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。

LLM Stack for 2024 – Initial Survey

3 点作者 yujian大约 1 年前

3 条评论

stevekaram大约 1 年前
I think one of the biggest struggles small startups and practitioners are facing is lack of a good option between &quot;I wonder if this works&quot; and &quot;ready for prime time.&quot; Running locally is an option with consumer hardware but is cost prohibitive for a team. Cloud providers are full of complications and hidden costs. Tools like Friendli and Bento are good but ambiguous on costs and get difficult to price end-to-end once you need the full stack of options. Hugging Face inference endpoints and other tools still seem like the best option around along with cloud DBs like Zilliz.<p>That said, it&#x27;s no wonder people just pay extra for the simplicity of a slightly smarter endpoint like OpenAI. Sure, over time the costs are insane and you lack any flexibility to create a truly targeted solution, but it <i>feels</i> like an all-in-one easy fix.
yujian大约 1 年前
Hi everyone, I put together this survey of tools for the LLM Stack in 2024. I&#x27;ve linked the friend-link for the Medium article in the URL. I&#x27;d love feedback from you guys about any tools I&#x27;ve missed.<p>If you&#x27;re a Medium member and want to support my writing, feel free to use the regular link - <a href="https:&#x2F;&#x2F;medium.com&#x2F;plain-simple-software&#x2F;the-llm-app-stack-2024-eac28b9dc1e7" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;plain-simple-software&#x2F;the-llm-app-stack-2...</a>
cybereporter大约 1 年前
This is great! Out of curiosity, what&#x27;s the difference between choosing a dedicated vector database vs. a traditional database with vector indices (e.g. pgvector with postgres?
评论 #39432798 未加载