Open jkomoros opened 1 year ago
The completion API sets a limit on the length of (input + output). The longer the context, the shorter the completion must be.
There's a balance between passing a lot of context to summarize and getting a long result.
It should be possible to configure that split in ask.
ask
Originally noticed while thinking about #14
sample.client
Consider tiktoken to measure token length.
The completion API sets a limit on the length of (input + output). The longer the context, the shorter the completion must be.
There's a balance between passing a lot of context to summarize and getting a long result.
It should be possible to configure that split in
ask
.Originally noticed while thinking about #14