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。

Show HN: Chat-focused RAG with automated memory management

4 点作者 eskibars超过 1 年前

2 条评论

eskibars超过 1 年前
Hi HN!<p>I lead product at Vectara. Yesterday, we launched Vectara Chat, which is a set of APIs to help organizations combine chatbots with RAG (Retrieval Augmented Generation). One of the most common things we&#x27;ve heard from the community of users trying to build chatbots is that they hallucinate (and hence the release of our hallucination evaluation model: <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;vectara&#x2F;hallucination_evaluation_model" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;vectara&#x2F;hallucination_evaluation_mode...</a>). One of the things we&#x27;ve realized when working with customers on RAG systems (especially multi-turn) is that a lot of overemphasis of effort into &quot;which model,&quot; &quot;which vector DB,&quot; and so on, but then miss incredibly important things like &quot;how do you make sure things like keywords -- non semantic-based bits of context -- influence results&quot; and &quot;how do I prompt engineer&quot; and &quot;how do I rewrite queries appropriately to include history?&quot;<p>This is our attempt to tackle that: you basically just give the API a conversation ID and a turn ID and Vectara will store the history and rewrite the queries using modern LLM techniques to provide the end user with the answer to their question.<p>We&#x27;ve just launched this feature: we started off as a LLM-based semantic search company, and then launched a RAG solution in May 2023, and we think this multi-turn Chat capability is the next stage of our offering. We&#x27;d love to hear feedback from the community!<p>A longer form blog post is at <a href="https:&#x2F;&#x2F;vectara.com&#x2F;blog&#x2F;vectara-chat-revolutionizing-chat-development-for-the-modern-business&#x2F;" rel="nofollow">https:&#x2F;&#x2F;vectara.com&#x2F;blog&#x2F;vectara-chat-revolutionizing-chat-d...</a>
boatbuilder超过 1 年前
So is this like dspy, but has a very specific user flow I.e chat
评论 #39420803 未加载