add insert support to generate endpoint (#215)

* add suffix

* update fill-in-the-middle example

* keep example

* lint

* variables

README.md

@@ -2,24 +2,6 @@
 
 The Ollama Python library provides the easiest way to integrate Python 3.8+ projects with [Ollama](https://github.com/ollama/ollama).
 
-## Prerequisites
-
-You need to have a local ollama server running to be able to continue. To do this:
-
-- Download: https://ollama.com/
-- Run an LLM: https://ollama.com/library
-    - Example: `ollama run llama2`
-    - Example: `ollama run llama2:70b`
-
-Then:
-
-```sh
-curl https://ollama.ai/install.sh | sh
-ollama serve
-```
-
-Next you can go ahead with `ollama-python`.
-
 ## Install
 
 ```sh
@@ -125,6 +107,12 @@ ollama.push('user/llama3')
 ollama.embeddings(model='llama3', prompt='The sky is blue because of rayleigh scattering')
 ```
 
+### Ps
+
+```python
+ollama.ps()
+```
+
 ## Custom client
 
 A custom client can be created with the following fields:

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 'content' not in message:
-        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 {},
@@ -188,6 +247,29 @@ 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 = '',
@@ -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,
@@ -250,6 +364,26 @@ 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,
@@ -336,6 +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:
@@ -380,10 +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,
@@ -412,6 +584,7 @@ class AsyncClient(BaseClient):
       json={
         'model': model,
         'prompt': prompt,
+        'suffix': suffix,
         'system': system,
         'template': template,
         'context': context or [],
@@ -425,10 +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,
@@ -446,13 +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 'content' not in message:
-        raise RequestError('messages must contain content')
       if images := message.get('images'):
         message['images'] = [_encode_image(image) for image in images]
 
@@ -462,6 +656,7 @@ class AsyncClient(BaseClient):
       json={
         'model': model,
         'messages': messages,
+        'tools': tools or [],
         'stream': stream,
         'format': format,
         'options': options or {},
@@ -470,6 +665,31 @@ 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 = '',
@@ -490,6 +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,
@@ -512,6 +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,
@@ -534,6 +786,26 @@ 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,
@@ -629,6 +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):
   """

poetry.lock

@@ -386,13 +386,13 @@ testing = ["pytest", "pytest-benchmark"]
 
 [[package]]
 name = "pytest"
-version = "8.2.0"
+version = "8.2.2"
 description = "pytest: simple powerful testing with Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pytest-8.2.0-py3-none-any.whl", hash = "sha256:1733f0620f6cda4095bbf0d9ff8022486e91892245bb9e7d5542c018f612f233"},
-    {file = "pytest-8.2.0.tar.gz", hash = "sha256:d507d4482197eac0ba2bae2e9babf0672eb333017bcedaa5fb1a3d42c1174b3f"},
+    {file = "pytest-8.2.2-py3-none-any.whl", hash = "sha256:c434598117762e2bd304e526244f67bf66bbd7b5d6cf22138be51ff661980343"},
+    {file = "pytest-8.2.2.tar.gz", hash = "sha256:de4bb8104e201939ccdc688b27a89a7be2079b22e2bd2b07f806b6ba71117977"},
 ]
 
 [package.dependencies]
@@ -408,13 +408,13 @@ dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments
 
 [[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 = "0.4.3"
+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-0.4.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:b70800c290f14ae6fcbb41bbe201cf62dfca024d124a1f373e76371a007454ce"},
-    {file = "ruff-0.4.3-py3-none-macosx_11_0_arm64.whl", hash = "sha256:08a0d6a22918ab2552ace96adeaca308833873a4d7d1d587bb1d37bae8728eb3"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eba1f14df3c758dd7de5b55fbae7e1c8af238597961e5fb628f3de446c3c40c5"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:819fb06d535cc76dfddbfe8d3068ff602ddeb40e3eacbc90e0d1272bb8d97113"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0bfc9e955e6dc6359eb6f82ea150c4f4e82b660e5b58d9a20a0e42ec3bb6342b"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:510a67d232d2ebe983fddea324dbf9d69b71c4d2dfeb8a862f4a127536dd4cfb"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dc9ff11cd9a092ee7680a56d21f302bdda14327772cd870d806610a3503d001f"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:29efff25bf9ee685c2c8390563a5b5c006a3fee5230d28ea39f4f75f9d0b6f2f"},
-    {file = "ruff-0.4.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18b00e0bcccf0fc8d7186ed21e311dffd19761cb632241a6e4fe4477cc80ef6e"},
-    {file = "ruff-0.4.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:262f5635e2c74d80b7507fbc2fac28fe0d4fef26373bbc62039526f7722bca1b"},
-    {file = "ruff-0.4.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:7363691198719c26459e08cc17c6a3dac6f592e9ea3d2fa772f4e561b5fe82a3"},
-    {file = "ruff-0.4.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:eeb039f8428fcb6725bb63cbae92ad67b0559e68b5d80f840f11914afd8ddf7f"},
-    {file = "ruff-0.4.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:927b11c1e4d0727ce1a729eace61cee88a334623ec424c0b1c8fe3e5f9d3c865"},
-    {file = "ruff-0.4.3-py3-none-win32.whl", hash = "sha256:25cacda2155778beb0d064e0ec5a3944dcca9c12715f7c4634fd9d93ac33fd30"},
-    {file = "ruff-0.4.3-py3-none-win_amd64.whl", hash = "sha256:7a1c3a450bc6539ef00da6c819fb1b76b6b065dec585f91456e7c0d6a0bbc725"},
-    {file = "ruff-0.4.3-py3-none-win_arm64.whl", hash = "sha256:71ca5f8ccf1121b95a59649482470c5601c60a416bf189d553955b0338e34614"},
-    {file = "ruff-0.4.3.tar.gz", hash = "sha256:ff0a3ef2e3c4b6d133fbedcf9586abfbe38d076041f2dc18ffb2c7e0485d5a07"},
+    {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

@@ -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': [],
@@ -522,6 +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': {},
@@ -560,6 +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': {},
@@ -590,6 +598,7 @@ async def test_async_client_chat_images(httpserver: HTTPServer):
           'images': ['iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGNgYGAAAAAEAAH2FzhVAAAAAElFTkSuQmCC'],
         },
       ],
+      'tools': [],
       'stream': False,
       'format': '',
       'options': {},
@@ -613,6 +622,7 @@ async def test_async_client_generate(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -653,6 +663,7 @@ async def test_async_client_generate_stream(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],
@@ -682,6 +693,7 @@ async def test_async_client_generate_images(httpserver: HTTPServer):
     json={
       'model': 'dummy',
       'prompt': 'Why is the sky blue?',
+      'suffix': '',
       'system': '',
       'template': '',
       'context': [],