Blaise Albis-Burdige

Hello everyone, We are thrilled to introduce Impactstack.ai! Impactstack.ai is an AI chatbot for social/environmental impact analysis, providing sustainability metrics and personalized green guidance. We use Semantic Scholar to supply Impactstack with over 200M+ academic papers. Gaia Lens integration offers event-driven articles and data tagged by UNSDG goals and SASB principles. 👥 Who...

Super DOPE! should b #1 imo, looking through docs rn we still bring our own embedding model right?

Nice work! A couple things/questions , for one i noticed a bug in your auth flow, if i go from /spalsh-->(inspire me) --> login-->signup-->fill out flow --> confirm email --> then hit generate we boot user out of session, maybe some auth provider funkiness combined with render variability? Otherwise feels fast and clean. 2nd Q: How are you searching the whois DB? I would be...

nice work! i actually saw someone begging for this on twitter recently, is the embedding index have text and image embeddings? like could i look for dog screenshots (if not this would be cool feature) or auto foldering by image embeddings!

Woah this is super cool im gonna test it out, been building custom AI routers to match API use cases, quick Q, is there any limit on number of endpoints allowed in the schema? like could the copilot handle 100 endpoints and routing those correctly? If so whats the upper limit on breadth of API ?

Wish there was a free demo, like the idea, a lil apprehensive. Imagine ur product manager sending passive aggressive memes about that sprint that didn't go as planned.

Promising idea but couple comments : as someone whos constantly jumping cloud providers a comparable table to GCP, AWS and Azure would really help me understand your differentiation. I'm not sure I would need this product as those cloud services seem to do the trick but if I could use nokori to write in one DB and have it deploy across multiple cloud providers in a harmonized way I would be...

Great idea, I guess couple questions before I try it out: Are you using a foundation model and prompt templates or your own model, w data like this as a consumer im a lil apprehensive about pumping my med data into a non-encrypted system. How do prevent hallucination also? Is there an out of training knowledge base or r u leaning on training set for inference. Looks slick tho nice work!

Super dope! I was looking for this hype to implement in a product im working on and not have to build this stack myself. Cheers will circle back once I use it a bit more