Transfers failing (same prompt, other transfers wo...
# support
f
call ID 01211784-d773-4044-9687-bf060238d764 All calls are transferred to the one same number. I have different types of calls specified in the prompt. This problem is primarily one specific type of call and the others don't seem to have the problem transferring.
s
disable the semanticCache
it will work.
also use temp 0.3
f
Where is semanticCache?
s
basically it store some frequent use data
and doesn't really send it to llm
due to this transfer might fail
f
The transfer is always to the same number so I don't have to worry about multiple numbers. There are different reasons for the transfer but I consistently tested the same scenario over and over again and it always fails and then I immediately test a different scenario and it succeeds then I change back and it fails again always the similar scenarios. Then I changed the llm model and it worked much much better. I changed from open AI chat GPT 40 mini, to Llama 3.1 70b on groc, And it worked so much better. Sometimes it transferred a little bit too much. I will test other models and I will test very slight variations in the prompt and many different scenarios. When I thoroughly understand what is going on or think I understand, I will post the solution here.
I think there is language in the Vapi system prompt regarding tool use that is unclear and contributing to these kinds of problems.
I switched to a more expensive frontier model (4o) and it works better, but I have to pay 7 cents more per minute.
4o mini failed, 4o succeeded.
s
You can change the tool description as well
but you will need to use API for it.
3 Views