After adding your own data and having ai quota, now you think about how it works.
let's made up a scenario where you have 3 data, each is around 1.500 characters length.
every data have their own score.
When you add any data, fonnte under the hood is generating and saving it's score.
around 1.500 characters on your data cost 1 ai quota.
Incoming chat process & cost
when a chat is coming, fonnte will give it a score, then compare it with all of your data's score.
the highest score relative to the question will be choosen.
but the data then will once again compared to the current chat and previous chat history.
it will compared once again with complete chats history.
then we have another highest score data.
after that, we will compare both highest data.
if they're not equal, then both of them is relevant to the chat and necessary to answer the question.
so the cost now is not just 1, but 2 due to additional data.
if the data is short enough and the total is less than 2000-2500 characters, your cost will more likely to be just 1.
but 2 might not the final cost you'll be charged.
there is also "hidden" cost that may occur due to your ai behaviour.
you may use chat history to make the chat flow is smooth, more like chatgpt behaviour.
this behaviour cost you more, can be around 1-2 additional ai quota depend on the chat history length.
if you do not use history, your ai might not remember previous chat, so it will behave like new chat.
this behaviour will not add cost for incoming data and the final incoming cost more likely to be 2 at most of the case.
Outgoing chat & cost
for response length, typically it will cost just 1.
but it the response is too long, it might get 2 or 3.
as long as we tried during development, most of our response cost 1 ai quota and rarely got 2.
it's including our lengthly code generation for our api example.
your outgoing chat cost will more likely to be 1 at most of the case.
Conclusion
so, in the end, your total cost is typically 2-3 ai quota.
from the incoming cost is typically 1-2 a quota.
while the outgoung cost is typically 1 quota.
but still, might go up to 5 ai quota due to 1-4 incoming data, and 1 outgoing data.