include tool calls

* Add type overloads for chat() method in _client.py

* Overloading

* Fix Overload Overlap

* Fix async chat

* Lint

* Reverse

---------

Co-authored-by: Simon Ottenhaus <simon.ottenhaus@kenbun.de>

README.md

@@ -1,6 +1,6 @@
 # Ollama Python Library
 
-The Ollama Python library provides the easiest way to integrate Python 3.8+ projects with [Ollama](https://github.com/jmorganca/ollama).
+The Ollama Python library provides the easiest way to integrate Python 3.8+ projects with [Ollama](https://github.com/ollama/ollama).
 
 ## Install
 
@@ -12,7 +12,7 @@ pip install ollama
 
 ```python
 import ollama
-response = ollama.chat(model='llama2', messages=[
+response = ollama.chat(model='llama3', messages=[
   {
     'role': 'user',
     'content': 'Why is the sky blue?',
@@ -29,7 +29,7 @@ Response streaming can be enabled by setting `stream=True`, modifying function c
 import ollama
 
 stream = ollama.chat(
-    model='llama2',
+    model='llama3',
     messages=[{'role': 'user', 'content': 'Why is the sky blue?'}],
     stream=True,
 )
@@ -40,18 +40,18 @@ for chunk in stream:
 
 ## API
 
-The Ollama Python library's API is designed around the [Ollama REST API](https://github.com/jmorganca/ollama/blob/main/docs/api.md)
+The Ollama Python library's API is designed around the [Ollama REST API](https://github.com/ollama/ollama/blob/main/docs/api.md)
 
 ### Chat
 
 ```python
-ollama.chat(model='llama2', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
+ollama.chat(model='llama3', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
 ```
 
 ### Generate
 
 ```python
-ollama.generate(model='llama2', prompt='Why is the sky blue?')
+ollama.generate(model='llama3', prompt='Why is the sky blue?')
 ```
 
 ### List
@@ -63,14 +63,14 @@ ollama.list()
 ### Show
 
 ```python
-ollama.show('llama2')
+ollama.show('llama3')
 ```
 
 ### Create
 
 ```python
 modelfile='''
-FROM llama2
+FROM llama3
 SYSTEM You are mario from super mario bros.
 '''
 
@@ -80,31 +80,37 @@ ollama.create(model='example', modelfile=modelfile)
 ### Copy
 
 ```python
-ollama.copy('llama2', 'user/llama2')
+ollama.copy('llama3', 'user/llama3')
 ```
 
 ### Delete
 
 ```python
-ollama.delete('llama2')
+ollama.delete('llama3')
 ```
 
 ### Pull
 
 ```python
-ollama.pull('llama2')
+ollama.pull('llama3')
 ```
 
 ### Push
 
 ```python
-ollama.push('user/llama2')
+ollama.push('user/llama3')
 ```
 
 ### Embeddings
 
 ```python
-ollama.embeddings(model='llama2', prompt='The sky is blue because of rayleigh scattering')
+ollama.embeddings(model='llama3', prompt='The sky is blue because of rayleigh scattering')
+```
+
+### Ps
+
+```python
+ollama.ps()
 ```
 
 ## Custom client
@@ -117,7 +123,7 @@ A custom client can be created with the following fields:
 ```python
 from ollama import Client
 client = Client(host='http://localhost:11434')
-response = client.chat(model='llama2', messages=[
+response = client.chat(model='llama3', messages=[
   {
     'role': 'user',
     'content': 'Why is the sky blue?',
@@ -133,7 +139,7 @@ from ollama import AsyncClient
 
 async def chat():
   message = {'role': 'user', 'content': 'Why is the sky blue?'}
-  response = await AsyncClient().chat(model='llama2', messages=[message])
+  response = await AsyncClient().chat(model='llama3', messages=[message])
 
 asyncio.run(chat())
 ```
@@ -146,7 +152,7 @@ from ollama import AsyncClient
 
 async def chat():
   message = {'role': 'user', 'content': 'Why is the sky blue?'}
-  async for part in await AsyncClient().chat(model='llama2', messages=[message], stream=True):
+  async for part in await AsyncClient().chat(model='llama3', messages=[message], stream=True):
     print(part['message']['content'], end='', flush=True)
 
 asyncio.run(chat())

examples/ps/main.py

@@ -0,0 +1,31 @@
+from ollama import ps, pull, chat
+
+response = pull('mistral', stream=True)
+progress_states = set()
+for progress in response:
+  if progress.get('status') in progress_states:
+    continue
+  progress_states.add(progress.get('status'))
+  print(progress.get('status'))
+
+print('\n')
+
+response = chat('mistral', messages=[{'role': 'user', 'content': 'Hello!'}])
+print(response['message']['content'])
+
+print('\n')
+
+response = ps()
+
+name = response['models'][0]['name']
+size = response['models'][0]['size']
+size_vram = response['models'][0]['size_vram']
+
+if size == size_vram:
+  print(f'{name}: 100% GPU')
+elif not size_vram:
+  print(f'{name}: 100% CPU')
+else:
+  size_cpu = size - size_vram
+  cpu_percent = round(size_cpu / size * 100)
+  print(f'{name}: {cpu_percent}% CPU/{100 - cpu_percent}% GPU')

ollama/__init__.py

@@ -29,6 +29,7 @@ __all__ = [
   'list',
   'copy',
   'show',
+  'ps',
 ]
 
 _client = Client()
@@ -43,3 +44,4 @@ delete = _client.delete
 list = _client.list
 copy = _client.copy
 show = _client.show
+ps = _client.ps

ollama/_client.py

@@ -7,10 +7,11 @@ import platform
 import urllib.parse
 from os import PathLike
 from pathlib import Path
+from copy import deepcopy
 from hashlib import sha256
 from base64 import b64encode, b64decode
 
-from typing import Any, AnyStr, Union, Optional, Sequence, Mapping, Literal
+from typing import Any, AnyStr, Union, Optional, Sequence, Mapping, Literal, overload
 
 import sys
 
@@ -96,6 +97,40 @@ class Client(BaseClient):
   ) -> Union[Mapping[str, Any], Iterator[Mapping[str, Any]]]:
     return self._stream(*args, **kwargs) if stream else self._request(*args, **kwargs).json()
 
+  @overload
+  def generate(
+    self,
+    model: str = '',
+    prompt: str = '',
+    system: str = '',
+    template: str = '',
+    context: Optional[Sequence[int]] = None,
+    stream: Literal[False] = False,
+    raw: bool = False,
+    format: Literal['', 'json'] = '',
+    images: Optional[Sequence[AnyStr]] = None,
+    tools: Optional[Sequence[Any]] = None,
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  def generate(
+    self,
+    model: str = '',
+    prompt: str = '',
+    system: str = '',
+    template: str = '',
+    context: Optional[Sequence[int]] = None,
+    stream: Literal[True] = True,
+    raw: bool = False,
+    format: Literal['', 'json'] = '',
+    images: Optional[Sequence[AnyStr]] = None,
+    tools: Optional[Sequence[Any]] = None,
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Iterator[Mapping[str, Any]]: ...
+
   def generate(
     self,
     model: str = '',
@@ -107,6 +142,7 @@ class Client(BaseClient):
     raw: bool = False,
     format: Literal['', 'json'] = '',
     images: Optional[Sequence[AnyStr]] = None,
+    tools: Optional[Sequence[Any]] = None,
     options: Optional[Options] = None,
     keep_alive: Optional[Union[float, str]] = None,
   ) -> Union[Mapping[str, Any], Iterator[Mapping[str, Any]]]:
@@ -135,6 +171,7 @@ class Client(BaseClient):
         'stream': stream,
         'raw': raw,
         'images': [_encode_image(image) for image in images or []],
+        'tools': tools or [],
         'format': format,
         'options': options or {},
         'keep_alive': keep_alive,
@@ -142,6 +179,28 @@ class Client(BaseClient):
       stream=stream,
     )
 
+  @overload
+  def chat(
+    self,
+    model: str = '',
+    messages: Optional[Sequence[Message]] = None,
+    stream: Literal[False] = False,
+    format: Literal['', 'json'] = '',
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  def chat(
+    self,
+    model: str = '',
+    messages: Optional[Sequence[Message]] = None,
+    stream: Literal[True] = True,
+    format: Literal['', 'json'] = '',
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Iterator[Mapping[str, Any]]: ...
+
   def chat(
     self,
     model: str = '',
@@ -164,6 +223,8 @@ class Client(BaseClient):
     if not model:
       raise RequestError('must provide a model')
 
+    messages = deepcopy(messages)
+
     for message in messages or []:
       if not isinstance(message, dict):
         raise TypeError('messages must be a list of Message or dict-like objects')
@@ -206,6 +267,22 @@ class Client(BaseClient):
       },
     ).json()
 
+  @overload
+  def pull(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[False] = False,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  def pull(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[True] = True,
+  ) -> Iterator[Mapping[str, Any]]: ...
+
   def pull(
     self,
     model: str,
@@ -228,6 +305,22 @@ class Client(BaseClient):
       stream=stream,
     )
 
+  @overload
+  def push(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[False] = False,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  def push(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[True] = True,
+  ) -> Iterator[Mapping[str, Any]]: ...
+
   def push(
     self,
     model: str,
@@ -250,11 +343,32 @@ class Client(BaseClient):
       stream=stream,
     )
 
+  @overload
   def create(
     self,
     model: str,
     path: Optional[Union[str, PathLike]] = None,
     modelfile: Optional[str] = None,
+    quantize: Optional[str] = None,
+    stream: Literal[False] = False,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  def create(
+    self,
+    model: str,
+    path: Optional[Union[str, PathLike]] = None,
+    modelfile: Optional[str] = None,
+    quantize: Optional[str] = None,
+    stream: Literal[True] = True,
+  ) -> Iterator[Mapping[str, Any]]: ...
+
+  def create(
+    self,
+    model: str,
+    path: Optional[Union[str, PathLike]] = None,
+    modelfile: Optional[str] = None,
+    quantize: Optional[str] = None,
     stream: bool = False,
   ) -> Union[Mapping[str, Any], Iterator[Mapping[str, Any]]]:
     """
@@ -276,6 +390,7 @@ class Client(BaseClient):
         'name': model,
         'modelfile': modelfile,
         'stream': stream,
+        'quantize': quantize,
       },
       stream=stream,
     )
@@ -334,6 +449,9 @@ class Client(BaseClient):
   def show(self, model: str) -> Mapping[str, Any]:
     return self._request('POST', '/api/show', json={'name': model}).json()
 
+  def ps(self) -> Mapping[str, Any]:
+    return self._request('GET', '/api/ps').json()
+
 
 class AsyncClient(BaseClient):
   def __init__(self, host: Optional[str] = None, **kwargs) -> None:
@@ -378,6 +496,38 @@ class AsyncClient(BaseClient):
     response = await self._request(*args, **kwargs)
     return response.json()
 
+  @overload
+  async def generate(
+    self,
+    model: str = '',
+    prompt: str = '',
+    system: str = '',
+    template: str = '',
+    context: Optional[Sequence[int]] = None,
+    stream: Literal[False] = False,
+    raw: bool = False,
+    format: Literal['', 'json'] = '',
+    images: Optional[Sequence[AnyStr]] = None,
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  async def generate(
+    self,
+    model: str = '',
+    prompt: str = '',
+    system: str = '',
+    template: str = '',
+    context: Optional[Sequence[int]] = None,
+    stream: Literal[True] = True,
+    raw: bool = False,
+    format: Literal['', 'json'] = '',
+    images: Optional[Sequence[AnyStr]] = None,
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> AsyncIterator[Mapping[str, Any]]: ...
+
   async def generate(
     self,
     model: str = '',
@@ -423,6 +573,28 @@ class AsyncClient(BaseClient):
       stream=stream,
     )
 
+  @overload
+  async def chat(
+    self,
+    model: str = '',
+    messages: Optional[Sequence[Message]] = None,
+    stream: Literal[False] = False,
+    format: Literal['', 'json'] = '',
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  async def chat(
+    self,
+    model: str = '',
+    messages: Optional[Sequence[Message]] = None,
+    stream: Literal[True] = True,
+    format: Literal['', 'json'] = '',
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> AsyncIterator[Mapping[str, Any]]: ...
+
   async def chat(
     self,
     model: str = '',
@@ -444,6 +616,8 @@ class AsyncClient(BaseClient):
     if not model:
       raise RequestError('must provide a model')
 
+    messages = deepcopy(messages)
+
     for message in messages or []:
       if not isinstance(message, dict):
         raise TypeError('messages must be a list of strings')
@@ -474,7 +648,7 @@ class AsyncClient(BaseClient):
     prompt: str = '',
     options: Optional[Options] = None,
     keep_alive: Optional[Union[float, str]] = None,
-  ) -> Sequence[float]:
+  ) -> Mapping[str, Sequence[float]]:
     response = await self._request(
       'POST',
       '/api/embeddings',
@@ -488,6 +662,22 @@ class AsyncClient(BaseClient):
 
     return response.json()
 
+  @overload
+  async def pull(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[False] = False,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  async def pull(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[True] = True,
+  ) -> AsyncIterator[Mapping[str, Any]]: ...
+
   async def pull(
     self,
     model: str,
@@ -510,6 +700,22 @@ class AsyncClient(BaseClient):
       stream=stream,
     )
 
+  @overload
+  async def push(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[False] = False,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  async def push(
+    self,
+    model: str,
+    insecure: bool = False,
+    stream: Literal[True] = True,
+  ) -> AsyncIterator[Mapping[str, Any]]: ...
+
   async def push(
     self,
     model: str,
@@ -532,11 +738,32 @@ class AsyncClient(BaseClient):
       stream=stream,
     )
 
+  @overload
   async def create(
     self,
     model: str,
     path: Optional[Union[str, PathLike]] = None,
     modelfile: Optional[str] = None,
+    quantize: Optional[str] = None,
+    stream: Literal[False] = False,
+  ) -> Mapping[str, Any]: ...
+
+  @overload
+  async def create(
+    self,
+    model: str,
+    path: Optional[Union[str, PathLike]] = None,
+    modelfile: Optional[str] = None,
+    quantize: Optional[str] = None,
+    stream: Literal[True] = True,
+  ) -> AsyncIterator[Mapping[str, Any]]: ...
+
+  async def create(
+    self,
+    model: str,
+    path: Optional[Union[str, PathLike]] = None,
+    modelfile: Optional[str] = None,
+    quantize: Optional[str] = None,
     stream: bool = False,
   ) -> Union[Mapping[str, Any], AsyncIterator[Mapping[str, Any]]]:
     """
@@ -558,6 +785,7 @@ class AsyncClient(BaseClient):
         'name': model,
         'modelfile': modelfile,
         'stream': stream,
+        'quantize': quantize,
       },
       stream=stream,
     )
@@ -625,6 +853,10 @@ class AsyncClient(BaseClient):
     response = await self._request('POST', '/api/show', json={'name': model})
     return response.json()
 
+  async def ps(self) -> Mapping[str, Any]:
+    response = await self._request('GET', '/api/ps')
+    return response.json()
+
 
 def _encode_image(image) -> str:
   """

ollama/_types.py

@@ -19,6 +19,9 @@ class BaseGenerateResponse(TypedDict):
   done: bool
   'True if response is complete, otherwise False. Useful for streaming to detect the final response.'
 
+  done_reason: str
+  'Reason for completion. Only present when done is True.'
+
   total_duration: int
   'Total duration in nanoseconds.'
 
@@ -49,6 +52,8 @@ class GenerateResponse(BaseGenerateResponse):
   context: Sequence[int]
   'Tokenized history up to the point of the response.'
 
+  tool_calls: Sequence[Any]
+  'List of tool calls made by the model.'
 
 class Message(TypedDict):
   """
@@ -95,7 +100,6 @@ class Options(TypedDict, total=False):
   numa: bool
   num_ctx: int
   num_batch: int
-  num_gqa: int
   num_gpu: int
   main_gpu: int
   low_vram: bool
@@ -105,8 +109,6 @@ class Options(TypedDict, total=False):
   use_mmap: bool
   use_mlock: bool
   embedding_only: bool
-  rope_frequency_base: float
-  rope_frequency_scale: float
   num_thread: int
 
   # runtime options

poetry.lock

@@ -371,13 +371,13 @@ xmp = ["defusedxml"]
 
 [[package]]
 name = "pluggy"
-version = "1.4.0"
+version = "1.5.0"
 description = "plugin and hook calling mechanisms for python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pluggy-1.4.0-py3-none-any.whl", hash = "sha256:7db9f7b503d67d1c5b95f59773ebb58a8c1c288129a88665838012cfb07b8981"},
-    {file = "pluggy-1.4.0.tar.gz", hash = "sha256:8c85c2876142a764e5b7548e7d9a0e0ddb46f5185161049a79b7e974454223be"},
+    {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
+    {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
 ]
 
 [package.extras]
@@ -386,13 +386,13 @@ testing = ["pytest", "pytest-benchmark"]
 
 [[package]]
 name = "pytest"
-version = "8.1.1"
+version = "8.2.2"
 description = "pytest: simple powerful testing with Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pytest-8.1.1-py3-none-any.whl", hash = "sha256:2a8386cfc11fa9d2c50ee7b2a57e7d898ef90470a7a34c4b949ff59662bb78b7"},
-    {file = "pytest-8.1.1.tar.gz", hash = "sha256:ac978141a75948948817d360297b7aae0fcb9d6ff6bc9ec6d514b85d5a65c044"},
+    {file = "pytest-8.2.2-py3-none-any.whl", hash = "sha256:c434598117762e2bd304e526244f67bf66bbd7b5d6cf22138be51ff661980343"},
+    {file = "pytest-8.2.2.tar.gz", hash = "sha256:de4bb8104e201939ccdc688b27a89a7be2079b22e2bd2b07f806b6ba71117977"},
 ]
 
 [package.dependencies]
@@ -400,21 +400,21 @@ colorama = {version = "*", markers = "sys_platform == \"win32\""}
 exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
 iniconfig = "*"
 packaging = "*"
-pluggy = ">=1.4,<2.0"
+pluggy = ">=1.5,<2.0"
 tomli = {version = ">=1", markers = "python_version < \"3.11\""}
 
 [package.extras]
-testing = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
+dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
 
 [[package]]
 name = "pytest-asyncio"
-version = "0.23.6"
+version = "0.23.7"
 description = "Pytest support for asyncio"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pytest-asyncio-0.23.6.tar.gz", hash = "sha256:ffe523a89c1c222598c76856e76852b787504ddb72dd5d9b6617ffa8aa2cde5f"},
-    {file = "pytest_asyncio-0.23.6-py3-none-any.whl", hash = "sha256:68516fdd1018ac57b846c9846b954f0393b26f094764a28c955eabb0536a4e8a"},
+    {file = "pytest_asyncio-0.23.7-py3-none-any.whl", hash = "sha256:009b48127fbe44518a547bddd25611551b0e43ccdbf1e67d12479f569832c20b"},
+    {file = "pytest_asyncio-0.23.7.tar.gz", hash = "sha256:5f5c72948f4c49e7db4f29f2521d4031f1c27f86e57b046126654083d4770268"},
 ]
 
 [package.dependencies]
@@ -458,28 +458,28 @@ Werkzeug = ">=2.0.0"
 
 [[package]]
 name = "ruff"
-version = "0.4.1"
+version = "0.4.7"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.4.1-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:2d9ef6231e3fbdc0b8c72404a1a0c46fd0dcea84efca83beb4681c318ea6a953"},
-    {file = "ruff-0.4.1-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:9485f54a7189e6f7433e0058cf8581bee45c31a25cd69009d2a040d1bd4bfaef"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d2921ac03ce1383e360e8a95442ffb0d757a6a7ddd9a5be68561a671e0e5807e"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:eec8d185fe193ad053eda3a6be23069e0c8ba8c5d20bc5ace6e3b9e37d246d3f"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:baa27d9d72a94574d250f42b7640b3bd2edc4c58ac8ac2778a8c82374bb27984"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:f1ee41580bff1a651339eb3337c20c12f4037f6110a36ae4a2d864c52e5ef954"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0926cefb57fc5fced629603fbd1a23d458b25418681d96823992ba975f050c2b"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2c6e37f2e3cd74496a74af9a4fa67b547ab3ca137688c484749189bf3a686ceb"},
-    {file = "ruff-0.4.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:efd703a5975ac1998c2cc5e9494e13b28f31e66c616b0a76e206de2562e0843c"},
-    {file = "ruff-0.4.1-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:b92f03b4aa9fa23e1799b40f15f8b95cdc418782a567d6c43def65e1bbb7f1cf"},
-    {file = "ruff-0.4.1-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:1c859f294f8633889e7d77de228b203eb0e9a03071b72b5989d89a0cf98ee262"},
-    {file = "ruff-0.4.1-py3-none-musllinux_1_2_i686.whl", hash = "sha256:b34510141e393519a47f2d7b8216fec747ea1f2c81e85f076e9f2910588d4b64"},
-    {file = "ruff-0.4.1-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:6e68d248ed688b9d69fd4d18737edcbb79c98b251bba5a2b031ce2470224bdf9"},
-    {file = "ruff-0.4.1-py3-none-win32.whl", hash = "sha256:b90506f3d6d1f41f43f9b7b5ff845aeefabed6d2494307bc7b178360a8805252"},
-    {file = "ruff-0.4.1-py3-none-win_amd64.whl", hash = "sha256:c7d391e5936af5c9e252743d767c564670dc3889aff460d35c518ee76e4b26d7"},
-    {file = "ruff-0.4.1-py3-none-win_arm64.whl", hash = "sha256:a1eaf03d87e6a7cd5e661d36d8c6e874693cb9bc3049d110bc9a97b350680c43"},
-    {file = "ruff-0.4.1.tar.gz", hash = "sha256:d592116cdbb65f8b1b7e2a2b48297eb865f6bdc20641879aa9d7b9c11d86db79"},
+    {file = "ruff-0.4.7-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:e089371c67892a73b6bb1525608e89a2aca1b77b5440acf7a71dda5dac958f9e"},
+    {file = "ruff-0.4.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:10f973d521d910e5f9c72ab27e409e839089f955be8a4c8826601a6323a89753"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:59c3d110970001dfa494bcd95478e62286c751126dfb15c3c46e7915fc49694f"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fa9773c6c00f4958f73b317bc0fd125295110c3776089f6ef318f4b775f0abe4"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:07fc80bbb61e42b3b23b10fda6a2a0f5a067f810180a3760c5ef1b456c21b9db"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:fa4dafe3fe66d90e2e2b63fa1591dd6e3f090ca2128daa0be33db894e6c18648"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a7c0083febdec17571455903b184a10026603a1de078428ba155e7ce9358c5f6"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ad1b20e66a44057c326168437d680a2166c177c939346b19c0d6b08a62a37589"},
+    {file = "ruff-0.4.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cbf5d818553add7511c38b05532d94a407f499d1a76ebb0cad0374e32bc67202"},
+    {file = "ruff-0.4.7-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:50e9651578b629baec3d1513b2534de0ac7ed7753e1382272b8d609997e27e83"},
+    {file = "ruff-0.4.7-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:8874a9df7766cb956b218a0a239e0a5d23d9e843e4da1e113ae1d27ee420877a"},
+    {file = "ruff-0.4.7-py3-none-musllinux_1_2_i686.whl", hash = "sha256:b9de9a6e49f7d529decd09381c0860c3f82fa0b0ea00ea78409b785d2308a567"},
+    {file = "ruff-0.4.7-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:13a1768b0691619822ae6d446132dbdfd568b700ecd3652b20d4e8bc1e498f78"},
+    {file = "ruff-0.4.7-py3-none-win32.whl", hash = "sha256:769e5a51df61e07e887b81e6f039e7ed3573316ab7dd9f635c5afaa310e4030e"},
+    {file = "ruff-0.4.7-py3-none-win_amd64.whl", hash = "sha256:9e3ab684ad403a9ed1226894c32c3ab9c2e0718440f6f50c7c5829932bc9e054"},
+    {file = "ruff-0.4.7-py3-none-win_arm64.whl", hash = "sha256:10f2204b9a613988e3484194c2c9e96a22079206b22b787605c255f130db5ed7"},
+    {file = "ruff-0.4.7.tar.gz", hash = "sha256:2331d2b051dc77a289a653fcc6a42cce357087c5975738157cd966590b18b5e1"},
 ]
 
 [[package]]

tests/test_client.py

@@ -334,6 +334,7 @@ def test_client_create_path(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -357,6 +358,7 @@ def test_client_create_path_relative(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -389,6 +391,7 @@ def test_client_create_path_user_home(httpserver: HTTPServer, userhomedir):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -412,6 +415,7 @@ def test_client_create_modelfile(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -442,6 +446,7 @@ PARAMETER stop [/INST]
 PARAMETER stop <<SYS>>
 PARAMETER stop <</SYS>>''',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -478,6 +483,7 @@ def test_client_create_from_library(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM llama2',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -798,6 +804,7 @@ async def test_async_client_create_path(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -822,6 +829,7 @@ async def test_async_client_create_path_relative(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -846,6 +854,7 @@ async def test_async_client_create_path_user_home(httpserver: HTTPServer, userho
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -870,6 +879,7 @@ async def test_async_client_create_modelfile(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -901,6 +911,7 @@ PARAMETER stop [/INST]
 PARAMETER stop <<SYS>>
 PARAMETER stop <</SYS>>''',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -938,6 +949,7 @@ async def test_async_client_create_from_library(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM llama2',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})