Everyone was so hyped up by this useless thing that I thought I was going crazy. Literally everything is done faster and easier and more readable and more maintainable doing it with a lines of Python yourself. Lot of hype with AI frameworks, especially this one.
Langchain Is Pointless
141–150 of 192 posts
Re: Langchain Is Pointless
#142The reason why Langchain is pointless is that it's trying to solve problems on top of technical foundations that just cannot support it. The #1 learning is that there is no reusability with the current generation of LLMs. We're using GPT-4 and 3.5T exclusively. Over the last several months, my team has been building several features using highly sophisticated LLM chains that do all manner of reasoning. The ultimate o…
100% agreed. I've used GPT professionally and we would try out different hosts, AI21, etc. and it there were always clear quality issues with just re-using your prompt and hyperparameters. Some of that was down to other models being lesser quality, but we'd also need to re-tune prompts when upgrading to new OpenAI models for the best effect. It turns out that LLMs aren't quite a commodity.
This is precisely why open source models will be limited. Most of the capabilities distinguishing GPT and later Gemini are emergent behaviors from the large parameter count the open source community is saying is not needed (at least for now).
Re: Langchain Is Pointless
#143The reason why Langchain is pointless is that it's trying to solve problems on top of technical foundations that just cannot support it. The #1 learning is that there is no reusability with the current generation of LLMs. We're using GPT-4 and 3.5T exclusively. Over the last several months, my team has been building several features using highly sophisticated LLM chains that do all manner of reasoning. The ultimate o…
this is precisely the problem i encountered and tried to solve with Edgechains. we think Generative AI is a config management problem (like Terraform or Kubernetes).
>None of this stuff is reusable. Langchain is attempting to set up abstractions to reuse everything. But what we end up with a mediocre DAG framework where all the instructions/data passing through is just garbage. The longer the chain, the more garbage you find at the output.
chains X prompts X LLMs == pods X services X nodes in Terraform.
So we model it on top of config management grammar that is proven to work in large production config - jsonnet.
A trivial example is this - https://github.com/arakoodev/EdgeChains/blob/main/Examples/r...
Would love to get an example of complex chains (even if u have an ARxiv paper) that you think we could solve in Edgechains-jsonnet ?
Re: Langchain Is Pointless
#144The reason why Langchain is pointless is that it's trying to solve problems on top of technical foundations that just cannot support it. The #1 learning is that there is no reusability with the current generation of LLMs. We're using GPT-4 and 3.5T exclusively. Over the last several months, my team has been building several features using highly sophisticated LLM chains that do all manner of reasoning. The ultimate o…
Much of why this stuff is not reusable is that eventually someone in the NLP world is going to properly migrate the features for promopt engineering that the coomers over in stable-diffusion/automatic1111 land have "pioneered", such as token weighting, negative prompts, token averaging, or etc. Literally all of these techniques work with regular LLMs (if you don't believe me, see here: https://gist.github.com/Helliso…
Automatic111 is the domain of Jupyter - desktop experimentation. When you go into production, there are tons of additional pieces of complexity that start hitting you - like prompt routing. So the problem space is different.
We have a simple concept - Generative AI is config management. We model it on top of config management grammar that is proven to work in large production config - jsonnet.
A trivial example is this - https://github.com/arakoodev/EdgeChains/blob/main/Examples/r...
Do u think this is something that works for you ?
Re: Langchain Is Pointless
#145Since last year, before I heard about langchain, I've been building my own stack of tooling for my own LLM projects that probably now covers about 10-20% of Langchain's functionality. I heard about Langchain earlier this year and groaned, thinking that I did a lot of work for nothing.. ..Then I actually used langchain. I was shocked at how poorly performant the code is. Some operations took 10x longer than how I did…
Yeah I've got a few thousand lines of langchain code now for a data cleaning pipeline... I've been fighting it every step of the way. Trying to replace sections of the pipeline to use a local LLM instead of OpenAI has had me have to replace the templates entirely, the chat based templates won't allow me to assign the proper user/assistant names, so the performance for the local LLM is terrible (stupid). They have zer…
I have an attempt in the same domain, would love feedback
We think - Generative AI is config management. We model it on top of config management grammar that is proven to work at K8s/Terraform scale - jsonnet.
https://github.com/arakoodev/EdgeChains/blob/main/Examples/r...
Prompts live outside the code. We didnt invent a new markup - we used jsonnet which is used in large scale kubernetes and has a grammar that has been well tested for config mgmt.
Re: Langchain Is Pointless
#146I believe the abstractions in Langchain are inherently flawed. The core problem resides in the composability of chains. While it offers a handy way to create prototypes, it becomes restricting when you desire to modify a specific element within the chain. The hierarchical design of chains in Langchain conceals the component you wish to alter and obscures the parts developers might want to adjust, making the process o…
Take a look at https://promptfile.org/ for an alternative approach to the prototyping -> app flow.
Promptfile is written in markdown, which is unsuited for templates and config management.
I have an attempt in the same domain, would love feedback
We didnt invent a new markup - we used jsonnet which is used in large scale kubernetes and has a grammar that has been well tested for config mgmt.
https://github.com/arakoodev/EdgeChains/blob/main/Examples/r...
Prompts live outside the code.
Re: Langchain Is Pointless
#147I have a full-on "The Problem With LangChain" blog post in the pipeline, and the reason I made a simple alternative ( https://news.ycombinator.com/item?id=36393782 ) because I spent a month working with LangChain and coming to the conclusion that it's just easier to make my own Python package than it is to hack LangChain to fit my needs. A few bullet points: - LangChain encourages tool lock-in for little developer be…
> Part of the reason I'm hesitant to release said blog post is because I don't want to be that asshole who criticizes open source software that's operating in good faith.
I agree with your restraint, this feels like it might be more productive in another format. Ultimately this either needs to be broached with the maintainers or an alternative should be started.
Re: Langchain Is Pointless
#148Remember, this is the project that raised ~$30m from Benchmark and Sequoia. There was a controversial "quality doesn't matter for software products" post and discussion[0] here on HN a few days ago and this is a beautiful example. Product may matter eventually, but you can sure surf the hype for a long time before the reckoning comes (and if you're lucky, you may even be able to get someone else to hold the bag then)…
We’ve seen the top dog fall from grace in the VC world before (KPCB missing social and mobile after a truly epic run in the 90s) Is that what we are starting to see for Sequoia? Like KP, I doubt they’ll fold, but it would be interesting to live in a world where sequoia is just top half instead of top 1.
Sequoia never figured out their edge in the enterprise world. They likely won't fall from grace since they're still investing in the space, but their filter is certainly poorer than their other areas of investment.
Re: Langchain Is Pointless
#149100% agree. It is just a tactical way to SLOW LLM startups down with debugging hell. Highly would not recommend.
Re: Langchain Is Pointless
#150LangChain is a "utils" library
Change my mind.