You are amazing. I'm a web dev, and I found your channel because of the first langchain tutorial. Then I find this, you have thought of everything! Truly grateful, and I'm keeping a close watch to learn from you. For your info, I would most certainly pay for a course by you on bringing an LLM app to production.
@@codingcrashcourses8533 Thank you, yes, I've had time to go through the rest of the videos. Truly excellent. I have a lot of learning to do to get up to the right level, and will keep coming back for more.
31 thousand views over 1 year and I'm making the first Like? That's nuts. Thanks for your time on this. I appreciate the direct style and solid quality.
@@codingcrashcourses8533 I see them now. App needed restart. sigh BTW The JS-specific content is much appreciated. A competent dev can translate but the language-specific vid removes a mental barrier ... and is also better for marketing your course offering to a broader audience. Good luck.
Thank you for the video, it was incredibly helpful. I was wondering if you could create a video that demonstrates the integration of all these elements. It would be fantastic to see how to set up a conversation, that will be stored, that utilizes sequential chains, incorporates the Vector Database, and implements an Agent. Watching all these components work together would be truly insightful. Managing chains, especially in larger projects, is a challenge I'm trying to overcome.
instead of putting the files in the project directory can we upload the files in AWS S3 or other cloud storage? how can we handle the conversion of files to vector embeddings using that approach?
excellent course, covers the basics to get started, i prefer the frame work in Javascript Node.js although i know the libraries are the same as the python one
Can I only use FaissStore with the paid version of the API key? I am getting an error: Error processing documents: Error: Request failed with status code 429
Is it possible for you to make a tutorial on how to use langchain JS with Amazon Bedrock API? I don't see many tutorials on the same. If you could do that, it would be super helpful. Great video by the way!
Nice and clear video. Maybee something for the future: I'd like to know more about how to create a custom tool, like creating a database connection and sending SQL as input for example. I tried using the calculato.jcs file as a template for a new custom tool but i get all kinds of errors from the library i dont understand unfortunately
Well this is an advanced request not many might be interested in. I also have other, more project based videos on the channel. This is just an Intro to the lib
REST Services should be stateless, so you should handle the memory outside of that service. I recommend not using the memory class inside a REST Service. I created multiple videos on langchain in production and one makes use of redis as memory. Here is the video: th-cam.com/video/I_4jEnDwGwI/w-d-xo.html
@@codingcrashcourses8533 I have installed langchain using: npm install -S langchain However, when I import I get the following error. I have put the target in tsconfig as ES2020, too: ../../../../node_modules/langchain/dist/callbacks/handlers/tracer.d.ts:22:23 - error TS2583: Cannot find name 'Map'. Do you need to change your target library? Try changing the 'lib' compiler option to 'es2015' or later. 22 protected runMap: Map; ~~~ Found 1 error in ../../../../node_modules/langchain/dist/callbacks/handlers/tracer.d.ts:22
Late for the party, but the error is in your import. I suppose you're trying to "import {callbacks} from 'langchain'. But thats deprecated. You should do something like 'import {handlers} from 'langchain/callbacks' This is not a copy and paste solution, but just to express the idea that now you have to import from the individual modules instead of root 'langchain'
Do you recommend any free to use LLM? OpenAI is no longer free and I just would like to play around langchain. Also, how safe are the LLMs to use in terms of getting our data exposed for their own ML scripts? I mean, will ChatGPT be trained by my chain calls using my private database resources?
Llama2 is currently state of the Art for open Source models. For openai models you can opt out, but i would recommend against using it for sensitive data.
@@codingcrashcourses8533 wow, really appreciated the llama 2 recommendation. I'm reading some articles and it looks amazing. I'm just wondering about the model being trained using our private data as well. I'll check if I can find an optout as you mentioned OpenAI does. Thanks again!
Hi. Can you please help select from LangChain objects? I need functionality from LangChain that allows me to switch a prompt (or probably a chain) if the user asks "How do I pay less tax?". If he asks this question, I need to ask him about his form of ownership, type of taxation, etc. and then use this information to select another prompt for further processing. But I use ConversationalRetrievalQAChain to work with OpenAI and Pinecone. My question is what is better to use for such a task? SequentialChain or Router or something else? Please not that I use TypeScript to write this app. Thank you!
I have the same task (with python) and do it like this. I use a custom classfier chain that returns an object. I run normal LLMChains and add the documents from the vectorstore manually, since it gives me more control, but thats of course up to you :)
@@codingcrashcourses8533 Sounds not so easy for me, especially considering JS/TS langchain isn't the same as Python version (not all of the objects are there. I couldn't find Router for example). Could you maybe shot a tutorial about this Dynamic Prompting with your custom Chain class or with some langchain object? :) I can't understand how those other chains would have the same "memory" as my default. Especially if simple chains doesn't have Vector store parameters in its initialisers.
@@wordpressmagics2613 Yeah, Router Chain seems not to exist (yet). Well, all these chains in the end help you to create a final prompt for the LLM which you send to the API. If you understand what the API expects and what the Interfaces of the Classes do under the hood, you can choose if you want a more high level chain or not. In the end, you can also build the history yourself if you want
I don't understand why to use langchain! It make simple things became complex! And also remove all freedom the programs have because of this "chains"! But, in other hands the TOOLS are the best ones!! I just use the tools! forget about this complicated chains and rules to use things and "this must do in this way", that's not why programming was made for!
Sign up for my complete LangChain course: www.udemy.com/course/langchain-in-action-develop-llm-powered-applications/?couponCode=557BD137E003DD93E491
You are amazing. I'm a web dev, and I found your channel because of the first langchain tutorial. Then I find this, you have thought of everything! Truly grateful, and I'm keeping a close watch to learn from you. For your info, I would most certainly pay for a course by you on bringing an LLM app to production.
There are already some vidoes about this in my playlist. Microservice pattern und deployment on ms azure
@@codingcrashcourses8533 Thank you, yes, I've had time to go through the rest of the videos. Truly excellent. I have a lot of learning to do to get up to the right level, and will keep coming back for more.
@@AdrianMark same here
Love it!! Please keep on making JS-AI contents. 👍
Gotta say one of the best videos on Langchain so far pls continue making this legacy content
Thanks, since the interest is quite high, i think about it :)
31 thousand views over 1 year and I'm making the first Like? That's nuts.
Thanks for your time on this. I appreciate the direct style and solid quality.
@@tonyg_nerd May be a Bug, but this vid has 900+ likes. Anyway, thank you :)
@@codingcrashcourses8533 I see them now. App needed restart. sigh
BTW The JS-specific content is much appreciated. A competent dev can translate but the language-specific vid removes a mental barrier ... and is also better for marketing your course offering to a broader audience. Good luck.
Thank you for the awesome tutorial!
Thank you for the video, it was incredibly helpful. I was wondering if you could create a video that demonstrates the integration of all these elements. It would be fantastic to see how to set up a conversation, that will be stored, that utilizes sequential chains, incorporates the Vector Database, and implements an Agent. Watching all these components work together would be truly insightful. Managing chains, especially in larger projects, is a challenge I'm trying to overcome.
I did something quite complex in a different Video. Also doing a microservice architecture in my udemy course
@@codingcrashcourses8533 In which video?
instead of putting the files in the project directory can we upload the files in AWS S3 or other cloud storage? how can we handle the conversion of files to vector embeddings using that approach?
Well Explained!!! Thank you so much for the video
Bro believe me, you helped me a lot with this video.
The content you gave me exactly what I need to know
Thank you very much.
Danke dir für das video. auf jeden fall hat es mir geholfen✌️🤙
Sorry , how to use those JS file in HTML file ? I do ,but wrong
I would recommend to build an express api around this
Bro , You need to create Playlist for individual Videos which you have covered, so we can bookmark
Quite detailed. Thank you for this
great course thanks man
Este video foi incrivel, vou colocá-lo em prática agora mesmo.
Muito Obrigado
Gracias ;)
excellent course, covers the basics to get started, i prefer the frame work in Javascript Node.js although i know the libraries are the same as the python one
Yes, already a little bit outdated unfortunately. But thanks :)
Can I only use FaissStore with the paid version of the API key? I am getting an error: Error processing documents: Error: Request failed with status code 429
when does this happen? Normally faiss is free to use and also will just be a file on your pc
Awesome! Thnak you!!! You are the best!
This guy is a blessing
How sweet ;)
A big fan of this channel. Please make a tutorial on how we can create a next js chatbot with vercel ai sdk and langchain.
thank you very much. To be honest, I have to find that out on my own first. I will pick that up next weekend :)
Is it possible for you to make a tutorial on how to use langchain JS with Amazon Bedrock API? I don't see many tutorials on the same. If you could do that, it would be super helpful. Great video by the way!
Currently not planned. I am pretty unfamiliar with everything from amazon
this was helpful thank you
Amazing!
can you make a tutorial on using langchain with some of the free hugging face api.
@@QuantumCanvas07 i already created tutorials on how to use ollama if that is also an Option for you
Great video I need help within my project do you think you can answer me some questions?
It depends on the Kind of questions. I can not do Personal consulting for everyone. I hope that is understandable
for the agent tools chain, is it passing all that info to the LLM? cause that looks like a whole lot of tokens…
Yes it is. Thats why i am Not the Biggest Fan of agents
Nice and clear video. Maybee something for the future: I'd like to know more about how to create a custom tool, like creating a database connection and sending SQL as input for example. I tried using the calculato.jcs file as a template for a new custom tool but i get all kinds of errors from the library i dont understand unfortunately
Well this is an advanced request not many might be interested in. I also have other, more project based videos on the channel. This is just an Intro to the lib
How can I use the data returned from my embeddings in the browser?
th-cam.com/video/I_4jEnDwGwI/w-d-xo.html take a Look here
Awesome!
Hi, can someone tell me how this memory would work in case of rest api? Does it cache the data locally using the memory key?
REST Services should be stateless, so you should handle the memory outside of that service. I recommend not using the memory class inside a REST Service. I created multiple videos on langchain in production and one makes use of redis as memory. Here is the video: th-cam.com/video/I_4jEnDwGwI/w-d-xo.html
is a nice one but i think latest version open ai chaged witout using the new Configuration
Yep, that was updated quite a bit :)
Could you make a tutorial on how to make applications with rete.js
sorry, I never heard of that before ;-)
@@codingcrashcourses8533 could u please check??🙃
1 problem.
The model `text-davinci-003` has been deprecated which basically all of them use.
Langchain Allows you to easily switch to another model :)
That is true @@codingcrashcourses8533
Just wanted to mention it, really nice tutorial tho
const model = new OpenAI({ temperature: 0, modelName:"gpt-4" });
Great teaching style. I am trying the code on typescript but having a problem with importing langchain. How can we work on typescript?
first of all - thank you very much! Where is the error happening?
@@codingcrashcourses8533 I have installed langchain using: npm install -S langchain
However, when I import I get the following error. I have put the target in tsconfig as ES2020, too:
../../../../node_modules/langchain/dist/callbacks/handlers/tracer.d.ts:22:23 - error TS2583: Cannot find name 'Map'. Do you need to change your target library? Try changing the 'lib' compiler option to 'es2015' or later.
22 protected runMap: Map;
~~~
Found 1 error in ../../../../node_modules/langchain/dist/callbacks/handlers/tracer.d.ts:22
Late for the party, but the error is in your import. I suppose you're trying to "import {callbacks} from 'langchain'. But thats deprecated. You should do something like 'import {handlers} from 'langchain/callbacks'
This is not a copy and paste solution, but just to express the idea that now you have to import from the individual modules instead of root 'langchain'
Can LangChain JS work with a locally running Llama.cpp? if so, do you have any materials on getting that up and running?
sorry, don´t have to much experience with LLama :/
Is there any other way to perform this without using the OPENAI_API_KEY, as the data is not secured when key is used
what do you mean? Why shouldn´t that be safe? You have to provide an API key to use OpenAI
Do you recommend any free to use LLM? OpenAI is no longer free and I just would like to play around langchain.
Also, how safe are the LLMs to use in terms of getting our data exposed for their own ML scripts? I mean, will ChatGPT be trained by my chain calls using my private database resources?
Llama2 is currently state of the Art for open Source models. For openai models you can opt out, but i would recommend against using it for sensitive data.
@@codingcrashcourses8533 thank you very much!
@@codingcrashcourses8533 wow, really appreciated the llama 2 recommendation. I'm reading some articles and it looks amazing. I'm just wondering about the model being trained using our private data as well. I'll check if I can find an optout as you mentioned OpenAI does. Thanks again!
Hi. Can you please help select from LangChain objects? I need functionality from LangChain that allows me to switch a prompt (or probably a chain) if the user asks "How do I pay less tax?". If he asks this question, I need to ask him about his form of ownership, type of taxation, etc. and then use this information to select another prompt for further processing. But I use ConversationalRetrievalQAChain to work with OpenAI and Pinecone. My question is what is better to use for such a task? SequentialChain or Router or something else? Please not that I use TypeScript to write this app. Thank you!
I have the same task (with python) and do it like this. I use a custom classfier chain that returns an object. I run normal LLMChains and add the documents from the vectorstore manually, since it gives me more control, but thats of course up to you :)
@@codingcrashcourses8533 Sounds not so easy for me, especially considering JS/TS langchain isn't the same as Python version (not all of the objects are there. I couldn't find Router for example). Could you maybe shot a tutorial about this Dynamic Prompting with your custom Chain class or with some langchain object? :) I can't understand how those other chains would have the same "memory" as my default. Especially if simple chains doesn't have Vector store parameters in its initialisers.
@@wordpressmagics2613 Yeah, Router Chain seems not to exist (yet). Well, all these chains in the end help you to create a final prompt for the LLM which you send to the API. If you understand what the API expects and what the Interfaces of the Classes do under the hood, you can choose if you want a more high level chain or not. In the end, you can also build the history yourself if you want
@@codingcrashcourses8533 Can I somehow get a paid consultation from you about how can I solve my problem in JavaScript?
Hi this video is great, but sadly outdated, would you mind create a new one with the latest versions ? Thanks!
man...do you sleep? Awesome work
⚠️👉Please make more tutorials on✨ Generative AI, or please tell me where i can learn this.
🌞🌈You are doing great work ❣️👍
Why no typescript?
I sticked close to the official documention
@@codingcrashcourses8533 Ah I see! Thank you for creating this content. If you make more I will be sure to watch 😃
@@lukem121 most of my content will be in python. Thats where I earn my money and am really good at. Js and Frontend is more of a Hobby ;).
why dont you make project videos like chatbot etc?
I have multiple projects on my channel :)
@@codingcrashcourses8533 coupon?
I don't understand why to use langchain! It make simple things became complex! And also remove all freedom the programs have because of this "chains"! But, in other hands the TOOLS are the best ones!! I just use the tools! forget about this complicated chains and rules to use things and "this must do in this way", that's not why programming was made for!