Assisstant prefill support

"messages": [

{

"role": "assistant",

"content": "",

"reasoning_content": "The reasoning in the response will start with this"

}

],

When messages end with an assistant message, it should be used to prefill the generated response, which is standard behavior for self hosted llama.cpp.

Please authenticate to join the conversation.

Upvoters
Status

New Submission

Board
💡

Feature Requests

Tags

API

Date

1 day ago

Subscribe to request

Get notified by email when there are changes.