π¨BREAKING: Uber launches QueryGPT
Natural Language to SQL Using Generative AI.
1. Uber has recently released QueryGPT inside of their SQL operations:
QueryGPT uses large language models (LLM), vector databases, and similarity search to generate complex queries from English questions that are provided by the user as input.
QueryGPT uses large language models (LLM), vector databases, and similarity search to generate complex queries from English questions that are provided by the user as input.
2. Operational Impact:
Uber's data platform handles 1,200,000 queries each month.
Before QueryGPT, Uber's Operations (3000 employees), spent 10+ minutes per SQL query.
After QueryGPT, average query is 3 minutes, with fewer errors. 3X speedup.
Uber's data platform handles 1,200,000 queries each month.
Before QueryGPT, Uber's Operations (3000 employees), spent 10+ minutes per SQL query.
After QueryGPT, average query is 3 minutes, with fewer errors. 3X speedup.
Full Article: uber.com/en-TW/blog/queβ¦
I have one more thing before you go.
If you want to become a generative AI data scientist in 2025 ($200,000 career), then I'd like to help:
I have one more thing before you go.
If you want to become a generative AI data scientist in 2025 ($200,000 career), then I'd like to help:
On Wednesday, November 12th, I'm sharing one of my best AI Projects:
οΏΌοΏΌ
How I built an AI Customer Segmentation Agent with Python
πRegister here (740+ Registered): learn.business-science.io/ai-register
οΏΌοΏΌ
How I built an AI Customer Segmentation Agent with Python
πRegister here (740+ Registered): learn.business-science.io/ai-register
That's a wrap! Over the next 24 days, I'm sharing the 24 concepts that helped me become a data scientist.
If you enjoyed this thread:
1. Follow me @mdancho84 for more of these
2. RT the tweet below to share this thread with your audience
If you enjoyed this thread:
1. Follow me @mdancho84 for more of these
2. RT the tweet below to share this thread with your audience
View Tweet
Generated by Thread Navigator
Press β + S to quick-export