add ci tests/lint

.github/workflows/test.yaml

@@ -0,0 +1,32 @@
+name: test
+
+on:
+  pull_request:
+
+jobs:
+  test:
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - run: pipx install poetry
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: poetry
+      - run: poetry install --with=dev
+      - run: poetry run ruff --output-format=github .
+      - run: poetry run pytest . --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov=ollama --cov-report=xml --cov-report=html
+      - name: check poetry.lock is up-to-date
+        run: poetry check --lock
+      - name: check requirements.txt is up-to-date
+        run: |
+          poetry export >requirements.txt
+          git diff --exit-code requirements.txt
+      - uses: actions/upload-artifact@v3
+        with:
+          name: pytest-results-${{ matrix.python-version }}
+          path: junit/test-results-${{ matrix.python-version }}.xml
+        if: ${{ always() }}

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -0,0 +1,70 @@
+# Ollama Python Library
+
+The Ollama Python library provides the easiest way to integrate your Python 3 project with [Ollama](https://github.com/jmorganca/ollama).
+
+## Getting Started
+
+Requires Python 3.8 or higher.
+
+```sh
+pip install ollama
+```
+
+A global default client is provided for convenience and can be used in the same way as the synchronous client.
+
+```python
+import ollama
+response = ollama.chat(model='llama2', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
+```
+
+```python
+import ollama
+message = {'role': 'user', 'content': 'Why is the sky blue?'}
+for part in ollama.chat(model='llama2', messages=[message], stream=True):
+  print(part['message']['content'], end='', flush=True)
+```
+
+
+### Using the Synchronous Client
+
+```python
+from ollama import Client
+message = {'role': 'user', 'content': 'Why is the sky blue?'}
+response = Client().chat(model='llama2', messages=[message])
+```
+
+Response streaming can be enabled by setting `stream=True`. This modifies the function to return a Python generator where each part is an object in the stream.
+
+```python
+from ollama import Client
+message = {'role': 'user', 'content': 'Why is the sky blue?'}
+for part in Client().chat(model='llama2', messages=[message], stream=True):
+  print(part['message']['content'], end='', flush=True)
+```
+
+### Using the Asynchronous Client
+
+```python
+import asyncio
+from ollama import AsyncClient
+
+async def chat():
+  message = {'role': 'user', 'content': 'Why is the sky blue?'}
+  response = await AsyncClient().chat(model='llama2', messages=[message])
+
+asyncio.run(chat())
+```
+
+Similar to the synchronous client, setting `stream=True` modifies the function to return a Python asynchronous generator.
+
+```python
+import asyncio
+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):
+    print(part['message']['content'], end='', flush=True)
+
+asyncio.run(chat())
+```

examples/simple-fill-in-middle/main.py

@@ -0,0 +1,22 @@
+from ollama import generate
+
+prefix = '''def remove_non_ascii(s: str) -> str:
+    """ '''
+
+suffix = '''
+    return result
+'''
+
+
+response = generate(
+  model='codellama:7b-code',
+  prompt=f'<PRE> {prefix} <SUF>{suffix} <MID>',
+  options={
+    'num_predict': 128,
+    'temperature': 0,
+    'top_p': 0.9,
+    'stop': ['<EOT>'],
+  },
+)
+
+print(response['response'])

ollama/__init__.py

@@ -1,30 +1,54 @@
-from ollama.client import Client
+from ._client import Client, AsyncClient
+
+__all__ = [
+  'Client',
+  'AsyncClient',
+  'generate',
+  'chat',
+  'pull',
+  'push',
+  'create',
+  'delete',
+  'list',
+  'copy',
+  'show',
+]
+
 
 _default_client = Client()
 
+
 def generate(*args, **kwargs):
   return _default_client.generate(*args, **kwargs)
 
+
 def chat(*args, **kwargs):
   return _default_client.chat(*args, **kwargs)
 
+
 def pull(*args, **kwargs):
   return _default_client.pull(*args, **kwargs)
 
+
 def push(*args, **kwargs):
   return _default_client.push(*args, **kwargs)
 
+
 def create(*args, **kwargs):
   return _default_client.create(*args, **kwargs)
 
+
 def delete(*args, **kwargs):
   return _default_client.delete(*args, **kwargs)
 
+
 def list(*args, **kwargs):
   return _default_client.list(*args, **kwargs)
 
+
 def copy(*args, **kwargs):
   return _default_client.copy(*args, **kwargs)
 
+
 def show(*args, **kwargs):
   return _default_client.show(*args, **kwargs)