KZhead
Ғылым және технология

LangChain Explained in 13 Minutes | QuickStart Tutorial for Beginners

Rabbitmetrics
2024 ж. 6 Мам.
667 782 Рет қаралды
Жүктеу

In this video, we're going to explore the core concepts of LangChain and understand how the framework can be used to build your own large language model applications.
Code for the video is available here:
github.com/rabbitmetrics/lang...
▬▬▬▬▬▬ V I D E O C H A P T E R S & T I M E S T A M P S ▬▬▬▬▬▬
0:00 Introduction and overview
0:38 Why Langchain?
3:40 The value proposition of Langchain
4:50 Unpacking Langchain
5:42 LLM Wrappers
6:58 Prompts and Prompt Templates
7:45 Chains
9:00 Embeddings and VectorStores
11:40 An example of a Langchain Agent

Пікірлер

  • 90% (or more) of tech tutorials start with code, without providing a conceptual overview, as you have done. This video is phenomenal...

    @imtanuki4106@imtanuki410611 ай бұрын

    • Appreciate it! 🙏 Thanks for watching

      @rabbitmetrics@rabbitmetrics11 ай бұрын

  • I've noticed a significant lack of comprehensive resources that cover LangChain thoroughly. Your work on the subject is highly valued. Thank you

    @adamgkruger@adamgkruger Жыл бұрын

    • Yes, there's not enough books on it. The documentation is sparse

      @artic4873@artic48736 ай бұрын

    • Agreed. This was the perfect introduction, for me at this time, to Lang chain.

      @andrewflewelling4294@andrewflewelling42942 ай бұрын

  • Your video really helps understand the basics of langchain and provides a good context as well. I'm looking forward to more such videos !

    @ranjithpals@ranjithpals7 ай бұрын

  • Thank you for the video. I think it gives a really good introduction to the topic without much distraction. Absolutely pleasant to follow even for a non-native speaker.

    @garratygarret8559@garratygarret85598 ай бұрын

  • This is the best 101 video I found on the subject. Most of the other videos assume you're already somewhat familiar with the tools or aren't that beginner friendly.

    @zerorusher@zerorusher11 ай бұрын

  • With immediate effect I have subscribe to your awesome channel. Explanation to LangChain was clear and concise. I really learnt a lot in just 12 minutes.

    @chukypedro818@chukypedro818 Жыл бұрын

  • Wow, this video on lang-chain have all the pieces i have been searching for. Thank you so much for taking time and making this awesome video.

    @Janeilliams@Janeilliams7 ай бұрын

  • This was an awesome and very straightforward video. I believe that it's the most useful video about LangChain that exists I've seen so far. Even people that don't know much about programming can follow. Thanks so much!

    @maya-akim@maya-akim Жыл бұрын

  • solid instructor. good intro langchain at the right level of depth. For as quick as he rips thru a huge amount of information, he is still pretty easy to follow.

    @nickfergis1425@nickfergis14258 ай бұрын

  • One of the best QuickStart streaming that I've seen. A clearly explanation in combination with images. Many thanks.

    @jayhu6075@jayhu6075 Жыл бұрын

    • Thank you! 🙏

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • I've been watching a lot of AI videos, this is definitely one the best - well-organized and very clear

    @steve_wk@steve_wk11 ай бұрын

  • Thank you so much for covering all the components in just 13 mins. Though, it took an hour to learn and absorb everything :D

    @ernikitamalviya@ernikitamalviya8 ай бұрын

  • I found this to be very comprehensive and indeed useful.

    @dudefromsa@dudefromsa9 ай бұрын

  • I have been searching and searching for an explanation of how to do this exact thing!! Yasssssss thank yooouuu! ❤

    @ejclearwater@ejclearwater3 ай бұрын

  • Having read through the LangChain's conceptual documentation, I must say this video is a great accompaniment. Very clear and well presented and for a non coder like myself, easy to understand. (I'd pay for a LangChain manual for 5 year olds!) . Subscribed.

    @danquixote6072@danquixote6072 Жыл бұрын

    • Thank you! 🙏 Glad it was helpful

      @rabbitmetrics@rabbitmetrics Жыл бұрын

    • Companion*

      @lukaskettner3597@lukaskettner3597 Жыл бұрын

  • Excellent intro, especially for an experienced programmer to start using after a single watch. Learned a lot in a short time with it. Thanks for making.

    @guitarcrax127@guitarcrax1278 ай бұрын

    • You're welcome! Thanks for watching

      @rabbitmetrics@rabbitmetrics7 ай бұрын

  • Thank you. I have watched a lot of videos that attempt to explain LLM's and LangChain as successfully as you have here but fail to do it as succinctly as you have. I was looking for a video that I can share with my clients that explains what LLM's and LangChain are without being too dumbed down or being too 'over their heads' and this video is perfect for that! So, again - thank you.

    @sitedev@sitedev Жыл бұрын

    • Glad it was helpful! I really appreciate the comment, thank you very much 🙏

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • This is a absolutely wonderfuk video on LangChain and its clear and concise. Coukd you do a tutorial for beginners??? 🙏🏼

    @repairstudio4940@repairstudio494010 ай бұрын

  • I never comment on any video but your flawless explanation made me, Thank you for such a masterpiece.

    @HarshGupta-sf4rj@HarshGupta-sf4rjАй бұрын

    • Appreciate the kind words! 🙏 Thanks for watching

      @rabbitmetrics@rabbitmetrics19 күн бұрын

  • Amazing tutorial and explanation, thank you!

    @leventyuksel93@leventyuksel9310 ай бұрын

  • This is gold! Thank you!❤

    @Bragheto@Bragheto Жыл бұрын

  • Thanks for the clarity , all the best

    @hectorprx@hectorprx10 ай бұрын

  • Thank you this is the info I was looking for.

    @RobbieMraz@RobbieMraz29 күн бұрын

  • This is a cool explanation of how langchain works.

    @TheAlokgupta83in@TheAlokgupta83in10 ай бұрын

  • The coolest thing about enhancing LLMs like this is that locally-runnable models will be very interesting (no huge API call costs) and smarter than by default.

    @4.0.4@4.0.4 Жыл бұрын

    • I would love local LLMs! Though I doubt that one advanced as GTP-3.5/4 will be able to be run locally for a few years because of the required computational power. I still look forward to the day that it becomes a thing though!

      @ignfishiv@ignfishiv Жыл бұрын

    • The costs are not the advantage. Hosting things on your own hardware is usually more expensive, especially if you need multiple models(embedding model, LLM, maybe a text to speech). The advantage I see is that you could use custom models trained on your data

      @leonidsdreams3919@leonidsdreams3919 Жыл бұрын

    • Enter neuromorphics: kzhead.info/sun/eLyafbWdoaWDjXA/bejne.html

      @oryxchannel@oryxchannel Жыл бұрын

  • Thank you very much for watching the video, a very well-structured clarification. 👍

    @ratral@ratral Жыл бұрын

    • Much appreciated! Thanks for watching

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • Thank you for explaining all the components. Highly appreciate it.

    @bharatpanchal8582@bharatpanchal85824 ай бұрын

    • You're welcome! Thanks for watching

      @rabbitmetrics@rabbitmetrics4 ай бұрын

  • Very good explanation with a simple example to understand how it works! Thanks for this content

    @miguelangelromerogutierrez9626@miguelangelromerogutierrez96269 ай бұрын

    • You're welcome! Thanks for watching

      @rabbitmetrics@rabbitmetrics8 ай бұрын

  • Great explanation! I learned a ton with your video

    @luiscosta9261@luiscosta92618 ай бұрын

  • Simply fantastic. Thank you very much for explaining it so well.

    @KayYesYouTuber@KayYesYouTuber8 ай бұрын

    • Appreciate the comment! 🙏 Thanks for watching

      @rabbitmetrics@rabbitmetrics7 ай бұрын

  • This is amazing stuff. Would love to see a deeper dive into it.

    @axelrein9901@axelrein9901 Жыл бұрын

    • Thanks for watching! I'm already working on some deep dive videos

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • Thanks for sharing the knowledge 👍

    @raffdev@raffdev8 ай бұрын

  • Fascinating. Thank you for this.

    @pleabargain@pleabargain11 ай бұрын

  • Excellent introduction! Thanks a lot :-)

    @jakobstyrupbrodersen926@jakobstyrupbrodersen92610 ай бұрын

  • Really fantastic crisp explanation of LLM nothing more nothing less.

    @rakeshmr3329@rakeshmr33293 ай бұрын

    • Thank you!

      @rabbitmetrics@rabbitmetrics3 ай бұрын

  • Excellent! I've spent hours looking for this 13 minute tutorial. You fa man! Thanks! 💪😁🌴🤙

    @MrAloha@MrAloha11 ай бұрын

    • Glad you found it! 😊 Thanks for watching

      @rabbitmetrics@rabbitmetrics11 ай бұрын

  • I inspected Langchain code as soon as it was released, ran some tests and never used it since. Im surprised so many consider its limitations acceptable. Using embedding similarity as a query filter is like trying to answer a prompt by comparing every chunk of text to your prompt. It makes absolutely no sense because often times an answer looks nothing like a question, and/or the data needed to answer a question looks nothing like the question. The purpose of the embedding layer in a transformer neural network is to prepare the prompt tensor for further processing through the remaining model layers. It’s like bringing your prompt to the starting line of a long process to be answered, but instead of bringing just the prompt to the starting line, langchain brings the entire text your asking the question of to the starting line with your question and asking them to look at each other and be like “hey, whoever looks like me, stand over here with me. Ok now the rest of you go away and I’m going to ask chatgpt to see which of you remaining can help answer me”. This is a slight of hand trick, trying to replace everything that happens after the starting line, with chatgpt, but it doesn’t really work for 2 big reasons: (1) chatgpt context is not large enough to transform both the entire text your asking a question of + your prompt, and the same limitation applies to batching (2) your embeddings are incomplete because they were not created by the network, but simply hacking the first layer in a sense

    @johnshaff@johnshaff Жыл бұрын

    • Interesting take. I suspect most people don't understand the technology enough to see how it works. Would be helpful if you could make a video explanation

      @MeatCatCheesyBlaster@MeatCatCheesyBlaster Жыл бұрын

    • Biggest limitation right know that we can’t get over with, is chat GPTs context length, there is no way around that unless the contexts is greatly increase by OpenAI themselves or we could train our gpt4 model on large texts

      @albertocambronero1326@albertocambronero1326 Жыл бұрын

    • @@albertocambronero1326 I agree. It would cool if there was a sort of "short term memory model" that could hold personal data. I don't see expanding context length as a parsimonious solution. Model queries produce the best results when they are sort and poignant. Any time you need to bring a ton of context to the prompt it reduces the relative weight of the primary question. Imagine a patient friend who accepts questions with an unrestricted context length. They have never read the book Great Gadsby (i.e. this would be like your personal data) - so to ask them a question about Jay Gatsby the question must begin by reading them the entire Great Gatsby novel, followed by "thee end... Where did Jay Gatsby go to college?" Then to ask them another Gatsby question it requires reading them the novel, again, and again. It would be awesome if there was a way to side-load a small personalized model that can plug into a LLM for extended capabilities.

      @dendrites@dendrites Жыл бұрын

    • ​@@dendrites amazing response, I did not know what was going on under the scenes with the context and did not know model queries produce the best results when they are sort and poignant. I believe that if you send the novel it would be stored in the context of the model and then you would be able multiple questions (?) or would the novel be lossing importance (weight) as more and more contexts is added? Referring to the comment that started this thread, the complicated bit about training the model on a certain topic, lets say: we train the existing GPT4 model in the book Great Gadsby it would probably know how to answer questions about the book, but it could not analize the whole book to find linguistic trends in the book (like what is the most talked about topic in the book) unless you ALSO feed the model with an article about "the most talked topic in the book". I mean I want my GPT4 model to read the book and analize the whole picture of what the book is about without needing extra articles about the book. (my use case is to make GPT4 analyze thousands of reviews and answer questions about it, but right now using NLP techniques sounds like a more duable option right now or at least until we have an option to extend GPT4 knowledge)

      @albertocambronero1326@albertocambronero1326 Жыл бұрын

    • You can't say simply "it doesn't really work". It really depends on the use case. There are true limitations and some creativity might be required to leverage it. The context size might me sufficient for smaller use cases or it might be sufficient to break down bigger questions into smaller questions with their own contexts and then summarize etc.

      @ugaaga198@ugaaga19811 ай бұрын

  • EXCELLENT OVERVIEW: Pls note Pinecone as of 1 week is NOT allowing new, free accounts to do any operations! PLS CONSIDER DOING SIMILAR VID FOSS end to end, There is a lot of interest. THANK YOU

    @bingolio@bingolio Жыл бұрын

  • Thank you very much, Rabbitmetrics! This tutorial is absolutely a gem for someone looking for a clear and concise overview of the main concepts!

    @ALEJANDV1@ALEJANDV18 ай бұрын

    • Thank you! I'm glad it was helpful

      @rabbitmetrics@rabbitmetrics7 ай бұрын

  • Great content! Just what someone who just jumped into Gen AI would need to solve diverse use cases. Subscribed!

    @Swanidhi@Swanidhi9 ай бұрын

    • Appreciate it! Thanks for watching

      @rabbitmetrics@rabbitmetrics8 ай бұрын

  • Excellent video. THank you for sharing. Would love to see a video on Langchain Agents. Thank you

    @ramp2011@ramp2011 Жыл бұрын

    • You're welcome! Thanks for watching

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • Awesome work thanks a lot!

    @noomondai@noomondai Жыл бұрын

  • This video really explains A-Z about langchain. This is damn good man.

    @saddam7008@saddam700810 ай бұрын

    • Appreciate the comment! Thanks for watching

      @rabbitmetrics@rabbitmetrics8 ай бұрын

  • Excellent video for beginners who want to start on Langchain. Well explained.

    @anandakumar31@anandakumar312 ай бұрын

    • Thanks! Glad it was useful

      @rabbitmetrics@rabbitmetrics2 ай бұрын

  • Subscribed. Others have clamored for the notebook. I do as well. Thank you.

    @roberthuff3122@roberthuff3122 Жыл бұрын

  • Your approach on this Langchain vid garnered you a Subscriber! Thanks!

    @spicer41282@spicer41282 Жыл бұрын

    • Appreciate the support! Thanks for watching

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • great overview and slides

    @kevon217@kevon217 Жыл бұрын

  • Excellent work!

    @mhm7129@mhm71298 ай бұрын

  • Great explanation, thanks!

    @TheOGDesigner@TheOGDesigner9 ай бұрын

  • Great video! Thank you.

    @micbab-vg2mu@micbab-vg2mu Жыл бұрын

  • Fantastic overview of Langchain! Thank you @Rabbitmetrics

    @hardikmehta8308@hardikmehta83088 ай бұрын

  • Thank you very much for the video! Really helpfull to kickstart with LangChain

    @CinematicHeartstrings@CinematicHeartstrings2 ай бұрын

    • Glad it was helpful!

      @rabbitmetrics@rabbitmetrics19 күн бұрын

  • This is very insightful and straight to the point.

    @dozieweon@dozieweon6 ай бұрын

    • Thank you!

      @rabbitmetrics@rabbitmetrics4 ай бұрын

  • Wonderful video. Thanks.

    @peralser@peralser Жыл бұрын

  • Great explanatory video! Would you provide a link to this Jypter notebook?

    @ilianos@ilianos Жыл бұрын

  • Thank you for this video. Now I can start work on my Langchain. Have subscribed!

    @limster5@limster511 ай бұрын

    • You're welcome! Thanks for watching

      @rabbitmetrics@rabbitmetrics11 ай бұрын

  • What a beautiful video. You Sir are a great teacher ! Thank You !

    @alaad1009@alaad10094 ай бұрын

    • Thank you!

      @rabbitmetrics@rabbitmetrics4 ай бұрын

  • Amazing short video packed with knowledge. Just smashed that subscribe button!

    @tosinlitics949@tosinlitics9494 ай бұрын

    • Appreciate the support, thanks for watching!

      @rabbitmetrics@rabbitmetrics4 ай бұрын

  • this video was nice and gives a good intro to the topic

    @ayhamkanhoush2912@ayhamkanhoush29125 ай бұрын

  • Great video clear and simple. I wonder is it were possible how can we use this with azure OpenAI

    @felipeblin8616@felipeblin8616 Жыл бұрын

  • Great video! Do you know if pinecone works with other languages? For example to store and then retrieve?

    @lpanebr@lpanebr Жыл бұрын

  • Great explanation!

    @henrisiepmann3501@henrisiepmann350111 ай бұрын

  • Awesome Explanation

    @realJeremyZhang@realJeremyZhang10 ай бұрын

  • Absolutely love the way you explained.

    @muhammadhaseeb2895@muhammadhaseeb28956 ай бұрын

    • Thank you!

      @rabbitmetrics@rabbitmetrics5 ай бұрын

  • Your explanation is super clear to understand for me as a beginner. I want to know brief steps for the code flow as titles just like 1.Creating environment to get keys, 2. etc.,. Can anyone answer it?

    @PhoebePhuu@PhoebePhuuАй бұрын

  • Thank you for your contribution through the KZhead space

    @emptiness116@emptiness116 Жыл бұрын

    • Appreciate it! Thanks for watching

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • This is really great video!

    @alioraqsa@alioraqsa Жыл бұрын

  • Highly appreciated video

    @jordanchristley1306@jordanchristley13069 ай бұрын

  • amazing tutorial. thank you. you are amazing

    @Stoicbob@Stoicbob11 ай бұрын

  • great! I can use this video to teach my friend

    @lee1221ee@lee1221ee Жыл бұрын

  • Bloody brilliant!

    @petrkushnir8178@petrkushnir81786 ай бұрын

  • This is excellent - I have a question re the splitting, lets imagine you have email templates that average like 2000 tokens a piece or IG captions with like 500 tokens - should things like this be embedded as one chunk or what is the advantage to splitting up into say 100 token splits?

    @mwonderlin@mwonderlin Жыл бұрын

  • Excellent overview - Thanks!

    @user-nk7lx2rw4t@user-nk7lx2rw4t5 ай бұрын

    • You're welcome, thanks for watching!

      @rabbitmetrics@rabbitmetrics5 ай бұрын

  • Great video, what is the first app that you were using to explain the diagram ?

    @kailashbalasubramaniyam230@kailashbalasubramaniyam230 Жыл бұрын

  • Brilliant. Structured and clear.

    @xGogita@xGogita2 ай бұрын

    • Thank you!

      @rabbitmetrics@rabbitmetrics19 күн бұрын

  • 👍 Your explanation is so structure and clear. I can understand how langchain works now even though I don’t know your python codes at all.

    @zenfoil@zenfoil2 ай бұрын

    • Thanks! 🙏 Glad it was helpful

      @rabbitmetrics@rabbitmetrics2 ай бұрын

  • Excellent intro. Harrison would approve!

    @shyama5612@shyama56124 ай бұрын

    • Thank you!

      @rabbitmetrics@rabbitmetrics4 ай бұрын

  • Great job, what is the soft that you use to draw these magic things?

    @zh4842@zh4842 Жыл бұрын

  • Great. Would love to have access to the code as well. Thanks!

    @alanwunsche-official@alanwunsche-official Жыл бұрын

  • thank you a lot, really helped

    @spacedust8061@spacedust80619 ай бұрын

  • This was so helpful! What are your thoughts on connecting langchain and flutterflow?

    @stereo_stan@stereo_stan10 ай бұрын

  • Thanks a lot. Very good explanation.

    @venkatkasthala1554@venkatkasthala1554Ай бұрын

    • Thanks!

      @rabbitmetrics@rabbitmetrics19 күн бұрын

  • Hi there, is there a way to combine steps 4 and 5? I assumed you would be using the Agent to answer questions on the autoencoder that we had focused on for the whole video, but then we just used it to do some maths. I think it would be useful if it could answer questions based on the embeddings we have in our index?

    @ciaranryan9485@ciaranryan94856 ай бұрын

  • Really good video!

    @Tom.malucao@Tom.malucao4 ай бұрын

  • Great!!! Fantastic! Awesome! Thank you for sharing!

    @leonardosouzaconradodesant6213@leonardosouzaconradodesant62134 ай бұрын

    • Thanks for watching!

      @rabbitmetrics@rabbitmetrics4 ай бұрын

  • just found your channel. Excellent Content - another sub for you sir!

    @andre-le-bone-aparte@andre-le-bone-aparte Жыл бұрын

    • Thank you I appreciate the support!

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • How is the relevant info (as a vector representation) and question (as a vector representation) combined as a prompt to query the LLM? The example you show is a standard ChatGPT textual prompting scenario. The LLM will spit out what it knows and not what it does not know. So what application will this info be useful for? Also is there any associated paper or benchmark that investigates the performance of extracting "relevant information" using this chunking method or is it implementing some DL based Q/A paper?

    @sujoyroy3157@sujoyroy3157 Жыл бұрын

  • great video !

    @stevehu6511@stevehu651110 ай бұрын

  • that's so amazing !!!

    @AMYclubNFTs@AMYclubNFTs Жыл бұрын

  • good instruction ...

    @skyforever1000@skyforever100013 күн бұрын

  • super helpful. I think langchain engineer could hold significant value in the current job market

    @youngsdiscovery8909@youngsdiscovery8909 Жыл бұрын

    • I agree!

      @rabbitmetrics@rabbitmetrics Жыл бұрын

  • Impressive video, thanks! I will subscribe to your channel!

    @robertof.8174@robertof.81746 ай бұрын

  • I am finding the challenge is the splitting of documents. It needs to be large enough to cater for the search but small for context windows. I tried to use large pieces and another split when trying to extract information. Not sure if it is the "right" way.

    @auslei@auslei8 ай бұрын

  • so well explained! :)

    @namenl2205@namenl2205Ай бұрын

    • Thanks!

      @rabbitmetrics@rabbitmetrics19 күн бұрын

  • very nice thank you

    @chavann@chavann3 ай бұрын

  • Very interesting..can we do this for image search? Query and similarity search for image search and image match? Can we see embeddings of images like text that you presented?. Thanks

    @DrAIScience@DrAIScience3 ай бұрын

  • Great video

    @nonomnismoriar9601@nonomnismoriar960111 ай бұрын

  • Detail explanation. Looking for solution to an application, can you please update your about page with a communication channel address. Thank you

    @srikon554@srikon5546 ай бұрын

  • Good 👍🏻

    @bharathbhimshetty8926@bharathbhimshetty89269 ай бұрын

  • Thank you

    @davidoludepo@davidoludepo6 ай бұрын
KZhead