[HN Gopher] We no longer use LangChain for building our AI agents
       ___________________________________________________________________
        
       We no longer use LangChain for building our AI agents
        
       Author : ma_za
       Score  : 38 points
       Date   : 2024-06-20 15:41 UTC (7 hours ago)
        
 (HTM) web link (www.octomind.dev)
 (TXT) w3m dump (www.octomind.dev)
        
       | CharlieDigital wrote:
       | Bigger problem might be using agents in the first place.
       | 
       | We did some testing with agents for content generation (e.g.
       | "authoring" agent, "researcher" agent, "editor" agent) and found
       | that it was easier to just write it as 3 sequential prompts with
       | an explicit control loop.
       | 
       | It's easier to debug, monitor, and control the output flow this
       | way.
       | 
       | But we still use Semantic Kernel[0] because the lowest level
       | abstractions that it provides are still very useful in reducing
       | the code that we have to roll ourselves and also makes some parts
       | of the API very flexible. These are things we'd end up writing
       | ourselves anyways so why not just use the framework primitives
       | instead?
       | 
       | [0] https://github.com/microsoft/semantic-kernel
        
         | Kiro wrote:
         | What's the difference? I thought "agents" was just a fancier
         | word for sequential prompts.
        
       | deckar01 wrote:
       | I recently unwrapped linktransformer to get access to some
       | intermediate calculations and realized it was a pretty thin
       | wrapper around SentenceTransformer and DBScan. It would have
       | taken me so much longer to get similar results without copying
       | their defaults and IO flow. It's easy to take for granted code
       | you didn't have to develop from scratch. It would be interesting
       | if there was a tool that inlined dependency calls and shook out
       | unvisited branches automatically.
        
         | luke-stanley wrote:
         | From memory, I recall Vulture might do something like that!
        
       | danielmarkbruce wrote:
       | Yup. The problem with frameworks is they assume (historically
       | mostly but not always correctly) that layers of abstraction mean
       | one can forget about the layers below. This just doesn't work
       | with LLMs. The systems are closer to biology or something.
        
       | Kydlaw wrote:
       | IMO LangChain provides very high level abstractions that are very
       | useful for prototyping. It allows you to abstract away components
       | while you dig deeper on some parts that will deliver actual
       | value.
       | 
       | But aside from that, I don't think I would run it in production.
       | If something breaks, I feel like we would be in a world of pain
       | to get things back up and running. I am glad they shared their
       | experience on that, this is an interesting data point.
        
       | cyanydeez wrote:
       | In some sense, this could be retitled "We no longer use training
       | wheels on our bikes"
        
       | maximilianburke wrote:
       | I just pulled out LangChain from our AI agents; we now have much
       | smaller docker images and the code is a lot easier to understand.
        
       ___________________________________________________________________
       (page generated 2024-06-20 23:00 UTC)