News for hackers. Stuff that matters.
Re:LangChain: Build AI apps with LLMs through composability by hooande on Tuesday January 17, 2023 @10:29PM (#34423112)
Isn't this a chat interface to various apis? I guess that's the point. But it doesn't seem like that is utilizing the power of large language models. Maybe I'm not understanding this.

Using a Google search api + a calculator to answer a question is cool [0]. but... we could already do that?

[0] https://langchain.readthedocs.io/en/latest/modules/agents/ex...

Re:LangChain: Build AI apps with LLMs through composability by mahastore on Tuesday January 17, 2023 @11:03PM (#34423310)
Yes also the part I don't understand is that how langchain can be used to make the agents smarter for a particular domain? I did not see any interface to provide feedback of feed data. Maybe I am missing something?
Re:LangChain: Build AI apps with LLMs through composability by Ozzie_osman on Wednesday January 18, 2023 @12:12AM (#34423644)
It's usually either providing data to the LLM, or doing back-and-forth with the LLM (usually a mix of both).

For instance, if you want it to answer questions about your code-base, the model doesn't know your code base. You can't feed the entire code-base into a prompt. So, you'd use langchain to: - preprocess your code-base, by chunking it and embedding it in some vector space - when you get a question, see where it is in the vector space and find the "k nearest neighbors" - pass those nearest neighbors, along with your question, to the LLM (because those neighbors are the contextually relevant pieces, and they'd fit in the prompt)

Re:LangChain: Build AI apps with LLMs through composability by delijati on Wednesday January 18, 2023 @06:00AM (#34425376)
i would really love to give it a try but with an offline LLM :/
Re:LangChain: Build AI apps with LLMs through composability by KennyFromIT on Tuesday January 17, 2023 @11:05PM (#34423317)
They have a dedicated chat bot for their docs that might be able to help you find answers to your questions...

https://chat.langchain.dev/

Re:LangChain: Build AI apps with LLMs through composability by user- on Tuesday January 17, 2023 @11:28PM (#34423440)
Me > can i use docker?

AI > Yes, you can use Docker with LangChain. For more information, please see the Docker Installation Guide in the LangChain documentation.

Then it links to a 404 lol. I checked the docs and there is nothing about docker in them. I wonder why its incorrect here

Re:LangChain: Build AI apps with LLMs through composability by andreigheorghe on Wednesday January 18, 2023 @06:30AM (#34425552)
maybe it's trained on non-published documentation pages?
[dead]
Re:LangChain: Build AI apps with LLMs through composability by rafaquintanilha on Wednesday January 18, 2023 @10:41AM (#34428032)
You can actually train the model to have access only to a specific body of text, like a documentation.

Very useful article explaining this approach: https://dagster.io/blog/chatgpt-langchain

Re:LangChain: Build AI apps with LLMs through composability by bob29 on Tuesday January 17, 2023 @11:42PM (#34423508)
>but... we could already do that? that sums up so much. the emperor has no clothes. few see it. its inferior to the modern purpose built tools. we act impressed a simple program can be created from a prompt, what has every programmer been doing already for the last 10 years with google search and stackoverflow?
Re:LangChain: Build AI apps with LLMs through composability by motoxpro on Wednesday January 18, 2023 @12:00AM (#34423584)
Another comment from this thread seems pretty cool to me. https://github.com/approximatelabs/sketch
Re:LangChain: Build AI apps with LLMs through composability by yunwal on Tuesday January 17, 2023 @11:54PM (#34423561)
I think building regexes is a good example of where chatgpt/copilot is useful. It’s not that it’s particularly difficult or requires much understanding, just very time consuming compared to writing an English language description and walking through an example.
Re:LangChain: Build AI apps with LLMs through composability by bob29 on Wednesday January 18, 2023 @09:24AM (#34426913)
Useful compared to writing a regex in notepad yeah.

Last time I was challenged by regex I easily found very fancy web page with so many nice features. Actual documentation, ability to select a specific regex engine (or implementation or whatever you call it) , real-time results on test data, highlighting that shows how the regex works, etc. and that was years ago I’m sure there’s even better web apps now.

I can’t imagine having a better experience asking AI chat than using a web app made for the purpose

Re:LangChain: Build AI apps with LLMs through composability by yunwal on Wednesday January 18, 2023 @10:13AM (#34427591)
Do you have a link to the site?

Being able give some examples and just state in plain English what you want the capture groups to be is pretty much my ideal regex experience (in other words, I don’t want to think about the semantics of regex ever).

Re:LangChain: Build AI apps with LLMs through composability by sandkoan on Wednesday January 18, 2023 @01:38PM (#34430924)
This might be what they're referring to: https://regex101.com/.
Re:LangChain: Build AI apps with LLMs through composability by yunwal on Thursday January 19, 2023 @11:19AM (#34441981)
That’s what I figured. Maybe it’s just me but for complicated use-cases this still takes me forever to get the right regex string, especially with capture groups.