TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Hacking LangChain for fun and profit

79 点作者 oldgun将近 2 年前

5 条评论

collinc777将近 2 年前
There's a pretty steep learning curve to langchain. I recommend avoiding it if you don't need higher level of abstractions.
yujian将近 2 年前
Great conceptual explanation of the different primitives in LangChain. Some possible inspiration for your upcoming piece involving vector stores with LangChain - <a href="https:&#x2F;&#x2F;milvus.io&#x2F;blog&#x2F;conversational-memory-in-langchain.md" rel="nofollow noreferrer">https:&#x2F;&#x2F;milvus.io&#x2F;blog&#x2F;conversational-memory-in-langchain.md</a>
fallingmeat将近 2 年前
still not sure of the value of the langchain abstraction. does anyone use it in prod?
评论 #36689262 未加载
评论 #36693911 未加载
评论 #36689811 未加载
评论 #36688172 未加载
评论 #36687992 未加载
flakiness将近 2 年前
Although LangChain might not be great as a library&#x2F;framework, it still could be a great starting point to learn about programming pattern for prompt&#x2F;actor programming.<p>They used to have a &quot;concepts&quot; page that links to relevant papers but it seems that the page is gone from the doc for some reason :-(
tehsauce将近 2 年前
I’ll save yall some time. If you are familiar with concatenating strings in python, langchain is a library which does just that, only a little less cleanly. Hope this helps!
评论 #36690500 未加载
评论 #36688815 未加载
评论 #36689477 未加载
评论 #36690326 未加载