[HN Gopher] Understanding LangChain Basic Concepts
___________________________________________________________________
Understanding LangChain Basic Concepts
Author : oldgun
Score : 31 points
Date : 2023-07-10 17:37 UTC (1 days ago)
(HTM) web link (blog.kevinhu.me)
(TXT) w3m dump (blog.kevinhu.me)
| collinc777 wrote:
| There's a pretty steep learning curve to langchain. I recommend
| avoiding it if you don't need higher level of abstractions.
| fallingmeat wrote:
| still not sure of the value of the langchain abstraction. does
| anyone use it in prod?
| wpride wrote:
| We do, but mostly as a fairly nice and fairly well-documented
| interface for plugging together tools like vector DBs and
| memory with LLMs.
|
| My feeling is that with the agentic/AutoGPT hype fading and
| OpenAI adding the functions API there's a lot less value in
| LangChain's abstractions, at least for production use cases.
| They're still cool for hacking/toys.
| viscanti wrote:
| Some of the abstractions seem a bit forced, but it seems nice
| to be abstracted away from how you'd handle vector storage or
| the LLM that get used (maybe someone launches something that
| does better than GPT4 on some sets of tasks and a few line
| change to swap over would be nice).
| yujian wrote:
| Great conceptual explanation of the different primitives in
| LangChain. Some possible inspiration for your upcoming piece
| involving vector stores with LangChain -
| https://milvus.io/blog/conversational-memory-in-langchain.md
| tehsauce wrote:
| I'll save yall some time. If you are familiar with concatenating
| strings, langchain is a library which does just that, only a
| little less cleanly. Hope this helps!
___________________________________________________________________
(page generated 2023-07-11 23:01 UTC)