fix formatting

Remove unused `messages` variable from `thinking-generate` example

examples/README.md

@@ -42,6 +42,10 @@ See [ollama/docs/api.md](https://github.com/ollama/ollama/blob/main/docs/api.md)
 - [list.py](list.py)
 
 
+### Ollama Show - Display model properties and capabilities
+- [show.py](show.py)
+
+
 ### Ollama ps - Show model status with CPU/GPU usage
 - [ps.py](ps.py)
 
@@ -55,7 +59,12 @@ Requirement: `pip install tqdm`
 - [create.py](create.py) 
 
 
-
 ### Ollama Embed - Generate embeddings with a model
 - [embed.py](embed.py)
 
+
+### Thinking - Enable thinking mode for a model
+- [thinking.py](thinking.py)
+
+### Thinking (generate) - Enable thinking mode for a model
+- [thinking-generate.py](thinking-generate.py)

examples/list.py

@@ -4,6 +4,7 @@ response: ListResponse = list()
 
 for model in response.models:
   print('Name:', model.model)
+  print('  Capabilities:', model.capabilities)
   print('  Size (MB):', f'{(model.size.real / 1024 / 1024):.2f}')
   if model.details:
     print('  Format:', model.details.format)

examples/show.py

@@ -0,0 +1,12 @@
+from ollama import ShowResponse, show
+
+response: ShowResponse = show('gemma3')
+print('Model Information:')
+print(f'Modified at:   {response.modified_at}')
+print(f'Template:      {response.template}')
+print(f'Modelfile:     {response.modelfile}')
+print(f'License:       {response.license}')
+print(f'Details:       {response.details}')
+print(f'Model Info:    {response.modelinfo}')
+print(f'Parameters:    {response.parameters}')
+print(f'Capabilities:  {response.capabilities}')

examples/thinking-generate.py

@@ -0,0 +1,6 @@
+from ollama import generate
+
+response = generate('deepseek-r1', 'why is the sky blue', think=True)
+
+print('Thinking:\n========\n\n' + response.thinking)
+print('\nResponse:\n========\n\n' + response.response)

examples/thinking.py

@@ -0,0 +1,13 @@
+from ollama import chat
+
+messages = [
+  {
+    'role': 'user',
+    'content': 'What is 10 + 23?',
+  },
+]
+
+response = chat('deepseek-r1', messages=messages, think=True)
+
+print('Thinking:\n========\n\n' + response.message.thinking)
+print('\nResponse:\n========\n\n' + response.message.content)

ollama/_client.py

@@ -190,6 +190,7 @@ class Client(BaseClient):
     template: str = '',
     context: Optional[Sequence[int]] = None,
     stream: Literal[False] = False,
+    think: Optional[bool] = None,
     raw: bool = False,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -208,6 +209,7 @@ class Client(BaseClient):
     template: str = '',
     context: Optional[Sequence[int]] = None,
     stream: Literal[True] = True,
+    think: Optional[bool] = None,
     raw: bool = False,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -225,6 +227,7 @@ class Client(BaseClient):
     template: Optional[str] = None,
     context: Optional[Sequence[int]] = None,
     stream: bool = False,
+    think: Optional[bool] = None,
     raw: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -253,6 +256,7 @@ class Client(BaseClient):
         template=template,
         context=context,
         stream=stream,
+        think=think,
         raw=raw,
         format=format,
         images=list(_copy_images(images)) if images else None,
@@ -270,6 +274,7 @@ class Client(BaseClient):
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[False] = False,
+    think: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -283,6 +288,7 @@ class Client(BaseClient):
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[True] = True,
+    think: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -295,6 +301,7 @@ class Client(BaseClient):
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: bool = False,
+    think: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -341,6 +348,7 @@ class Client(BaseClient):
         messages=list(_copy_messages(messages)),
         tools=list(_copy_tools(tools)),
         stream=stream,
+        think=think,
         format=format,
         options=options,
         keep_alive=keep_alive,
@@ -694,6 +702,7 @@ class AsyncClient(BaseClient):
     template: str = '',
     context: Optional[Sequence[int]] = None,
     stream: Literal[False] = False,
+    think: Optional[bool] = None,
     raw: bool = False,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -712,6 +721,7 @@ class AsyncClient(BaseClient):
     template: str = '',
     context: Optional[Sequence[int]] = None,
     stream: Literal[True] = True,
+    think: Optional[bool] = None,
     raw: bool = False,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -729,6 +739,7 @@ class AsyncClient(BaseClient):
     template: Optional[str] = None,
     context: Optional[Sequence[int]] = None,
     stream: bool = False,
+    think: Optional[bool] = None,
     raw: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     images: Optional[Sequence[Union[str, bytes, Image]]] = None,
@@ -756,6 +767,7 @@ class AsyncClient(BaseClient):
         template=template,
         context=context,
         stream=stream,
+        think=think,
         raw=raw,
         format=format,
         images=list(_copy_images(images)) if images else None,
@@ -773,6 +785,7 @@ class AsyncClient(BaseClient):
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[False] = False,
+    think: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -786,6 +799,7 @@ class AsyncClient(BaseClient):
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: Literal[True] = True,
+    think: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -798,6 +812,7 @@ class AsyncClient(BaseClient):
     *,
     tools: Optional[Sequence[Union[Mapping[str, Any], Tool, Callable]]] = None,
     stream: bool = False,
+    think: Optional[bool] = None,
     format: Optional[Union[Literal['', 'json'], JsonSchemaValue]] = None,
     options: Optional[Union[Mapping[str, Any], Options]] = None,
     keep_alive: Optional[Union[float, str]] = None,
@@ -845,6 +860,7 @@ class AsyncClient(BaseClient):
         messages=list(_copy_messages(messages)),
         tools=list(_copy_tools(tools)),
         stream=stream,
+        think=think,
         format=format,
         options=options,
         keep_alive=keep_alive,

ollama/_types.py

@@ -207,6 +207,9 @@ class GenerateRequest(BaseGenerateRequest):
   images: Optional[Sequence[Image]] = None
   'Image data for multimodal models.'
 
+  think: Optional[bool] = None
+  'Enable thinking mode (for thinking models).'
+
 
 class BaseGenerateResponse(SubscriptableBaseModel):
   model: Optional[str] = None
@@ -248,6 +251,9 @@ class GenerateResponse(BaseGenerateResponse):
   response: str
   'Response content. When streaming, this contains a fragment of the response.'
 
+  thinking: Optional[str] = None
+  'Thinking content. Only present when thinking is enabled.'
+
   context: Optional[Sequence[int]] = None
   'Tokenized history up to the point of the response.'
 
@@ -263,6 +269,9 @@ class Message(SubscriptableBaseModel):
   content: Optional[str] = None
   'Content of the message. Response messages contains message fragments when streaming.'
 
+  thinking: Optional[str] = None
+  'Thinking content. Only present when thinking is enabled.'
+
   images: Optional[Sequence[Image]] = None
   """
   Optional list of image data for multimodal models.
@@ -345,6 +354,9 @@ class ChatRequest(BaseGenerateRequest):
   tools: Optional[Sequence[Tool]] = None
   'Tools to use for the chat.'
 
+  think: Optional[bool] = None
+  'Enable thinking mode (for thinking models).'
+
 
 class ChatResponse(BaseGenerateResponse):
   """
@@ -452,6 +464,7 @@ class ListResponse(SubscriptableBaseModel):
     digest: Optional[str] = None
     size: Optional[ByteSize] = None
     details: Optional[ModelDetails] = None
+    capabilities: Optional[List[str]] = None
 
   models: Sequence[Model]
   'List of models.'
@@ -506,6 +519,8 @@ class ShowResponse(SubscriptableBaseModel):
 
   parameters: Optional[str] = None
 
+  capabilities: Optional[List[str]] = None
+
 
 class ProcessResponse(SubscriptableBaseModel):
   class Model(SubscriptableBaseModel):