Concept
continuationToken
A chunked-response parameter added to the Google Generate Content API that allows model output to be read in chunks of 64k. It serves as an interim means of supporting the extremely long output capability of Long Decode.
Timeline (last 90 days)
Oct 14
Google's Generate Content API has added a continuationToken parameter, allowing responses to be read in chunks of 64k.
Unverified50%
Oct 14
LangChainJS will support the continuationToken approach first, but the maintainer positions it as a temporary transitional solution.
Unverified50%