Oh that's odd... are you accessing the web app through a regular browser like chrome, safari, mozilla, etc. ? I know the Google SSO does not work if you access the web app through something like Facebook's built in browser.
I've been living in Montreal now for the last couple of years and have struggled to find people to practice speaking French with, so I created a web app to talk with an AI to improve my conversational skills [1]. I launched a few months ago and am seeing a little bit under $500/month in revenue so far.
I initially started by offering the service for free, but it eventually became too expensive to handle by myself. I then decided to switch to a paid and free tier and by that point I had amassed enough of a user base that a decent handful signed up to the paid tier. I optimized for user growth > revenue in the beginning because I kept thinking, "if people are not going to use this for free then they surely are not going to pay for it".
Anyhow, it's called Proseable and it also supports English, Italian, German, and Spanish!
Absolutely, what I've noticed is that the current apps are great for beginners but after a certain point the only way to improve your ability to speak a new language is to well... speak it. I built Proseable to help people move beyond the generic how to order a coffee or ask to go to the bathroom, and have more meaningful conversations in the real world. Check it out!
Maybe I'm misunderstanding what exactly a vector db is.
Let's say you have a chatbot and stored in its database is the usual info like session id, timestamp, message etc. To "vectorize" this db then would be to vectorize all the messages. Is this too simple an understanding?
Once the db has been vectorized then we can do semantic search on the messages and create more informative graphs based off the semantic similarity for messages within a given timeframe or other criteria.
I've always wondered, what determines which planet or solar system to observe? I guess I'd like to think we have a list of solar systems that are most likely to hold life and simply go down it from most likely to least likely but it surely can't be that reductive.
Lots of focus on RAG here, and rightfully so, but I feel an overlooked benefit to vector databases is the novel visualizations they provide. To be able to plot qualitative data onto a 2d graph with tsne reduction provides a new method with which to draw insights from. I think many companies would benefit from such a visualization tool, especially those in qualitative research.
I think there may be a typo with the "Restart" button. An interesting project though! I'm curious, where do you see this going next? Would it be to have the AI execute the plan?