon shock everyone 😅.
      You wait for it 🙂

  • @prostokrasavchik8837
    @prostokrasavchik8837 4 місяці тому

    sometimes you question why nice people stay with ibm?

  • @rajnishkumar7084
    @rajnishkumar7084 8 місяців тому

    4000 laoff today. are you affected.

  • @1238a8
    @1238a8 6 місяців тому

    Everything, what could be done with langchain, better to be done without langchain.
    Langchain is everything bad from huggingface, without anything good, except false promise to make AI go brrrr with few lines of code.
    Okay, it will go brrrrr. But slowly.
    And when you'll need something at least a bit uncommon, you'll find, that everything is obfuscated behind several levels of unnecessary abstractions. And you'll need to rewrite everything.

  • @AndresSolar-y3g
    @AndresSolar-y3g 6 місяців тому

    subscribed

  • @toenytv7946
    @toenytv7946 8 місяців тому +1

    Way to break down the chain. Well done.