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。

Interview with David Garnitz, Creator of VectorFlow

2 点作者 CShorten超过 1 年前
VectorFlow (open-sourced on GH) is a new tool for ingesting data into Vector Databases such as Weaviate! There is quite an interesting End-to-End stack emerging at the ingestion layer, from:<p>- Retrieving data from misc. sources such as Slack, Salesforce, GitHub, Google Drive, Notion, ...<p>- To then Chunking the Text (maybe with the use of Visual Document Layout parsers like what Unstructured is imagining)<p>- Extracting Metadata potentially (say the &quot;age&quot; of an NBA player as in the Evaporate-Code+ research)<p>- Then sending this data off to embedding model inference and unpacking that can of worms from inference acceleration to load balancing<p>- Finally -- importing the vectors themselves to Weaviate!<p>I learned so much from this conversation, I really hope you enjoy listening and please check out VectorFlow!<p>https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=efAvOsO8Gik

暂无评论

暂无评论