KTextAddons
#include <ollamareply.h>
Public Attributes | |
std::chrono::nanoseconds | duration |
std::chrono::nanoseconds | loadDuration |
std::chrono::nanoseconds | promptEvalDuration |
int | promptEvalTokenCount |
int | tokenCount |
std::chrono::nanoseconds | totalDuration |
Detailed Description
The OllamaReplyInfo class represents information about a reply from an LLM.
When an LLM generates a completion, the server generally will return some information about the completion, including the duration of the completion, the number of tokens received, and the duration of the prompt evaluation. This struct encapsulates such information. If any one of these fields is not available, it will be set to its default value.
Definition at line 20 of file ollamareply.h.
Member Data Documentation
◆ duration
std::chrono::nanoseconds OllamaReplyInfo::duration |
The time spent generating the reply.
Definition at line 37 of file ollamareply.h.
◆ loadDuration
std::chrono::nanoseconds OllamaReplyInfo::loadDuration |
The time spent loading the model.
Definition at line 25 of file ollamareply.h.
◆ promptEvalDuration
std::chrono::nanoseconds OllamaReplyInfo::promptEvalDuration |
The time spent evaluating the prompt.
Definition at line 31 of file ollamareply.h.
◆ promptEvalTokenCount
int OllamaReplyInfo::promptEvalTokenCount |
The number of tokens in the prompt.
Definition at line 28 of file ollamareply.h.
◆ tokenCount
int OllamaReplyInfo::tokenCount |
The number of tokens in the reply.
Definition at line 34 of file ollamareply.h.
◆ totalDuration
std::chrono::nanoseconds OllamaReplyInfo::totalDuration |
The total time from when the request was received by the server to when the reply was returned.
Definition at line 22 of file ollamareply.h.
The documentation for this struct was generated from the following file:
Documentation copyright © 1996-2025 The KDE developers.
Generated on Fri Apr 11 2025 11:48:13 by doxygen 1.13.2 written by Dimitri van Heesch, © 1997-2006
KDE's Doxygen guidelines are available online.