add insert support to generate endpoint (#215)

* add suffix

* update fill-in-the-middle example

* keep example

* lint

* variables

.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: daily
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: daily

.github/workflows/test.yaml

@@ -26,7 +26,7 @@ jobs:
         run: |
           poetry export >requirements.txt
           git diff --exit-code requirements.txt
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
           name: pytest-results-${{ matrix.python-version }}
           path: junit/test-results-${{ matrix.python-version }}.xml

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='They 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/fill-in-middle/main.py

@@ -1,16 +1,16 @@
 from ollama import generate
 
-prefix = '''def remove_non_ascii(s: str) -> str:
+prompt = '''def remove_non_ascii(s: str) -> str:
     """ '''
 
 suffix = """
     return result
 """
 
-
 response = generate(
   model='codellama:7b-code',
-  prompt=f'<PRE> {prefix} <SUF>{suffix} <MID>',
+  prompt=prompt,
+  suffix=suffix,
   options={
     'num_predict': 128,
     'temperature': 0,

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')

examples/tools/README.md

@@ -0,0 +1,3 @@
+# tools
+
+This example demonstrates how to utilize tool calls with an asynchronous Ollama client and the chat endpoint. 

examples/tools/main.py

@@ -0,0 +1,87 @@
+import json
+import ollama
+import asyncio
+
+
+# Simulates an API call to get flight times
+# In a real application, this would fetch data from a live database or API
+def get_flight_times(departure: str, arrival: str) -> str:
+  flights = {
+    'NYC-LAX': {'departure': '08:00 AM', 'arrival': '11:30 AM', 'duration': '5h 30m'},
+    'LAX-NYC': {'departure': '02:00 PM', 'arrival': '10:30 PM', 'duration': '5h 30m'},
+    'LHR-JFK': {'departure': '10:00 AM', 'arrival': '01:00 PM', 'duration': '8h 00m'},
+    'JFK-LHR': {'departure': '09:00 PM', 'arrival': '09:00 AM', 'duration': '7h 00m'},
+    'CDG-DXB': {'departure': '11:00 AM', 'arrival': '08:00 PM', 'duration': '6h 00m'},
+    'DXB-CDG': {'departure': '03:00 AM', 'arrival': '07:30 AM', 'duration': '7h 30m'},
+  }
+
+  key = f'{departure}-{arrival}'.upper()
+  return json.dumps(flights.get(key, {'error': 'Flight not found'}))
+
+
+async def run(model: str):
+  client = ollama.AsyncClient()
+  # Initialize conversation with a user query
+  messages = [{'role': 'user', 'content': 'What is the flight time from New York (NYC) to Los Angeles (LAX)?'}]
+
+  # First API call: Send the query and function description to the model
+  response = await client.chat(
+    model=model,
+    messages=messages,
+    tools=[
+      {
+        'type': 'function',
+        'function': {
+          'name': 'get_flight_times',
+          'description': 'Get the flight times between two cities',
+          'parameters': {
+            'type': 'object',
+            'properties': {
+              'departure': {
+                'type': 'string',
+                'description': 'The departure city (airport code)',
+              },
+              'arrival': {
+                'type': 'string',
+                'description': 'The arrival city (airport code)',
+              },
+            },
+            'required': ['departure', 'arrival'],
+          },
+        },
+      },
+    ],
+  )
+
+  # Add the model's response to the conversation history
+  messages.append(response['message'])
+
+  # Check if the model decided to use the provided function
+  if not response['message'].get('tool_calls'):
+    print("The model didn't use the function. Its response was:")
+    print(response['message']['content'])
+    return
+
+  # Process function calls made by the model
+  if response['message'].get('tool_calls'):
+    available_functions = {
+      'get_flight_times': get_flight_times,
+    }
+    for tool in response['message']['tool_calls']:
+      function_to_call = available_functions[tool['function']['name']]
+      function_response = function_to_call(tool['function']['arguments']['departure'], tool['function']['arguments']['arrival'])
+      # Add function response to the conversation
+      messages.append(
+        {
+          'role': 'tool',
+          'content': function_response,
+        }
+      )
+
+  # Second API call: Get final response from the model
+  final_response = await client.chat(model=model, messages=messages)
+  print(final_response['message']['content'])
+
+
+# Run the async function
+asyncio.run(run('mistral'))

ollama/__init__.py

@@ -21,6 +21,7 @@ __all__ = [
   'ResponseError',
   'generate',
   'chat',
+  'embed',
   'embeddings',
   'pull',
   'push',
@@ -29,12 +30,14 @@ __all__ = [
   'list',
   'copy',
   'show',
+  'ps',
 ]
 
 _client = Client()
 
 generate = _client.generate
 chat = _client.chat
+embed = _client.embed
 embeddings = _client.embeddings
 pull = _client.pull
 push = _client.push
@@ -43,3 +46,4 @@ 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
 
@@ -26,7 +27,7 @@ try:
 except metadata.PackageNotFoundError:
   __version__ = '0.0.0'
 
-from ollama._types import Message, Options, RequestError, ResponseError
+from ollama._types import Message, Options, RequestError, ResponseError, Tool
 
 
 class BaseClient:
@@ -96,10 +97,45 @@ 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 = '',
+    suffix: 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
+  def generate(
+    self,
+    model: str = '',
+    prompt: str = '',
+    suffix: 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,
+  ) -> Iterator[Mapping[str, Any]]: ...
+
+  def generate(
+    self,
+    model: str = '',
+    prompt: str = '',
+    suffix: str = '',
     system: str = '',
     template: str = '',
     context: Optional[Sequence[int]] = None,
@@ -129,6 +165,7 @@ class Client(BaseClient):
       json={
         'model': model,
         'prompt': prompt,
+        'suffix': suffix,
         'system': system,
         'template': template,
         'context': context or [],
@@ -142,10 +179,35 @@ class Client(BaseClient):
       stream=stream,
     )
 
+  @overload
   def chat(
     self,
     model: str = '',
     messages: Optional[Sequence[Message]] = None,
+    tools: Optional[Sequence[Tool]] = 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,
+    tools: Optional[Sequence[Tool]] = 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 = '',
+    messages: Optional[Sequence[Message]] = None,
+    tools: Optional[Sequence[Tool]] = None,
     stream: bool = False,
     format: Literal['', 'json'] = '',
     options: Optional[Options] = None,
@@ -164,13 +226,9 @@ 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')
-      if not (role := message.get('role')) or role not in ['system', 'user', 'assistant']:
-        raise RequestError('messages must contain a role and it must be one of "system", "user", or "assistant"')
-      if not message.get('content'):
-        raise RequestError('messages must contain content')
       if images := message.get('images'):
         message['images'] = [_encode_image(image) for image in images]
 
@@ -180,6 +238,7 @@ class Client(BaseClient):
       json={
         'model': model,
         'messages': messages,
+        'tools': tools or [],
         'stream': stream,
         'format': format,
         'options': options or {},
@@ -188,13 +247,36 @@ class Client(BaseClient):
       stream=stream,
     )
 
+  def embed(
+    self,
+    model: str = '',
+    input: Union[str, Sequence[AnyStr]] = '',
+    truncate: bool = True,
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Mapping[str, Any]:
+    if not model:
+      raise RequestError('must provide a model')
+
+    return self._request(
+      'POST',
+      '/api/embed',
+      json={
+        'model': model,
+        'input': input,
+        'truncate': truncate,
+        'options': options or {},
+        'keep_alive': keep_alive,
+      },
+    ).json()
+
   def embeddings(
     self,
     model: str = '',
     prompt: str = '',
     options: Optional[Options] = None,
     keep_alive: Optional[Union[float, str]] = None,
-  ) -> Sequence[float]:
+  ) -> Mapping[str, Sequence[float]]:
     return self._request(
       'POST',
       '/api/embeddings',
@@ -206,6 +288,22 @@ 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 +326,22 @@ 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 +364,32 @@ 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 +411,7 @@ class Client(BaseClient):
         'name': model,
         'modelfile': modelfile,
         'stream': stream,
+        'quantize': quantize,
       },
       stream=stream,
     )
@@ -334,6 +470,9 @@ 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:
@@ -378,10 +517,45 @@ class AsyncClient(BaseClient):
     response = await self._request(*args, **kwargs)
     return response.json()
 
+  @overload
   async def generate(
     self,
     model: str = '',
     prompt: str = '',
+    suffix: 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 = '',
+    suffix: 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 = '',
+    prompt: str = '',
+    suffix: str = '',
     system: str = '',
     template: str = '',
     context: Optional[Sequence[int]] = None,
@@ -410,6 +584,7 @@ class AsyncClient(BaseClient):
       json={
         'model': model,
         'prompt': prompt,
+        'suffix': suffix,
         'system': system,
         'template': template,
         'context': context or [],
@@ -423,10 +598,35 @@ class AsyncClient(BaseClient):
       stream=stream,
     )
 
+  @overload
   async def chat(
     self,
     model: str = '',
     messages: Optional[Sequence[Message]] = None,
+    tools: Optional[Sequence[Tool]] = 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,
+    tools: Optional[Sequence[Tool]] = 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 = '',
+    messages: Optional[Sequence[Message]] = None,
+    tools: Optional[Sequence[Tool]] = None,
     stream: bool = False,
     format: Literal['', 'json'] = '',
     options: Optional[Options] = None,
@@ -444,13 +644,9 @@ 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')
-      if not (role := message.get('role')) or role not in ['system', 'user', 'assistant']:
-        raise RequestError('messages must contain a role and it must be one of "system", "user", or "assistant"')
-      if not message.get('content'):
-        raise RequestError('messages must contain content')
       if images := message.get('images'):
         message['images'] = [_encode_image(image) for image in images]
 
@@ -460,6 +656,7 @@ class AsyncClient(BaseClient):
       json={
         'model': model,
         'messages': messages,
+        'tools': tools or [],
         'stream': stream,
         'format': format,
         'options': options or {},
@@ -468,13 +665,38 @@ class AsyncClient(BaseClient):
       stream=stream,
     )
 
+  async def embed(
+    self,
+    model: str = '',
+    input: Union[str, Sequence[AnyStr]] = '',
+    truncate: bool = True,
+    options: Optional[Options] = None,
+    keep_alive: Optional[Union[float, str]] = None,
+  ) -> Mapping[str, Any]:
+    if not model:
+      raise RequestError('must provide a model')
+
+    response = await self._request(
+      'POST',
+      '/api/embed',
+      json={
+        'model': model,
+        'input': input,
+        'truncate': truncate,
+        'options': options or {},
+        'keep_alive': keep_alive,
+      },
+    )
+
+    return response.json()
+
   async def embeddings(
     self,
     model: str = '',
     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 +710,22 @@ 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 +748,22 @@ 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 +786,32 @@ 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 +833,7 @@ class AsyncClient(BaseClient):
         'name': model,
         'modelfile': modelfile,
         'stream': stream,
+        'quantize': quantize,
       },
       stream=stream,
     )
@@ -625,6 +901,10 @@ 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

@@ -1,5 +1,5 @@
 import json
-from typing import Any, TypedDict, Sequence, Literal
+from typing import Any, TypedDict, Sequence, Literal, Mapping
 
 import sys
 
@@ -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.'
 
@@ -50,6 +53,27 @@ class GenerateResponse(BaseGenerateResponse):
   'Tokenized history up to the point of the response.'
 
 
+class ToolCallFunction(TypedDict):
+  """
+  Tool call function.
+  """
+
+  name: str
+  'Name of the function.'
+
+  args: NotRequired[Mapping[str, Any]]
+  'Arguments of the function.'
+
+
+class ToolCall(TypedDict):
+  """
+  Model tool calls.
+  """
+
+  function: ToolCallFunction
+  'Function to be called.'
+
+
 class Message(TypedDict):
   """
   Chat message.
@@ -73,6 +97,34 @@ class Message(TypedDict):
   Valid image formats depend on the model. See the model card for more information.
   """
 
+  tool_calls: NotRequired[Sequence[ToolCall]]
+  """
+  Tools calls to be made by the model.
+  """
+
+
+class Property(TypedDict):
+  type: str
+  description: str
+  enum: NotRequired[Sequence[str]]  # `enum` is optional and can be a list of strings
+
+
+class Parameters(TypedDict):
+  type: str
+  required: Sequence[str]
+  properties: Mapping[str, Property]
+
+
+class ToolFunction(TypedDict):
+  name: str
+  description: str
+  parameters: Parameters
+
+
+class Tool(TypedDict):
+  type: str
+  function: ToolFunction
+
 
 class ChatResponse(BaseGenerateResponse):
   """
@@ -95,7 +147,6 @@ 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 +156,6 @@ 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

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "anyio"
@@ -285,79 +285,80 @@ files = [
 
 [[package]]
 name = "pillow"
-version = "10.2.0"
+version = "10.3.0"
 description = "Python Imaging Library (Fork)"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pillow-10.2.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:7823bdd049099efa16e4246bdf15e5a13dbb18a51b68fa06d6c1d4d8b99a796e"},
-    {file = "pillow-10.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:83b2021f2ade7d1ed556bc50a399127d7fb245e725aa0113ebd05cfe88aaf588"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6fad5ff2f13d69b7e74ce5b4ecd12cc0ec530fcee76356cac6742785ff71c452"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da2b52b37dad6d9ec64e653637a096905b258d2fc2b984c41ae7d08b938a67e4"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:47c0995fc4e7f79b5cfcab1fc437ff2890b770440f7696a3ba065ee0fd496563"},
-    {file = "pillow-10.2.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:322bdf3c9b556e9ffb18f93462e5f749d3444ce081290352c6070d014c93feb2"},
-    {file = "pillow-10.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:51f1a1bffc50e2e9492e87d8e09a17c5eea8409cda8d3f277eb6edc82813c17c"},
-    {file = "pillow-10.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:69ffdd6120a4737710a9eee73e1d2e37db89b620f702754b8f6e62594471dee0"},
-    {file = "pillow-10.2.0-cp310-cp310-win32.whl", hash = "sha256:c6dafac9e0f2b3c78df97e79af707cdc5ef8e88208d686a4847bab8266870023"},
-    {file = "pillow-10.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:aebb6044806f2e16ecc07b2a2637ee1ef67a11840a66752751714a0d924adf72"},
-    {file = "pillow-10.2.0-cp310-cp310-win_arm64.whl", hash = "sha256:7049e301399273a0136ff39b84c3678e314f2158f50f517bc50285fb5ec847ad"},
-    {file = "pillow-10.2.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:35bb52c37f256f662abdfa49d2dfa6ce5d93281d323a9af377a120e89a9eafb5"},
-    {file = "pillow-10.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9c23f307202661071d94b5e384e1e1dc7dfb972a28a2310e4ee16103e66ddb67"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:773efe0603db30c281521a7c0214cad7836c03b8ccff897beae9b47c0b657d61"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11fa2e5984b949b0dd6d7a94d967743d87c577ff0b83392f17cb3990d0d2fd6e"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:716d30ed977be8b37d3ef185fecb9e5a1d62d110dfbdcd1e2a122ab46fddb03f"},
-    {file = "pillow-10.2.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a086c2af425c5f62a65e12fbf385f7c9fcb8f107d0849dba5839461a129cf311"},
-    {file = "pillow-10.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c8de2789052ed501dd829e9cae8d3dcce7acb4777ea4a479c14521c942d395b1"},
-    {file = "pillow-10.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:609448742444d9290fd687940ac0b57fb35e6fd92bdb65386e08e99af60bf757"},
-    {file = "pillow-10.2.0-cp311-cp311-win32.whl", hash = "sha256:823ef7a27cf86df6597fa0671066c1b596f69eba53efa3d1e1cb8b30f3533068"},
-    {file = "pillow-10.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:1da3b2703afd040cf65ec97efea81cfba59cdbed9c11d8efc5ab09df9509fc56"},
-    {file = "pillow-10.2.0-cp311-cp311-win_arm64.whl", hash = "sha256:edca80cbfb2b68d7b56930b84a0e45ae1694aeba0541f798e908a49d66b837f1"},
-    {file = "pillow-10.2.0-cp312-cp312-macosx_10_10_x86_64.whl", hash = "sha256:1b5e1b74d1bd1b78bc3477528919414874748dd363e6272efd5abf7654e68bef"},
-    {file = "pillow-10.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0eae2073305f451d8ecacb5474997c08569fb4eb4ac231ffa4ad7d342fdc25ac"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b7c2286c23cd350b80d2fc9d424fc797575fb16f854b831d16fd47ceec078f2c"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e23412b5c41e58cec602f1135c57dfcf15482013ce6e5f093a86db69646a5aa"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:52a50aa3fb3acb9cf7213573ef55d31d6eca37f5709c69e6858fe3bc04a5c2a2"},
-    {file = "pillow-10.2.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:127cee571038f252a552760076407f9cff79761c3d436a12af6000cd182a9d04"},
-    {file = "pillow-10.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:8d12251f02d69d8310b046e82572ed486685c38f02176bd08baf216746eb947f"},
-    {file = "pillow-10.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:54f1852cd531aa981bc0965b7d609f5f6cc8ce8c41b1139f6ed6b3c54ab82bfb"},
-    {file = "pillow-10.2.0-cp312-cp312-win32.whl", hash = "sha256:257d8788df5ca62c980314053197f4d46eefedf4e6175bc9412f14412ec4ea2f"},
-    {file = "pillow-10.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:154e939c5f0053a383de4fd3d3da48d9427a7e985f58af8e94d0b3c9fcfcf4f9"},
-    {file = "pillow-10.2.0-cp312-cp312-win_arm64.whl", hash = "sha256:f379abd2f1e3dddb2b61bc67977a6b5a0a3f7485538bcc6f39ec76163891ee48"},
-    {file = "pillow-10.2.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:8373c6c251f7ef8bda6675dd6d2b3a0fcc31edf1201266b5cf608b62a37407f9"},
-    {file = "pillow-10.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:870ea1ada0899fd0b79643990809323b389d4d1d46c192f97342eeb6ee0b8483"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b4b6b1e20608493548b1f32bce8cca185bf0480983890403d3b8753e44077129"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3031709084b6e7852d00479fd1d310b07d0ba82765f973b543c8af5061cf990e"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:3ff074fc97dd4e80543a3e91f69d58889baf2002b6be64347ea8cf5533188213"},
-    {file = "pillow-10.2.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:cb4c38abeef13c61d6916f264d4845fab99d7b711be96c326b84df9e3e0ff62d"},
-    {file = "pillow-10.2.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:b1b3020d90c2d8e1dae29cf3ce54f8094f7938460fb5ce8bc5c01450b01fbaf6"},
-    {file = "pillow-10.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:170aeb00224ab3dc54230c797f8404507240dd868cf52066f66a41b33169bdbe"},
-    {file = "pillow-10.2.0-cp38-cp38-win32.whl", hash = "sha256:c4225f5220f46b2fde568c74fca27ae9771536c2e29d7c04f4fb62c83275ac4e"},
-    {file = "pillow-10.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:0689b5a8c5288bc0504d9fcee48f61a6a586b9b98514d7d29b840143d6734f39"},
-    {file = "pillow-10.2.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:b792a349405fbc0163190fde0dc7b3fef3c9268292586cf5645598b48e63dc67"},
-    {file = "pillow-10.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c570f24be1e468e3f0ce7ef56a89a60f0e05b30a3669a459e419c6eac2c35364"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8ecd059fdaf60c1963c58ceb8997b32e9dc1b911f5da5307aab614f1ce5c2fb"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c365fd1703040de1ec284b176d6af5abe21b427cb3a5ff68e0759e1e313a5e7e"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:70c61d4c475835a19b3a5aa42492409878bbca7438554a1f89d20d58a7c75c01"},
-    {file = "pillow-10.2.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:b6f491cdf80ae540738859d9766783e3b3c8e5bd37f5dfa0b76abdecc5081f13"},
-    {file = "pillow-10.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9d189550615b4948f45252d7f005e53c2040cea1af5b60d6f79491a6e147eef7"},
-    {file = "pillow-10.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:49d9ba1ed0ef3e061088cd1e7538a0759aab559e2e0a80a36f9fd9d8c0c21591"},
-    {file = "pillow-10.2.0-cp39-cp39-win32.whl", hash = "sha256:babf5acfede515f176833ed6028754cbcd0d206f7f614ea3447d67c33be12516"},
-    {file = "pillow-10.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:0304004f8067386b477d20a518b50f3fa658a28d44e4116970abfcd94fac34a8"},
-    {file = "pillow-10.2.0-cp39-cp39-win_arm64.whl", hash = "sha256:0fb3e7fc88a14eacd303e90481ad983fd5b69c761e9e6ef94c983f91025da869"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-macosx_10_10_x86_64.whl", hash = "sha256:322209c642aabdd6207517e9739c704dc9f9db943015535783239022002f054a"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3eedd52442c0a5ff4f887fab0c1c0bb164d8635b32c894bc1faf4c618dd89df2"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cb28c753fd5eb3dd859b4ee95de66cc62af91bcff5db5f2571d32a520baf1f04"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:33870dc4653c5017bf4c8873e5488d8f8d5f8935e2f1fb9a2208c47cdd66efd2"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:3c31822339516fb3c82d03f30e22b1d038da87ef27b6a78c9549888f8ceda39a"},
-    {file = "pillow-10.2.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a2b56ba36e05f973d450582fb015594aaa78834fefe8dfb8fcd79b93e64ba4c6"},
-    {file = "pillow-10.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:d8e6aeb9201e655354b3ad049cb77d19813ad4ece0df1249d3c793de3774f8c7"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-macosx_10_10_x86_64.whl", hash = "sha256:2247178effb34a77c11c0e8ac355c7a741ceca0a732b27bf11e747bbc950722f"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:15587643b9e5eb26c48e49a7b33659790d28f190fc514a322d55da2fb5c2950e"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753cd8f2086b2b80180d9b3010dd4ed147efc167c90d3bf593fe2af21265e5a5"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:7c8f97e8e7a9009bcacbe3766a36175056c12f9a44e6e6f2d5caad06dcfbf03b"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d1b35bcd6c5543b9cb547dee3150c93008f8dd0f1fef78fc0cd2b141c5baf58a"},
-    {file = "pillow-10.2.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:fe4c15f6c9285dc54ce6553a3ce908ed37c8f3825b5a51a15c91442bb955b868"},
-    {file = "pillow-10.2.0.tar.gz", hash = "sha256:e87f0b2c78157e12d7686b27d63c070fd65d994e8ddae6f328e0dcf4a0cd007e"},
+    {file = "pillow-10.3.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:90b9e29824800e90c84e4022dd5cc16eb2d9605ee13f05d47641eb183cd73d45"},
+    {file = "pillow-10.3.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a2c405445c79c3f5a124573a051062300936b0281fee57637e706453e452746c"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:78618cdbccaa74d3f88d0ad6cb8ac3007f1a6fa5c6f19af64b55ca170bfa1edf"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:261ddb7ca91fcf71757979534fb4c128448b5b4c55cb6152d280312062f69599"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:ce49c67f4ea0609933d01c0731b34b8695a7a748d6c8d186f95e7d085d2fe475"},
+    {file = "pillow-10.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:b14f16f94cbc61215115b9b1236f9c18403c15dd3c52cf629072afa9d54c1cbf"},
+    {file = "pillow-10.3.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d33891be6df59d93df4d846640f0e46f1a807339f09e79a8040bc887bdcd7ed3"},
+    {file = "pillow-10.3.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b50811d664d392f02f7761621303eba9d1b056fb1868c8cdf4231279645c25f5"},
+    {file = "pillow-10.3.0-cp310-cp310-win32.whl", hash = "sha256:ca2870d5d10d8726a27396d3ca4cf7976cec0f3cb706debe88e3a5bd4610f7d2"},
+    {file = "pillow-10.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:f0d0591a0aeaefdaf9a5e545e7485f89910c977087e7de2b6c388aec32011e9f"},
+    {file = "pillow-10.3.0-cp310-cp310-win_arm64.whl", hash = "sha256:ccce24b7ad89adb5a1e34a6ba96ac2530046763912806ad4c247356a8f33a67b"},
+    {file = "pillow-10.3.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:5f77cf66e96ae734717d341c145c5949c63180842a545c47a0ce7ae52ca83795"},
+    {file = "pillow-10.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e4b878386c4bf293578b48fc570b84ecfe477d3b77ba39a6e87150af77f40c57"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdcbb4068117dfd9ce0138d068ac512843c52295ed996ae6dd1faf537b6dbc27"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9797a6c8fe16f25749b371c02e2ade0efb51155e767a971c61734b1bf6293994"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:9e91179a242bbc99be65e139e30690e081fe6cb91a8e77faf4c409653de39451"},
+    {file = "pillow-10.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:1b87bd9d81d179bd8ab871603bd80d8645729939f90b71e62914e816a76fc6bd"},
+    {file = "pillow-10.3.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:81d09caa7b27ef4e61cb7d8fbf1714f5aec1c6b6c5270ee53504981e6e9121ad"},
+    {file = "pillow-10.3.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:048ad577748b9fa4a99a0548c64f2cb8d672d5bf2e643a739ac8faff1164238c"},
+    {file = "pillow-10.3.0-cp311-cp311-win32.whl", hash = "sha256:7161ec49ef0800947dc5570f86568a7bb36fa97dd09e9827dc02b718c5643f09"},
+    {file = "pillow-10.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:8eb0908e954d093b02a543dc963984d6e99ad2b5e36503d8a0aaf040505f747d"},
+    {file = "pillow-10.3.0-cp311-cp311-win_arm64.whl", hash = "sha256:4e6f7d1c414191c1199f8996d3f2282b9ebea0945693fb67392c75a3a320941f"},
+    {file = "pillow-10.3.0-cp312-cp312-macosx_10_10_x86_64.whl", hash = "sha256:e46f38133e5a060d46bd630faa4d9fa0202377495df1f068a8299fd78c84de84"},
+    {file = "pillow-10.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:50b8eae8f7334ec826d6eeffaeeb00e36b5e24aa0b9df322c247539714c6df19"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d3bea1c75f8c53ee4d505c3e67d8c158ad4df0d83170605b50b64025917f338"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:19aeb96d43902f0a783946a0a87dbdad5c84c936025b8419da0a0cd7724356b1"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:74d28c17412d9caa1066f7a31df8403ec23d5268ba46cd0ad2c50fb82ae40462"},
+    {file = "pillow-10.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:ff61bfd9253c3915e6d41c651d5f962da23eda633cf02262990094a18a55371a"},
+    {file = "pillow-10.3.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:d886f5d353333b4771d21267c7ecc75b710f1a73d72d03ca06df49b09015a9ef"},
+    {file = "pillow-10.3.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4b5ec25d8b17217d635f8935dbc1b9aa5907962fae29dff220f2659487891cd3"},
+    {file = "pillow-10.3.0-cp312-cp312-win32.whl", hash = "sha256:51243f1ed5161b9945011a7360e997729776f6e5d7005ba0c6879267d4c5139d"},
+    {file = "pillow-10.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:412444afb8c4c7a6cc11a47dade32982439925537e483be7c0ae0cf96c4f6a0b"},
+    {file = "pillow-10.3.0-cp312-cp312-win_arm64.whl", hash = "sha256:798232c92e7665fe82ac085f9d8e8ca98826f8e27859d9a96b41d519ecd2e49a"},
+    {file = "pillow-10.3.0-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:4eaa22f0d22b1a7e93ff0a596d57fdede2e550aecffb5a1ef1106aaece48e96b"},
+    {file = "pillow-10.3.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cd5e14fbf22a87321b24c88669aad3a51ec052eb145315b3da3b7e3cc105b9a2"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1530e8f3a4b965eb6a7785cf17a426c779333eb62c9a7d1bbcf3ffd5bf77a4aa"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d512aafa1d32efa014fa041d38868fda85028e3f930a96f85d49c7d8ddc0383"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:339894035d0ede518b16073bdc2feef4c991ee991a29774b33e515f1d308e08d"},
+    {file = "pillow-10.3.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:aa7e402ce11f0885305bfb6afb3434b3cd8f53b563ac065452d9d5654c7b86fd"},
+    {file = "pillow-10.3.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:0ea2a783a2bdf2a561808fe4a7a12e9aa3799b701ba305de596bc48b8bdfce9d"},
+    {file = "pillow-10.3.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c78e1b00a87ce43bb37642c0812315b411e856a905d58d597750eb79802aaaa3"},
+    {file = "pillow-10.3.0-cp38-cp38-win32.whl", hash = "sha256:72d622d262e463dfb7595202d229f5f3ab4b852289a1cd09650362db23b9eb0b"},
+    {file = "pillow-10.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:2034f6759a722da3a3dbd91a81148cf884e91d1b747992ca288ab88c1de15999"},
+    {file = "pillow-10.3.0-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:2ed854e716a89b1afcedea551cd85f2eb2a807613752ab997b9974aaa0d56936"},
+    {file = "pillow-10.3.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:dc1a390a82755a8c26c9964d457d4c9cbec5405896cba94cf51f36ea0d855002"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4203efca580f0dd6f882ca211f923168548f7ba334c189e9eab1178ab840bf60"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3102045a10945173d38336f6e71a8dc71bcaeed55c3123ad4af82c52807b9375"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:6fb1b30043271ec92dc65f6d9f0b7a830c210b8a96423074b15c7bc999975f57"},
+    {file = "pillow-10.3.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:1dfc94946bc60ea375cc39cff0b8da6c7e5f8fcdc1d946beb8da5c216156ddd8"},
+    {file = "pillow-10.3.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b09b86b27a064c9624d0a6c54da01c1beaf5b6cadfa609cf63789b1d08a797b9"},
+    {file = "pillow-10.3.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d3b2348a78bc939b4fed6552abfd2e7988e0f81443ef3911a4b8498ca084f6eb"},
+    {file = "pillow-10.3.0-cp39-cp39-win32.whl", hash = "sha256:45ebc7b45406febf07fef35d856f0293a92e7417ae7933207e90bf9090b70572"},
+    {file = "pillow-10.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:0ba26351b137ca4e0db0342d5d00d2e355eb29372c05afd544ebf47c0956ffeb"},
+    {file = "pillow-10.3.0-cp39-cp39-win_arm64.whl", hash = "sha256:50fd3f6b26e3441ae07b7c979309638b72abc1a25da31a81a7fbd9495713ef4f"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-macosx_10_10_x86_64.whl", hash = "sha256:6b02471b72526ab8a18c39cb7967b72d194ec53c1fd0a70b050565a0f366d355"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:8ab74c06ffdab957d7670c2a5a6e1a70181cd10b727cd788c4dd9005b6a8acd9"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:048eeade4c33fdf7e08da40ef402e748df113fd0b4584e32c4af74fe78baaeb2"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e2ec1e921fd07c7cda7962bad283acc2f2a9ccc1b971ee4b216b75fad6f0463"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:4c8e73e99da7db1b4cad7f8d682cf6abad7844da39834c288fbfa394a47bbced"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:16563993329b79513f59142a6b02055e10514c1a8e86dca8b48a893e33cf91e3"},
+    {file = "pillow-10.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:dd78700f5788ae180b5ee8902c6aea5a5726bac7c364b202b4b3e3ba2d293170"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-macosx_10_10_x86_64.whl", hash = "sha256:aff76a55a8aa8364d25400a210a65ff59d0168e0b4285ba6bf2bd83cf675ba32"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:b7bc2176354defba3edc2b9a777744462da2f8e921fbaf61e52acb95bafa9828"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:793b4e24db2e8742ca6423d3fde8396db336698c55cd34b660663ee9e45ed37f"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d93480005693d247f8346bc8ee28c72a2191bdf1f6b5db469c096c0c867ac015"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c83341b89884e2b2e55886e8fbbf37c3fa5efd6c8907124aeb72f285ae5696e5"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:1a1d1915db1a4fdb2754b9de292642a39a7fb28f1736699527bb649484fb966a"},
+    {file = "pillow-10.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a0eaa93d054751ee9964afa21c06247779b90440ca41d184aeb5d410f20ff591"},
+    {file = "pillow-10.3.0.tar.gz", hash = "sha256:9d2455fbf44c914840c793e89aa82d0e1763a14253a000743719ae5946814b2d"},
 ]
 
 [package.extras]
@@ -370,13 +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]
@@ -385,13 +386,13 @@ testing = ["pytest", "pytest-benchmark"]
 
 [[package]]
 name = "pytest"
-version = "7.4.4"
+version = "8.2.2"
 description = "pytest: simple powerful testing with Python"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "pytest-7.4.4-py3-none-any.whl", hash = "sha256:b090cdf5ed60bf4c45261be03239c2c1c22df034fbffe691abe93cd80cea01d8"},
-    {file = "pytest-7.4.4.tar.gz", hash = "sha256:2cf0005922c6ace4a3e2ec8b4080eb0d9753fdc93107415332f50ce9e7994280"},
+    {file = "pytest-8.2.2-py3-none-any.whl", hash = "sha256:c434598117762e2bd304e526244f67bf66bbd7b5d6cf22138be51ff661980343"},
+    {file = "pytest-8.2.2.tar.gz", hash = "sha256:de4bb8104e201939ccdc688b27a89a7be2079b22e2bd2b07f806b6ba71117977"},
 ]
 
 [package.dependencies]
@@ -399,21 +400,21 @@ colorama = {version = "*", markers = "sys_platform == \"win32\""}
 exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
 iniconfig = "*"
 packaging = "*"
-pluggy = ">=0.12,<2.0"
-tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
+pluggy = ">=1.5,<2.0"
+tomli = {version = ">=1", markers = "python_version < \"3.11\""}
 
 [package.extras]
-testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "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]
@@ -425,13 +426,13 @@ testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"]
 
 [[package]]
 name = "pytest-cov"
-version = "4.1.0"
+version = "5.0.0"
 description = "Pytest plugin for measuring coverage."
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "pytest-cov-4.1.0.tar.gz", hash = "sha256:3904b13dfbfec47f003b8e77fd5b589cd11904a21ddf1ab38a64f204d6a10ef6"},
-    {file = "pytest_cov-4.1.0-py3-none-any.whl", hash = "sha256:6ba70b9e97e69fcc3fb45bfeab2d0a138fb65c4d0d6a41ef33983ad114be8c3a"},
+    {file = "pytest-cov-5.0.0.tar.gz", hash = "sha256:5837b58e9f6ebd335b0f8060eecce69b662415b16dc503883a02f45dfeb14857"},
+    {file = "pytest_cov-5.0.0-py3-none-any.whl", hash = "sha256:4f0764a1219df53214206bf1feea4633c3b558a2925c8b59f144f682861ce652"},
 ]
 
 [package.dependencies]
@@ -439,7 +440,7 @@ coverage = {version = ">=5.2.1", extras = ["toml"]}
 pytest = ">=4.6"
 
 [package.extras]
-testing = ["fields", "hunter", "process-tests", "pytest-xdist", "six", "virtualenv"]
+testing = ["fields", "hunter", "process-tests", "pytest-xdist", "virtualenv"]
 
 [[package]]
 name = "pytest-httpserver"
@@ -457,28 +458,28 @@ Werkzeug = ">=2.0.0"
 
 [[package]]
 name = "ruff"
-version = "0.1.15"
+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-0.1.15-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:5fe8d54df166ecc24106db7dd6a68d44852d14eb0729ea4672bb4d96c320b7df"},
-    {file = "ruff-0.1.15-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6f0bfbb53c4b4de117ac4d6ddfd33aa5fc31beeaa21d23c45c6dd249faf9126f"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0d432aec35bfc0d800d4f70eba26e23a352386be3a6cf157083d18f6f5881c8"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9405fa9ac0e97f35aaddf185a1be194a589424b8713e3b97b762336ec79ff807"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c66ec24fe36841636e814b8f90f572a8c0cb0e54d8b5c2d0e300d28a0d7bffec"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:6f8ad828f01e8dd32cc58bc28375150171d198491fc901f6f98d2a39ba8e3ff5"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86811954eec63e9ea162af0ffa9f8d09088bab51b7438e8b6488b9401863c25e"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fd4025ac5e87d9b80e1f300207eb2fd099ff8200fa2320d7dc066a3f4622dc6b"},
-    {file = "ruff-0.1.15-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b17b93c02cdb6aeb696effecea1095ac93f3884a49a554a9afa76bb125c114c1"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:ddb87643be40f034e97e97f5bc2ef7ce39de20e34608f3f829db727a93fb82c5"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:abf4822129ed3a5ce54383d5f0e964e7fef74a41e48eb1dfad404151efc130a2"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_i686.whl", hash = "sha256:6c629cf64bacfd136c07c78ac10a54578ec9d1bd2a9d395efbee0935868bf852"},
-    {file = "ruff-0.1.15-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:1bab866aafb53da39c2cadfb8e1c4550ac5340bb40300083eb8967ba25481447"},
-    {file = "ruff-0.1.15-py3-none-win32.whl", hash = "sha256:2417e1cb6e2068389b07e6fa74c306b2810fe3ee3476d5b8a96616633f40d14f"},
-    {file = "ruff-0.1.15-py3-none-win_amd64.whl", hash = "sha256:3837ac73d869efc4182d9036b1405ef4c73d9b1f88da2413875e34e0d6919587"},
-    {file = "ruff-0.1.15-py3-none-win_arm64.whl", hash = "sha256:9a933dfb1c14ec7a33cceb1e49ec4a16b51ce3c20fd42663198746efc0427360"},
-    {file = "ruff-0.1.15.tar.gz", hash = "sha256:f6dfa8c1b21c913c326919056c390966648b680966febcb796cc9d1aaab8564e"},
+    {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]]
@@ -534,4 +535,4 @@ watchdog = ["watchdog (>=2.3)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.8"
-content-hash = "78c0e3f11a62251ec1582f38173bafc50ac134d13f042f9378f75e4f64e004aa"
+content-hash = "aa94e026d55b1357763a45d56cdcd20d0b53ec318350c2176b19313e315ab96d"

pyproject.toml

@@ -13,12 +13,12 @@ python = "^3.8"
 httpx = "^0.27.0"
 
 [tool.poetry.group.dev.dependencies]
-pytest = "^7.4.3"
+pytest = ">=7.4.3,<9.0.0"
 pytest-asyncio = "^0.23.2"
-pytest-cov = "^4.1.0"
+pytest-cov = ">=4.1,<6.0"
 pytest-httpserver = "^1.0.8"
 pillow = "^10.2.0"
-ruff = "^0.1.8"
+ruff = ">=0.1.8,<0.5.0"
 
 [build-system]
 requires = ["poetry-core"]

tests/test_client.py

@@ -26,6 +26,7 @@ def test_client_chat(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'messages': [{'role': 'user', 'content': 'Why is the sky blue?'}],
+      'tools': [],
       'stream': False,
       'format': '',
       'options': {},
@@ -73,6 +74,7 @@ def test_client_chat_stream(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'messages': [{'role': 'user', 'content': 'Why is the sky blue?'}],
+      'tools': [],
       'stream': True,
       'format': '',
       'options': {},
@@ -102,6 +104,7 @@ def test_client_chat_images(httpserver: HTTPServer):
           'images': ['iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGNgYGAAAAAEAAH2FzhVAAAAAElFTkSuQmCC'],
         },
       ],
+      'tools': [],
       'stream': False,
       'format': '',
       'options': {},
@@ -134,6 +137,7 @@ def test_client_generate(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -179,6 +183,7 @@ def test_client_generate_stream(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -207,6 +212,7 @@ def test_client_generate_images(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -334,6 +340,7 @@ def test_client_create_path(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -357,6 +364,7 @@ def test_client_create_path_relative(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -389,6 +397,7 @@ 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 +421,7 @@ def test_client_create_modelfile(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM @sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855\n',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -442,6 +452,7 @@ PARAMETER stop [/INST]
 PARAMETER stop <<SYS>>
 PARAMETER stop <</SYS>>''',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -478,6 +489,7 @@ def test_client_create_from_library(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM llama2',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -516,6 +528,7 @@ async def test_async_client_chat(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'messages': [{'role': 'user', 'content': 'Why is the sky blue?'}],
+      'tools': [],
       'stream': False,
       'format': '',
       'options': {},
@@ -554,6 +567,7 @@ async def test_async_client_chat_stream(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'messages': [{'role': 'user', 'content': 'Why is the sky blue?'}],
+      'tools': [],
       'stream': True,
       'format': '',
       'options': {},
@@ -584,6 +598,7 @@ async def test_async_client_chat_images(httpserver: HTTPServer):
           'images': ['iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGNgYGAAAAAEAAH2FzhVAAAAAElFTkSuQmCC'],
         },
       ],
+      'tools': [],
       'stream': False,
       'format': '',
       'options': {},
@@ -607,6 +622,7 @@ async def test_async_client_generate(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -647,6 +663,7 @@ async def test_async_client_generate_stream(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -676,6 +693,7 @@ async def test_async_client_generate_images(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -798,6 +816,7 @@ 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 +841,7 @@ 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 +866,7 @@ 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 +891,7 @@ 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 +923,7 @@ PARAMETER stop [/INST]
 PARAMETER stop <<SYS>>
 PARAMETER stop <</SYS>>''',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})
 
@@ -938,6 +961,7 @@ async def test_async_client_create_from_library(httpserver: HTTPServer):
       'name': 'dummy',
       'modelfile': 'FROM llama2',
       'stream': False,
+      'quantize': None,
     },
   ).respond_with_json({})