Cocoon
p/cocoon-7
Semantically profiles your data using LLMs
Zachary Huang
Cocoon — Semantically profiles your data using LLMs
3
We profile tables: this is the first step to understanding the table and identifying any anomalies. Many small decisions require semantics by LLMs. For example, an age of 100 is acceptable, but -1 is impossible! Upload a CSV and we will send back the profile.
Replies
Best
Zachary Huang
Maker
📌
Hi Product Hunt Community! 👋 I'm a PhD working on applying LLMs to data, and I'm the builder of Cocoon. The problem we solve involves profiling tables: this is the initial step where you need to understand the table and identify any anomalies. 📊 During the process, many small decisions require semantic understanding. For example, missing values are normal for 'deathdate' (still alive) but abnormal for 'name.' For outliers, 100 for ages is fine, but some are -1, which is impossible! We use LLMs to semantically understand your tables and detect anomalies. 🔍 You can try it by uploading a CSV, and we will email back the profile. Check out our open-source project for more example profiles: https://github.com/Cocoon-Data-T... Let me know your feedback. Thanks! 🙏
John Wheeler
This is seriously impressive. Is this out of academia? It doesn't look like just any old GPT wrapper. The screenshots are professional and the UI looks clean and well organized. Best of luck with your launch!
Zachary Huang
@john_wheeler2 Yes! The paper has been accepted at HILDA: https://arxiv.org/abs/2404.12552. Thank you!