Increase input character limit and output token limit for Kagi Assistant

mackid1993

Same. I'd rather just use quick answer and use ChatGPT for real AI queries. The limits on assistant make it useless for rewriting a large word document or debugging a large amount of code.
I would gladly switch back if Assistant were on par with ChatGPT.

mackid1993

I've also had responses cut off because the output was over 1000 tokens, just like cut off mid sentence.

xeophon

Agreed as well. It is counterintuitive (imo) to show the context size in the comparison page when it is usable

mackid1993

I think the most important thing is it's just increased but on par with ChatGPT, otherwise I can't see myself paying $25/month for Kagi. I'd rather pay $10 and get awesome search and pay $20 to OpenAI and get awesome AI.

I'd rather pay $25 to Kagi and get awesome search AND awesome AI and support the good guys in the process.

doskagi

What is the limit now?

Luis

doskagi the input character limit are 40,000 chars. cc @Thibaultmol

Thibaultmol

Luis might be good to also know the token limit.

And have both mentioned in the docs

doskagi

Luis Amazing, thank you! Does this apply to attached documents too?

Thibaultmol

Honestly It'd like to see this be opened again, because the limit should be way higher still in my opinion. def considering models like Gemini have 1M context windows cc @Luis

doskagi

Thibaultmol Agreed!

doskagi

My understanding is that when making an API call, the Assistant uploads the entire chat at every instance. Does this mean that the character/token limit is reduced with each additional query in the same chat, given previous queries (with related uploaded documents) would need to be re-sent?