LangChain Explained in 13 Minutes | QuickStart Tutorial for Beginners

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

[@imtanuki4106]

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

[@rabbitmetrics]

Appreciate it! 🙏 Thanks for watching

[@adamgkruger]

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

[@artic4873]

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

[@andrewflewelling4294]

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

[@zerorusher]

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.

[@maya-akim]

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!

[@chukypedro818]

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.

[@jayhu6075]

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

[@rabbitmetrics]

Thank you! 🙏

[@ranjithpals]

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

[@garratygarret8559]

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.

[@steve_wk]

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

[@Janeilliams]

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.

[@ejclearwater]

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

[@sitedev]

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.

[@rabbitmetrics]

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

[@danquixote6072]

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.

[@rabbitmetrics]

Thank you! 🙏 Glad it was helpful

[@lukaskettner3597]

Companion*

[@nickfergis1425]

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.

[@guitarcrax127]

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.

[@rabbitmetrics]

You're welcome! Thanks for watching

[@ernikitamalviya]

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

[@dudefromsa]

I found this to be very comprehensive and indeed useful.

[@Bragheto]

This is gold! Thank you!❤

[@HarshGupta-sf4rj]

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

[@rabbitmetrics]

Appreciate the kind words! 🙏 Thanks for watching

[@leventyuksel93]

Amazing tutorial and explanation, thank you!

[@hectorprx]

Thanks for the clarity , all the best

[@ratral]

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

[@rabbitmetrics]

Much appreciated! Thanks for watching

[@4.0.4]

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.

[@ignfishiv]

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!

[@leonidsdreams3919]

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

[@oryxchannel]

Enter neuromorphics: kzbin.info/www/bejne/e4nEfoSbn9iAkJo

[@repairstudio4940]

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

[@TheAlokgupta83in]

This is a cool explanation of how langchain works.

[@miguelangelromerogutierrez9626]

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

[@rabbitmetrics]

You're welcome! Thanks for watching

[@MrAloha]

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

[@rabbitmetrics]

Glad you found it! 😊 Thanks for watching

[@bharatpanchal8582]

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

[@rabbitmetrics]

You're welcome! Thanks for watching

[@jakobstyrupbrodersen926]

Excellent introduction! Thanks a lot :-)

[@KayYesYouTuber]

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

[@rabbitmetrics]

Appreciate the comment! 🙏 Thanks for watching

[@axelrein9901]

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

[@rabbitmetrics]

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

[@spicer41282]

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

[@rabbitmetrics]

Appreciate the support! Thanks for watching

[@saddam7008]

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

[@rabbitmetrics]

Appreciate the comment! Thanks for watching

[@pleabargain]

Fascinating. Thank you for this.

[@RobbieMraz]

Thank you this is the info I was looking for.

[@Swanidhi]

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

[@rabbitmetrics]

Appreciate it! Thanks for watching

[@mwonderlin]

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?

[@rakeshmr3329]

Really fantastic crisp explanation of LLM nothing more nothing less.

[@rabbitmetrics]

Thank you!

[@luiscosta9261]

Great explanation! I learned a ton with your video

[@ALEJANDV1]

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

[@rabbitmetrics]

Thank you! I'm glad it was helpful

[@bingolio]

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

[@tosinlitics949]

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

[@rabbitmetrics]

Appreciate the support, thanks for watching!

[@anandakumar31]

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

[@rabbitmetrics]

Thanks! Glad it was useful

[@noomondai]

Awesome work thanks a lot!

[@dozieweon]

This is very insightful and straight to the point.

[@rabbitmetrics]

Thank you!

[@ramp2011]

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

[@rabbitmetrics]

You're welcome! Thanks for watching

[@mhm7129]

Excellent work!

[@alaad1009]

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

[@rabbitmetrics]

Thank you!

[@ciaranryan9485]

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?

[@limster5]

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

[@rabbitmetrics]

You're welcome! Thanks for watching

[@hardikmehta8308]

Fantastic overview of Langchain! Thank you @Rabbitmetrics

[@raffdev]

Thanks for sharing the knowledge 👍

[@johnshaff]

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

[@MeatCatCheesyBlaster]

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

[@albertocambronero1326]

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

[@dendrites]

@@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.

[@albertocambronero1326]

​@@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)

[@ugaaga198]

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.

[@sujoyroy3157]

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?

[@CinematicHeartstrings]

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

[@rabbitmetrics]

Glad it was helpful!

[@user-nk7lx2rw4t]

Excellent overview - Thanks!

[@rabbitmetrics]

You're welcome, thanks for watching!

[@muhammadhaseeb2895]

Absolutely love the way you explained.

[@rabbitmetrics]

Thank you!

[@TheOGDesigner]

Great explanation, thanks!

[@shyama5612]

Excellent intro. Harrison would approve!

[@rabbitmetrics]

Thank you!

[@ayhamkanhoush2912]

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

[@lpanebr]

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

[@alioraqsa]

This is really great video!

[@roberthuff3122]

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

[@kevon217]

great overview and slides

[@ilianos]

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

[@micbab-vg2mu]

Great video! Thank you.

[@felipeblin8616]

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

[@henrisiepmann3501]

Great explanation!

[@emptiness116]

Thank you for your contribution through the KZbin space

[@rabbitmetrics]

Appreciate it! Thanks for watching

[@stereo_stan]

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

[@xGogita]

Brilliant. Structured and clear.

[@rabbitmetrics]

Thank you!

[@Stoicbob]

amazing tutorial. thank you. you are amazing

[@andre-le-bone-aparte]

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

[@rabbitmetrics]

Thank you I appreciate the support!

[@auslei]

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.

[@leonardosouzaconradodesant6213]

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

[@rabbitmetrics]

Thanks for watching!

[@realJeremyZhang]

Awesome Explanation

[@petrkushnir8178]

Bloody brilliant!

[@namenl2205]

so well explained! :)

[@rabbitmetrics]

Thanks!

[@peralser]

Wonderful video. Thanks.

[@jordanchristley1306]

Highly appreciated video

[@zh4842]

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

[@kailashbalasubramaniyam230]

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

[@zenfoil]

👍 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.

[@rabbitmetrics]

Thanks! 🙏 Glad it was helpful

[@alanwunsche-official]

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

[@PhoebePhuu]

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?

[@musumo1908]

Thanks! This is the best high level langchain video I have watched. Im not a programmer but this overview is invaluable...its clearly explained and demystified the dark arts of langchain 😂😂...question, whats the most straightforward way of converting website data into vectors? Is there some way to scrape urls...looking to create simple q&a agents for small websites...thanks

[@rabbitmetrics]

I’m glad it was helpful, I appreciate the comment! Regarding scraping urls, take a look at the latest video I’ve uploaded kzbin.info/www/bejne/f17Flnuio556q9U In that video I’m using LangChain’s integration with Apify to extract content from my own webpage

[@musumo1908]

@@rabbitmetrics thanks. Yes took a look. Will see what I can do. Came across Apify in my research yesterday ! Will try to run this with llamaindex ….Im teaching myself! There’s not many apify videos around so thanks

[@youngsdiscovery8909]

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

[@rabbitmetrics]

I agree!

[@venkatkasthala1554]

Thanks a lot. Very good explanation.

[@rabbitmetrics]

Thanks!

[@lee1221ee]

great! I can use this video to teach my friend

[@spacedust8061]

thank you a lot, really helped

[@babakbandpey]

Thanks friend. You answered a lot of questions here and the repo, helped understanding your presentation much better. Please share more. Have a great day.

[@rabbitmetrics]

You're welcome! Thanks for watching

[@WilmanArambillete]

great video thanks for sharing. I have a question i am a newbie at this, why do we need to do the query in the vector DB? I mean the idea is to use an LLM, inject my data which could be stored into a DB and then ask the model which would include my data to get a response right? But why do i need to do a syntatic search to my DB then ? I am confused

[@florinfilip6355]

Wilman, embeddings must be stored somewhere (typical a vector database) in order to retrieve the document relevant to the question quickly using the indexes.

[@KurtAnderson64]

Newbie question, but home does one create the .env file in colab? I create a new file and try to rename it .env but it just disappears?

[@Tom.malucao]

Really good video!

[@jimg8296]

Nice video, can it be updated to not use any external services. Think dealing with sensitive data, don't want to feed it to OpenAI for embeddings, or use online models.

[@AMYclubNFTs]

that's so amazing !!!

[@vikaspoddar9456]

🎉🎉🎉 Great overview of LangChain, can you do similar video on using LangChain on open_assistant and weiviate vector database

[@rabbitmetrics]

Thanks! That’s a good idea for a video

[@DrAIScience]

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

[@bunnihilator]

Can these LLM return an entity data with all its attributes, or do they only return conversation text?

[@bwilliams060]

Excellent unpack! Can you please provide a link to this notebook?