matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 08:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

add thinking support to the api and cli (#10584)

Browse Source 
- Both `/api/generate` and `/api/chat` now accept a `"think"`
  option that allows specifying whether thinking mode should be on or
  not
- Templates get passed this new option so, e.g., qwen3's template can
  put `/think` or `/no_think` in the system prompt depending on the
  value of the setting
- Models' thinking support is inferred by inspecting model templates.
  The prefix and suffix the parser uses to identify thinking support is
  also automatically inferred from templates
- Thinking control & parsing is opt-in via the API to prevent breaking
  existing API consumers. If the `"think"` option is not specified, the
  behavior is unchanged from previous versions of ollama
- Add parsing for thinking blocks in both streaming/non-streaming mode
  in both `/generate` and `/chat`
- Update the CLI to make use of these changes. Users can pass `--think`
  or `--think=false` to control thinking, or during an interactive
  session they can use the commands `/set think` or `/set nothink`
- A `--hidethinking` option has also been added to the CLI. This makes
  it easy to use thinking in scripting scenarios like
  `ollama run qwen3 --think --hidethinking "my question here"` where you
  just want to see the answer but still want the benefits of thinking
  models
This commit is contained in:
Devon Rifkin
2025-05-28 19:38:52 -07:00
committed by GitHub
parent aa25aff10d
commit 5f57b0ef42
17 changed files with 1195 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
server/prompt.go
View File

@@ -19,7 +19,7 @@ type tokenizeFunc func(context.Context, string) ([]int, error)
// chatPrompt accepts a list of messages and returns the prompt and images that should be used for the next chat turn.
// chatPrompt truncates any messages that exceed the context window of the model, making sure to always include 1) the
// latest message and 2) system messages
func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.Options, msgs []api.Message, tools []api.Tool) (prompt string, images []llm.ImageData, _ error) {
func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.Options, msgs []api.Message, tools []api.Tool, think *bool) (prompt string, images []llm.ImageData, _ error) {
var system []api.Message
// TODO: Ideally we would compute this from the projector metadata but some pieces are implementation dependent
@@ -41,8 +41,12 @@ func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.
}
}
thinkVal := false
if think != nil {
thinkVal = *think
}
var b bytes.Buffer
if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[i:]...), Tools: tools}); err != nil {
if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[i:]...), Tools: tools, Think: thinkVal, IsThinkSet: think != nil}); err != nil {
return "", nil, err
}
@@ -96,7 +100,11 @@ func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.
// truncate any messages that do not fit into the context window
var b bytes.Buffer
if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[currMsgIdx:]...), Tools: tools}); err != nil {
thinkVal := false
if think != nil {
thinkVal = *think
}
if err := m.Template.Execute(&b, template.Values{Messages: append(system, msgs[currMsgIdx:]...), Tools: tools, Think: thinkVal, IsThinkSet: think != nil}); err != nil {
return "", nil, err
}