Files
semantic-kernel/python/pyproject.toml
T
Eduard van Valkenburg 003cc4c010 Python: Feature python vector stores preb (#12271)
### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->
Overhaul of the VectorStores to get it matching with dotnet and the
latest development there.

Closes: 
- #11938 
- #11598 
- #11597
- #11517 
- #10561 
- #10391 
- #9911 
- #9892 
- #10867 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

Many changes, some highlights:
- Moved from different vector fields types, to a single with a enum
first VectorStoreField()
- Renamed several items
- Made embeddinggenerrator a part of the vector field spec and do
automatic vectorization from there or from the same param on a
collection
- Adds hybrid search using the same setup
- Removed the intermediate TextSeachVectorSearch object need, by
allowing `create_search_function` directly on a collection

Will write out full changes in a migration guide in the docs.

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
2025-06-19 18:34:59 +00:00

251 lines
5.9 KiB
TOML

[project]
name = "semantic-kernel"
description = "Semantic Kernel Python SDK"
authors = [{ name = "Microsoft", email = "[email protected]"}]
readme = "README.md"
# Version read from __version__ field in __init__.py by Flit
dynamic = ["version"]
requires-python = ">=3.10"
license = {file = "LICENSE"}
urls.homepage = "https://learn.microsoft.com/en-us/semantic-kernel/overview/"
urls.source = "https://github.com/microsoft/semantic-kernel/tree/main/python"
urls.release_notes = "https://github.com/microsoft/semantic-kernel/releases?q=tag%3Apython-1&expanded=true"
urls.issues = "https://github.com/microsoft/semantic-kernel/issues"
classifiers = [
"License :: OSI Approved :: MIT License",
"Development Status :: 5 - Production/Stable",
"Intended Audience :: Developers",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Framework :: Pydantic :: 2",
"Typing :: Typed",
]
dependencies = [
# azure agents
"azure-ai-projects >= 1.0.0b11",
"azure-ai-agents >= 1.1.0b1",
"aiohttp ~= 3.8",
"cloudevents ~=1.0",
"pydantic >=2.0,!=2.10.0,!=2.10.1,!=2.10.2,!=2.10.3,<2.12",
"pydantic-settings ~= 2.0",
"defusedxml ~= 0.7",
# azure identity
"azure-identity >= 1.13",
# embeddings
"numpy >= 1.25.0; python_version < '3.12'",
"numpy >= 1.26.0; python_version >= '3.12'",
# openai connector
"openai >= 1.67",
# openapi and swagger
"openapi_core >= 0.18,<0.20",
"websockets >= 13, < 16",
"aiortc>=1.9.0",
# OpenTelemetry
"opentelemetry-api ~= 1.24",
"opentelemetry-sdk ~= 1.24",
"prance >= 23.6.21,< 25.4.9",
# templating
"pybars4 ~= 0.9",
"jinja2 ~= 3.1",
"nest-asyncio ~= 1.6",
"scipy>=1.15.1",
"websockets >= 13, < 16",
"aiortc>=1.9.0",
# Protobuf
"protobuf",
# explicit typing extensions
"typing-extensions>=4.13",
]
### Optional dependencies
[project.optional-dependencies]
anthropic = [
"anthropic ~= 0.32"
]
autogen = [
"autogen-agentchat >= 0.2, <0.4"
]
aws = [
"boto3>=1.36.4,<1.39.0",
]
azure = [
"azure-ai-inference >= 1.0.0b6",
"azure-core-tracing-opentelemetry >= 1.0.0b11",
"azure-search-documents >= 11.6.0b4",
"azure-cosmos ~= 4.7"
]
chroma = [
"chromadb >= 0.5,< 1.1"
]
dapr = [
"dapr>=1.14.0",
"dapr-ext-fastapi>=1.14.0",
"flask-dapr>=1.14.0",
]
faiss = [
"faiss-cpu>=1.10.0"
]
google = [
"google-cloud-aiplatform == 1.97.0",
"google-generativeai ~= 0.8"
]
hugging_face = [
"transformers[torch] ~= 4.28",
"sentence-transformers >= 2.2,< 5.0",
"torch == 2.7.1"
]
mcp = [
"mcp>=1.8",
]
milvus = [
"pymilvus >= 2.3,< 2.6",
"milvus >= 2.3,<2.3.8; platform_system != 'Windows'"
]
mistralai = [
"mistralai >= 1.2,< 2.0"
]
mongo = [
"pymongo >= 4.8.0, < 4.13",
"motor >= 3.3.2,< 3.8.0"
]
notebooks = [
"ipykernel ~= 6.29"
]
ollama = [
"ollama ~= 0.4"
]
onnx = [
"onnxruntime-genai ~= 0.7"
]
pandas = [
"pandas ~= 2.2"
]
pinecone = [
"pinecone[asyncio, grpc] ~= 7.0"
]
postgres = [
"psycopg[binary,pool] ~= 3.2"
]
qdrant = [
"qdrant-client ~= 1.9"
]
redis = [
"redis[hiredis] ~= 6.0",
"types-redis ~= 4.6.0.20240425",
"redisvl ~= 0.4"
]
realtime = [
"websockets >= 13, < 16",
"aiortc>=1.9.0",
]
sql = [
"pyodbc >= 5.2"
]
usearch = [
"usearch ~= 2.16",
"pyarrow >= 12.0,< 21.0"
]
weaviate = [
"weaviate-client>=4.10,<5.0",
]
[tool.uv]
prerelease = "if-necessary-or-explicit"
dev-dependencies = [
"pre-commit ~= 3.7",
"ipykernel ~= 6.29",
"nbconvert ~= 7.16",
"pytest ~= 8.2",
"pytest-xdist[psutil] ~= 3.6",
"pytest-cov >= 5.0",
"pytest-asyncio ~= 0.24",
"pytest-timeout>=2.3.1",
"snoop ~= 0.4",
"mypy >= 1.10",
"types-PyYAML ~= 6.0.12.20240311",
"ruff ~= 0.9"
]
environments = [
"sys_platform == 'darwin'",
"sys_platform == 'linux'",
"sys_platform == 'win32'"
]
[tool.pytest.ini_options]
testpaths = 'tests'
addopts = "-ra -q -r fEX"
asyncio_mode = "auto"
asyncio_default_fixture_loop_scope = "function"
filterwarnings = [
'ignore:.*FunctionChoiceBehavior.*:DeprecationWarning'
]
timeout = 120
markers = [
"ollama: mark a test as requiring the Ollama service (use \"not ollama\" to skip those tests)",
"onnx: mark a test as requiring the Onnx service (use \"not onnx\" to skip those tests)"
]
[tool.ruff]
line-length = 120
target-version = "py310"
include = ["*.py", "*.pyi", "**/pyproject.toml", "*.ipynb"]
preview = true
[tool.ruff.lint]
fixable = ["ALL"]
unfixable = []
select = [
"D", #pydocstyle checks
"E", #error checks
"F", #pyflakes checks
"I", #isort
"CPY", #copyright
"ISC", #implicit string concat
"INP", #implicit namespace package
"RSE", #raise exception parantheses check
"RET", #flake8-return check
"SIM", #flake8-simplify check
"TD", #todos
"FIX", #fixme checks
"ERA", #remove connected out code
"RUF" #RUF specific rules
]
ignore = [
"D100", #allow missing docstring in public module
"D104", #allow missing docstring in public package
"D418", #allow docstring on overloaded function
"TD003", #allow missing link to todo issue
"FIX002" #allow todo
]
[tool.ruff.format]
docstring-code-format = true
[tool.ruff.lint.pydocstyle]
convention = "google"
[tool.ruff.lint.per-file-ignores]
# Ignore all directories named `tests` and `samples`.
"tests/**" = ["D", "INP", "TD", "ERA001", "RUF"]
"samples/**" = ["D", "INP", "ERA001", "RUF"]
# Ignore all files that end in `_test.py`.
"*_test.py" = ["D"]
"*.ipynb" = ["CPY", "E501"]
[tool.ruff.lint.flake8-copyright]
notice-rgx = "^# Copyright \\(c\\) Microsoft\\. All rights reserved\\."
min-file-size = 1
[tool.bandit]
targets = ["semantic_kernel"]
exclude_dirs = ["tests"]
[tool.flit.module]
name = "semantic_kernel"
[build-system]
requires = ["flit-core >= 3.9,<4.0"]
build-backend = "flit_core.buildapi"