Merge pull request #553 from ollama/drifkin/thinking-levels

add support for 'high'/'medium'/'low' think values

Author: drifkin

examples/README.md

@@ -73,3 +73,6 @@ Requirement: `pip install tqdm`
 
 ### Thinking (generate) - Enable thinking mode for a model
 - [thinking-generate.py](thinking-generate.py)
+
+### Thinking (levels) - Choose the thinking level
+- [thinking-levels.py](thinking-generate.py)

examples/thinking-levels.py

@@ -0,0 +1,26 @@
+from ollama import chat
+
+
+def heading(text):
+  print(text)
+  print('=' * len(text))
+
+
+messages = [
+  {'role': 'user', 'content': 'What is 10 + 23?'},
+]
+
+# gpt-oss supports 'low', 'medium', 'high'
+levels = ['low', 'medium', 'high']
+for i, level in enumerate(levels):
+  response = chat('gpt-oss:20b', messages=messages, think=level)
+
+  heading(f'Thinking ({level})')
+  print(response.message.thinking)
+  print('\n')
+  heading('Response')
+  print(response.message.content)
+  print('\n')
+  if i < len(levels) - 1:
+    print('-' * 20)
+    print('\n')

ollama/_client.py

@@ -274,7 +274,7 @@ def chat(
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[False] = False,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -288,7 +288,7 @@ def chat(
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[True] = True,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -301,7 +301,7 @@ def chat(
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: bool = False,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -702,7 +702,7 @@ async def generate(
     template: str = '',
     context: Optional[Sequence[int]] = None,
     stream: Literal[False] = False,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     raw: bool = False,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -721,7 +721,7 @@ async def generate(
     template: str = '',
     context: Optional[Sequence[int]] = None,
     stream: Literal[True] = True,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     raw: bool = False,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -739,7 +739,7 @@ async def generate(
     template: Optional[str] = None,
     context: Optional[Sequence[int]] = None,
     stream: bool = False,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     raw: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -785,7 +785,7 @@ async def chat(
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[False] = False,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -799,7 +799,7 @@ async def chat(
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[True] = True,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -812,7 +812,7 @@ async def chat(
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: bool = False,
-    think: Optional[bool] = None,
+    think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,

ollama/_types.py

@@ -207,7 +207,7 @@ class GenerateRequest(BaseGenerateRequest):
   images: Optional[Sequence[Image]] = None
   'Image data for multimodal models.'
 
-  think: Optional[bool] = None
+  think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None
   'Enable thinking mode (for thinking models).'
 
 
@@ -357,7 +357,7 @@ def serialize_model(self, nxt):
   tools: Optional[Sequence[Tool]] = None
   'Tools to use for the chat.'
 
-  think: Optional[bool] = None
+  think: Optional[Union[bool, Literal['low', 'medium', 'high']]] = None
   'Enable thinking mode (for thinking models).'