Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why we no longer use LangChain for building our AI agents

octomind.dev

Post reply on HN
Print view View original

41–50 of 307 posts

Re: Why we no longer use LangChain for building our AI agents

#41

Post by causal »

refulgentis wrote: post #34
infecto wrote: post #33

LangChain itself blows my mind as one of the most useless libraries to exist. I hope this does not come off the wrong way but so many people told me they were using it so it was easy to move been models. I just did not understand it, these are simple API calls that felt like Web Dev 101 when starting a new product. Maybe its that so many new people were coming into the field using LLM but it surprised me as even what…

Ah, the halcyon days of March 2023, we were a while loop away from AGI. I remember there was something that was It for like a month, to the point that whoever built the framework was treating a cocktail napkin on which they scribbled, whatever, "act, evaluate, decide next action, repeat", as if it was a historical talisman. And I wasn't sure! Maybe it was!

Yeah I thought the consensus against LangChain was formed a year ago, surprised to still be seeing these articles.

Re: Why we no longer use LangChain for building our AI agents

#42

Post by richrichie »

infecto wrote: post #33

LangChain itself blows my mind as one of the most useless libraries to exist. I hope this does not come off the wrong way but so many people told me they were using it so it was easy to move been models. I just did not understand it, these are simple API calls that felt like Web Dev 101 when starting a new product. Maybe its that so many new people were coming into the field using LLM but it surprised me as even what…

Langchain seems to have been made just for the tutorial business on Udemy and Youtube.

Re: Why we no longer use LangChain for building our AI agents

#43

Post by refulgentis »

causal wrote: post #41
refulgentis wrote: post #34

Earlier quoted context omitted.

Ah, the halcyon days of March 2023, we were a while loop away from AGI. I remember there was something that was It for like a month, to the point that whoever built the framework was treating a cocktail napkin on which they scribbled, whatever, "act, evaluate, decide next action, repeat", as if it was a historical talisman. And I wasn't sure! Maybe it was!

Yeah I thought the consensus against LangChain was formed a year ago, surprised to still be seeing these articles.

Just chit chatting, not a strong claim, more a hot take I turn over in my mind:

my guess is 40% of software engineers did a AI pivot the last 18 months, so there's a massive market for frameworks, and there's an inclination to go beyond REST requests, find something that just does it for you / can do all the cool patterns you'll find in research papers.

Incredible amount of bad info out there, whether its the 10th prompting framework that boils down to a while loop and just drives up token costs, the 400 LLM tokenizer library that can only do GPT-3.5/4.0, the Nth app that took XX ex-FAANG and $XX mil and a year to get another web app, or another iOS-only OpenAI client with background blur,m memory thats an array of strings injected into every call

It's at the point where I'm hoping for a cooling down even though I'm launching something*, and think it's hilarious people rant about it all just being hype and think people agree.

* TL;Dr consumer app with 'chain gui', just hand people an easy to use GUI like playground.openai.com / console.anthropic.com, instead of getting cute and being the Nth team to try to launch a full grade assistant on a monthly plan matching openai pricing, shoving 6000K+ prompts with each request and not showing them

Re: Why we no longer use LangChain for building our AI agents

#45

Post by ahzhou »

altdataseller wrote: post #17

Langchain reminds me of GraphQL. A technology that a lot of ppl seem to hype about, sounds like something you should use because all the cool kids use it, but at the end of the day just makes things unncessarily complicated.

GraphQL is very powerful when combined with Relay. It’s useless extra bloat if you just use it like REST.

The difference between the two technologies is that LangChain was developed and funded before anyone know what to do with LLMs and GraphQL was internal tooling using to solve a real problem at Meta.

In a lot of ways, LangChain is a poor abstraction because the layer it’s abstracting was (and still is) in it’s infancy.

Re: Why we no longer use LangChain for building our AI agents

#46

Post by lolinder »

ilaksh wrote: post #26
lolinder wrote: post #14

Earlier quoted context omitted.

For most of what people are doing with AI you don't need Python because you don't need the ML ecosystem. You're either going to be talking to some provider's API (in which case there are wrappers aplenty and even if there weren't their APIs are simple and trivial to wrap yourself) or you're going to self-host a model somewhere, in which case you can use something like ollama to give yourself an easy API to code again…

They become agents when the LLM output is function calls.

So the output of Black Box A is an instruction to give Black Box B a piece of data X and then give the resulting output back to BBA. We're still just wiring up black boxes to each other the same as we've always done, and we still don't need an abstraction for that.

Re: Why we no longer use LangChain for building our AI agents

#47

Post by langcss »

ravenstine wrote: post #38
infecto wrote: post #33

LangChain itself blows my mind as one of the most useless libraries to exist. I hope this does not come off the wrong way but so many people told me they were using it so it was easy to move been models. I just did not understand it, these are simple API calls that felt like Web Dev 101 when starting a new product. Maybe its that so many new people were coming into the field using LLM but it surprised me as even what…

Every time I approached LangChain, contrary to the attitude of my colleagues, I could never figure out what the point of it was other than to fetishize certain design patterns. Interacting with an LLM in a useful way requires literally none of what LangChain has to offer, yet for a time it was on its way to being the de facto way to do anything with LLMs. It reminds me a lot of the false promise of ORMs, which is tha…

ORMs are useful though for a different reason. They let you creat typed objects then generate the schema from them and automatically create a lot of boilerplate SQL for you.

Admittedly for anything more than 1-2 joins you are better off hand crafting the SQL. But that is the exception not the rule.

Refactoring DB changes becomes easier, you have a history of migrations for free, DDL generation for free.

In the early 2000 I worked where people handcrafted SQL for every little query for 100 tables and yeah you end up with inconsistent APIs and bugs that are eliminated by code generation / meta programming done by ORMs.

Re: Why we no longer use LangChain for building our AI agents

#48

Post by nosefurhairdo »

altdataseller wrote: post #17

Langchain reminds me of GraphQL. A technology that a lot of ppl seem to hype about, sounds like something you should use because all the cool kids use it, but at the end of the day just makes things unncessarily complicated.

Evaluating technology based on its "cool kid usage" and a vague sense of complexity is likely not the best strategy. Perhaps instead you could ask "what problems does this solve/create?"

Re: Why we no longer use LangChain for building our AI agents

#49

Post by chatmasta »

infecto wrote: post #33

LangChain itself blows my mind as one of the most useless libraries to exist. I hope this does not come off the wrong way but so many people told me they were using it so it was easy to move been models. I just did not understand it, these are simple API calls that felt like Web Dev 101 when starting a new product. Maybe its that so many new people were coming into the field using LLM but it surprised me as even what…

It was the first pass at solving the common problems when building with LLMs. People jumped on it because it was trendy and popular.

But it quickly became obvious that LangChain would be better named LangSpaghetti.

That’s nothing against the authors. What are the chances the first attempt at solving a problem is successful? They should be commended for shipping quickly and raising money on top of it to keep iterating.

The mistake of LangChain is that they doubled down on the bad abstraction. They should have been iterating by exploring different approaches to solving the problem, not by adding even more complexity to their first attempt.

Post reply on HN