[ggnore7452]

The place where I work was an early adopter of LLM, having started working on it a year ago.

When I build stuff with GPT-3, especially in the earlier days, I get the strong impression that it's like we are doing machine learning without Numpy and Pandas.

with LangChain, many of the systems I have built can be done in just one or two lines, making life much easier for rest of us. I also believe that LangChain's Agent framework is underappreciated as it was pretty ahead of its time until the official ChatGPT plugins were released. (contributed to LangChain a bit too.)

Unfortunately, the documentation is lacking indeed. While I understand the need to move quickly, it is not good that some crucial concepts like Customized LLM have inadequate documentation. (Perhaps having some LLM builds on top of the repo would be more effective than documentation at this point.)

[Karrot_Kream]

The docs are lacking but the underlying code is so simple that it's just a few clicks/rg searches away from figuring out what you need. It's all mostly ways to do string templating. IMO the ergonomics of LangChain need an overhaul; there's too many ways to do the same thing and there's too much type erasure that makes it hard to use strengths in a particular LLM. For example, it's still a pain to distinguish between using a Chat oriented LLM vs a regular completion one.

There also seems to be really poor observability in the code and performance seems to be an afterthought. I tell friends who ask about LangChain that it's great to experiment with but not something I'd put into production. Hopefully this funding helps them shore things up.

[SheinhardtWigCo]

Are you saying you'd use something else in production?

> For example, it's still a pain to distinguish between using a Chat oriented LLM vs a regular completion one.

Totally agree. After using it for a few weeks, this is one of the most visible weaknesses in the design.

[thequadehunter]

I was about to rant about the documentation, but I just checked and it seems to have improved a lot.

[mpaepper]

I agree that the agents are underappreciated.

To make them more accessible I rewrote them in ~200 lines of code, so you can easily understand how it works.

They have access to a python console, Google search and hacker news search:

https://github.com/mpaepper/llm_agents

[paulgb]

In case anyone misses it buried in the readme, your accompanying blog post looks like the solid introduction to the subject that I've been looking for: https://www.paepper.com/blog/posts/intelligent-agents-guided...

[jason-phillips]

I was looking through Langchain's docs and code last weekend. I'm surprised how well it is documented, actually. I thought it was fairly feature rich vis-a-vis potential chaining opportunities, but with obvious room to grow. Quite impressive, all things considered.

Excited to see what happens going forward.

[startupsfail]

I think LangChain is already outdated and it (and its copycats) are going to cripple the entire field.

[intelVISA]

It is, but it'll still get copious funding and let a few sly engineers escape the Matrix - so what's the harm?

[cube2222]

Could you expand on what you think is the state of the art and direction we should be heading in?

[spacemanspiff01]

Why? What do you think the better model is?

[o_____________o]

There are two Javascript alternatives, but how robust the development is remains to be seen:

https://github.com/hwchase17/langchainjs

https://github.com/cfortuner/promptable

[TrevorJ]

Where do you see Langchain fitting into the ecosystem once Open AI rolls out plugins more widely?

[ggnore7452]

it still works well with other LLM (like llama and more).

various small, open sourced, and verticle LLMs vs one large GPT models would be quite interesting.

[passion__desire]

Then we will connect plugins visually as Unreal's Blueprint Visual Scripting allows.

[thequadehunter]

It's unfortunate that prettymuch all shiny AI things have horrible documentation. I see a lot of misinformation in non-researcher AI circles and I feel like it stems from that sometimes.

[stan_kirdey]

it is ironic that documentation is lacking when it can be generated with an LLM, using LangChain itself