highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 21:17:41 +01:00
Code Issues Packages Projects Releases Wiki Activity

Reapply "add truncate and shift parameters" (#12582)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-10-11 16:06:14 -07:00
committed by GitHub
parent 5db8a818a1
commit 6544e14735
8 changed files with 298 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
api/types.go
View File

@@ -106,6 +106,14 @@ type GenerateRequest struct {
// before this option was introduced)
Think *ThinkValue `json:"think,omitempty"`
// Truncate is a boolean that, when set to true, truncates the chat history messages
// if the rendered prompt exceeds the context length limit.
Truncate *bool `json:"truncate,omitempty"`
// Shift is a boolean that, when set to true, shifts the chat history
// when hitting the context length limit instead of erroring.
Shift *bool `json:"shift,omitempty"`
// DebugRenderOnly is a debug option that, when set to true, returns the rendered
// template instead of calling the model.
DebugRenderOnly bool `json:"_debug_render_only,omitempty"`
@@ -140,6 +148,14 @@ type ChatRequest struct {
// for supported models.
Think *ThinkValue `json:"think,omitempty"`
// Truncate is a boolean that, when set to true, truncates the chat history messages
// if the rendered prompt exceeds the context length limit.
Truncate *bool `json:"truncate,omitempty"`
// Shift is a boolean that, when set to true, shifts the chat history
// when hitting the context length limit instead of erroring.
Shift *bool `json:"shift,omitempty"`
// DebugRenderOnly is a debug option that, when set to true, returns the rendered
// template instead of calling the model.
DebugRenderOnly bool `json:"_debug_render_only,omitempty"`