Ghita here, CEO and Co-Founder of ZeroEntropy (YC W25).
We built ZeroEntropy to help developers deploy more accurate retrieval systems, faster. Using our API, you can upload documents of any type, and retrieve accurate and relevant information from your knowledge base, in just a few lines of code.
We just released a new open-weight reranker that outperforms models like Cohere's rerank-3.5, or even Gemini Flash used as a reranker. You can check out the performance here.
At ZeroEntropy we also take the same ELO-based system we used to train our rerankers, use it annotate your data so that you have observability and clear retrieval metrics!
If you want us to bring an extremely robust evaluation framework to your retrieval pipeline message us at founders@zeroentropy.dev or join our slack!
Theoretically I can guess at the likely positive results but theres an upfront friction to witness those results and I'm not sure of the ROI. It would be good to see a side by side comparison, The POST requests in the docs are good but I imagine something even easier to show the comparative value would be very compelling.
Congrats on YC W25. The retrieval accuracy problem is definitely real for developers building RAG systems. How does ZeroEntropy handle edge cases with complex document structures? @ghita_houir_alami
Report
this is actually something we could use, managing our search hasn't been as easy as we thought
ZeroEntropy (YC W25)
Hey guys!
Ghita here, CEO and Co-Founder of ZeroEntropy (YC W25).
We built ZeroEntropy to help developers deploy more accurate retrieval systems, faster. Using our API, you can upload documents of any type, and retrieve accurate and relevant information from your knowledge base, in just a few lines of code.
We just released a new open-weight reranker that outperforms models like Cohere's rerank-3.5, or even Gemini Flash used as a reranker. You can check out the performance here.
If you want to give it a try, you can check out our documentation, and get an API Key on our dashboard.
Happy Searching!
@ghita_houir_alami
At ZeroEntropy we also take the same ELO-based system we used to train our rerankers, use it annotate your data so that you have observability and clear retrieval metrics!
If you want us to bring an extremely robust evaluation framework to your retrieval pipeline message us at founders@zeroentropy.dev or join our slack!
Congrats for the launch! Upvoted.
As support, I'm giving you a free website audit: you can check there the grammar mistakes, improvements, GDPR/CCPA compliance and it might increase your conversion rates.
https://www.fastaudit.io/audit-report/98bd2f37b3cd24f6543b5299db6490111693c1d085e3cce4f3d172442407af89
Good luck!
ZeroEntropy (YC W25)
@radulepy Thanks a lot! Will check it out!
Velocity
Theoretically I can guess at the likely positive results but theres an upfront friction to witness those results and I'm not sure of the ROI. It would be good to see a side by side comparison, The POST requests in the docs are good but I imagine something even easier to show the comparative value would be very compelling.
ZeroEntropy (YC W25)
@kevin_mcdonagh1 Hey Kevin! Makes sense, for our reranker, you can see a full benchmarking write up on our blog here: https://www.zeroentropy.dev/blog/announcing-zeroentropys-first-reranker
Great work team! Reranker was smooth to integrate and has drastically improved our AI agent's accuracy!
ZeroEntropy (YC W25)
@mahima_manik Thanks a lot! You can check out the docs at https://docs.zeroentropy.dev!
Smoopit
Congrats on YC W25. The retrieval accuracy problem is definitely real for developers building RAG systems. How does ZeroEntropy handle edge cases with complex document structures? @ghita_houir_alami
this is actually something we could use, managing our search hasn't been as easy as we thought