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: Fuzzy deduplicate any CSV using vector embeddings

5 点作者 remolacha6 个月前
I made an app to fuzzy-deduplicate my Google Sheets and CRM records<p>- No manual configuration required<p>- Works out-of-the-box on most data types (ex. people, companies, product catalog)<p>Implementation details:<p>- Embeds records using an E5-family model<p>- Performs similarity search using DuckDB w&#x2F; vector similarity extension<p>- Does last-mile comparison and merges duplicates using Claude<p>Demo video: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;7mZ0kdwXBwM" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;7mZ0kdwXBwM</a><p>Github repo (Apache 2.0 licensed): <a href="https:&#x2F;&#x2F;github.com&#x2F;SnowPilotOrg&#x2F;dedupe_it">https:&#x2F;&#x2F;github.com&#x2F;SnowPilotOrg&#x2F;dedupe_it</a><p>Background story: My company has a table for tracking leads, which includes website visitors, demo form submissions, app signups, and manual entries. It’s full of duplicates. And writing formulas to merge those dupes has been a massive PITA.<p>I figured that an LLM could handle any data shape and give me a way to deal with tricky custom rules like “treat international subsidiaries as distinct from their parent company”.<p>The challenging thing was avoiding an NxN comparison matrix. The solution I came up with was first narrowing down our search space using vector embeddings + semantic similarity search, and then using a generative LLM only to compare a few nearest neighbors and merge.<p>Some cool attributes of this approach:<p>- Can work incrementally (no reprocessing the entire dataset)<p>- Allows processing all records in parallel<p>- Composes with deterministic dedupe rules<p>Lmk any feedback on how to make this better!

2 条评论

K0IN6 个月前
This is very interesting, i was building something similar, but i used <a href="https:&#x2F;&#x2F;github.com&#x2F;K0IN&#x2F;string-embed">https:&#x2F;&#x2F;github.com&#x2F;K0IN&#x2F;string-embed</a> (embeddings based on a distance function - Levenshtein in my case) to generate embeddings, for deterministic matching.<p>I will follow your project, im interested in your ann search speeds :)
评论 #42064782 未加载
DigiFreeze6 个月前
high-key useful! Are you thinking of making a Google Sheets extension? How are you thinking about data privacy? Any plans to make a local-only app?
评论 #42064814 未加载