Recent post on the same topic: https://news.ycombinator.com/item?id=36645575
The Problem with LangChain
11–20 of 97 posts
Re: The Problem with LangChain
#12I generally agree, but why so polemic? I mean, it starts by giving the full name of the original author… calls using his free software a waste of time… destroys the design as if tearing down someone’s work who made bad decisions at every turn when making a brand-new thing that is FOSS. Did anyone else find that a bit strange? Did I miss the light-hearted tone buried somewhere? That said, strangely… useful examples an…
I think you're reading into the tone too much, but I address this very argument at the end.
> No one wants to be that asshole who criticizes free and open source software operating in good faith like LangChain, but I’ll take the burden. To be clear, I have nothing against Harrison Chase or the other maintainers of LangChain (who encourage feedback!). However, LangChain’s popularity has warped the AI startup ecosystem around LangChain itself and the hope of OMG AGI I MADE SKYNET, which is why I am compelled to be honest with my misgivings about it.
Re: The Problem with LangChain
#13Langchain is perfect to give you ideas for how to interact with LLMs, but for me it's been easier to implement everything myself than to use it.
I agree completely. I use it for inspiration and maybe a quick prototype to understand something, but I usually implement the pieces myself. Debugging LangChain performance and bugs is just an exercise in frustration.
Re: The Problem with LangChain
#14I generally agree, but why so polemic? I mean, it starts by giving the full name of the original author… calls using his free software a waste of time… destroys the design as if tearing down someone’s work who made bad decisions at every turn when making a brand-new thing that is FOSS. Did anyone else find that a bit strange? Did I miss the light-hearted tone buried somewhere? That said, strangely… useful examples an…
They're well funded, so go ahead and criticize them.
https://blog.langchain.dev/announcing-our-10m-seed-round-led...
Re: The Problem with LangChain
#15Thanks for referencing the ‘implementing LangChain in 100 lines of code’ post I wrote a few months back. Really glad it was useful. And yes, I completely agree, much of LangChain is an abstraction that does little more than obfuscate.
Re: The Problem with LangChain
#16LangChain is definitely verbose, and personally I don't use it. That being said, they have some pretty interesting tools the author didn't cover: their example selectors e.g. the MaxMarginalRelevance selector [1] is interesting, useful, and similar example selector tools become something close to necessary for managing large LLM applications.
I wish the code quality was better, but poking around their docs does give pretty interesting ideas you can build yourself, even if you don't use LangChain. I think the release of OpenAI function calling has also just kinda sideswiped the need for large parts of these kind of frameworks — you don't need much help in coercing to JSON or parsing anymore if you use the function calling API.
1: https://python.langchain.com/docs/modules/model_io/prompts/e...
Re: The Problem with LangChain
#17I generally agree, but why so polemic? I mean, it starts by giving the full name of the original author… calls using his free software a waste of time… destroys the design as if tearing down someone’s work who made bad decisions at every turn when making a brand-new thing that is FOSS. Did anyone else find that a bit strange? Did I miss the light-hearted tone buried somewhere? That said, strangely… useful examples an…
Disappointment? Langchain promises a lot, it's generated lots of hype, it's got a big VC investment. So it must be awesome. But when you try to use it, you find yourself wasting hours or days to discover there's nothing particularly exciting behind the curtain.
Re: The Problem with LangChain
#18I'm in the exact same spot as the author just a few days in instead of months. Frankly I could see langchain is garbage software just by looking at the code. It still helps me get shit done fast to figure out how things are supposed to work. Sort of a cookbook of AI recepies. Once I have an approach narrowed down I'll rewrite everything on top of stuff langchain is supposedly wrapping. For now it's faster than tracki…
Yes! This is why I started working on AIPL. The scripts are much more like recipes (linear, contained in a single-file, self-evident even to people who don't know the language). For instance, here's a multi-level summarizer of a webpage: https://github.com/saulpw/aipl/blob/develop/examples/summari...
The goal is to capture all that knowledge that langchain has, into consistent legos that you can combine and parameterize with the prompts, without all the complexity and boilerplate of langchain, nor having to learn all the Python libraries and their APIs. Perfect for prototypes and experiments (like a notebook, as you suggest), and then if you find something that really works, you can hand-off a single text file to an engineer and they can make it work in a production environment.
Re: The Problem with LangChain
#19I generally agree, but why so polemic? I mean, it starts by giving the full name of the original author… calls using his free software a waste of time… destroys the design as if tearing down someone’s work who made bad decisions at every turn when making a brand-new thing that is FOSS. Did anyone else find that a bit strange? Did I miss the light-hearted tone buried somewhere? That said, strangely… useful examples an…
I think you're reading into the tone too much, but I address this very argument at the end. > No one wants to be that asshole who criticizes free and open source software operating in good faith like LangChain, but I’ll take the burden. To be clear, I have nothing against Harrison Chase or the other maintainers of LangChain (who encourage feedback!). However, LangChain’s popularity has warped the AI startup ecosystem…
Thanks for replying. I get your angle a bit better now, and as a sarcastic guy should have gotten it!
My main headfake in this actually revolutionary-incremental advance over the past 8 or so months… has been more similar to yours than I read at first. Nice post!
Re: The Problem with LangChain
#20In response to how over complex I saw the langchain and autogpt code was, I made my own implementation that starts with a solid foundation to doing similar types of things https://youtu.be/KN_etwBLej8 and I share the code if you want to do the same