EOSC Data Commons Search

[project] requires-python = ">=3.10" name = "data-commons-search" description = "A Model Context Protocol (MCP) server to access data from various open-access data publishers, developed for the EOSC Data Commons project." readme = "README.md" license = { file = "LICENSE" } authors = [ { name = "Vincent Emonet", email = "vincent.emonet@gmail.com" }, ] maintainers = [ { name = "Vincent Emonet", email = "vincent.emonet@gmail.com" }, ] keywords = [ "EOSC", "Data Commons", "Search", "Datasets", "Tools", "MCP", ] classifiers = [ "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Programming Language :: Python :: 3.12", "Programming Language :: Python :: 3.13", ] dynamic = ["version"] dependencies = [ "mcp >=1.19.0", "pydantic >=2.12.0", "pydantic-settings >=2.11.0", "httpx >=0.28.1", "fastembed >=0.7.3", "opensearch-py >=3.0.0", ] [project.optional-dependencies] agent = [ "starlette >=0.48.0", "uvicorn[standard] >=0.38.0", "ag-ui-protocol >=0.1.9", "langchain >=1.0.2", "langchain-mcp-adapters >=0.1.10", "langchain-openai >=1.0.1", "langchain-groq >=1.0.0", # "langchain-huggingface", # This will install torch and many heavy nvidia dependencies ] gpu = [ "fastembed-gpu >=0.5.1", ] [dependency-groups] dev = [ "pytest >=8.4.2", "pytest-asyncio >=1.2.0", "pytest-cov >=7.0.0", "mypy >=1.18.0", "pre-commit >=4.3.0", "mcp[cli]", ] # # Required for onnxruntime-gpu on CUDA 12 # [tool.uv.pip] # extra-index-url = ["https://aiinfra.pkgs.visualstudio.com/Publicsrc/_packaging/onnxruntime-cuda-12/pypi/simple/"] [project.urls] Homepage = "https://github.com/EOSC-Data-Commons/data-commons-search" Documentation = "https://github.com/EOSC-Data-Commons/data-commons-search" History = "https://github.com/EOSC-Data-Commons/data-commons-search/releases" Tracker = "https://github.com/EOSC-Data-Commons/data-commons-search/issues" Source = "https://github.com/EOSC-Data-Commons/data-commons-search" [project.scripts] data-commons-search = "data_commons_search.mcp_server:cli" ## TOOLS [tool.hatch.version] path = "src/data_commons_search/__init__.py" [tool.hatch.build.targets.wheel] packages = ["src/data_commons_search"] [tool.hatch.metadata] allow-direct-references = true [tool.pytest.ini_options] asyncio_mode = "auto" asyncio_default_fixture_loop_scope="session" addopts = [ "-vvv", # Verbose level 3 "--durations=10", # Show 10 slowest tests durations "--cov=src", "--color=yes", "--cov-report=term-missing", ] [tool.mypy] files = ["src/"] strict = false implicit_reexport = true follow_imports = "normal" ignore_missing_imports = true pretty = true show_column_numbers = true warn_no_return = true warn_unused_ignores = true warn_redundant_casts = true disallow_untyped_defs = true disallow_any_generics = true disallow_untyped_calls = false # needed due to _eval() not being typed in rdflib [tool.ruff] target-version = "py310" line-length = 120 exclude = [ "**/__init__.py", ] [tool.ruff.lint] select = [ "I", # isort "N", # pep8-naming "S", # bandit "A", # flake8-builtins "YTT", # flake8-2020 "B", # flake8-bugbear "C", # flake8-comprehensions "ICN", # flake8-import-conventions "SIM", # flake8-simplify "TID", # flake8-tidy-imports "Q", # flake8-quotes # "FBT", # flake8-boolean-trap "F", # pyflakes "UP", # pyupgrade "E", # pycodestyle errors "W", # pycodestyle warnings "PLC", # pylint convention "PLE", # pylint error "PLW", # pylint warning "RUF", # ruff specific "T", ] ignore = [ "E501", # line too long "C901", # too complex "T201", # do not use print "B008", # do not perform function calls in argument defaults ] [tool.ruff.lint.per-file-ignores] "__init__.py" = ["I", "F401"] # module imported but unused # Tests can use magic values, assertions, and relative imports: "tests/*" = ["PLR2004", "S101", "S105", "TID252"] [tool.git-cliff.git] # NOTE: Add an exclamation mark in your commit message prefix to indicate a BREAKING change https://www.conventionalcommits.org # e.g. `feat!: changed things` or `feat(python)!: changed things` commit_parsers = [ { message = "^feat", group = "⛰️ Features" }, { message = "^fix", group = "🐛 Bug Fixes" }, { message = "^doc", group = "📚 Documentation" }, { message = "^perf", group = "⚡ Performance" }, { message = "^refactor", group = "🚜 Refactor" }, { message = "^style", group = "🎨 Styling" }, { message = "^test", group = "🧪 Testing" }, { message = "^ci", group = "⚙️ Continuous Integration" }, { message = "^chore\\(release\\): prepare for", skip = true }, { message = "^chore\\(deps\\)", skip = true }, { message = "^chore\\(pr\\)", skip = true }, { message = "^chore\\(pull\\)", skip = true }, { message = "^chore", group = "🛠️ Miscellaneous Tasks" }, { body = ".*security", group = "🛡️ Security" }, { message = "^revert", group = "◀️ Revert" }, ] conventional_commits = true filter_unconventional = false split_commits = false # Protect breaking changes from being skipped due to matching a skipping commit_parser protect_breaking_commits = false filter_commits = false tag_pattern = "v?[0-9].*" topo_order = false sort_commits = "oldest" [tool.git-cliff.changelog] header = """ # 🪵 Changelog\n """ # Template for the changelog: https://keats.github.io/tera/docs body = """ {% if version %}\ {% if previous.version %}\ ## [{{ version | trim_start_matches(pat="v") }}](<REPO>/compare/{{ previous.version }}..{{ version }}) - {{ timestamp | date(format="%Y-%m-%d") }} {% else %}\ ## [{{ version | trim_start_matches(pat="v") }}](<REPO>/tree/{{ version }}) - {{ timestamp | date(format="%Y-%m-%d") }} {% endif %}\ {% else %}\ ## [unreleased] {% endif %}\ {% for group, commits in commits | group_by(attribute="group") %} ### {{ group | upper_first }} {% for commit in commits %} - {% if commit.breaking %}[**breaking**] {% endif %}{{ commit.message | upper_first | trim }} - ([{{ commit.id | truncate(length=7, end="") }}](<REPO>/commit/{{ commit.id }}))\ {% endfor %} {% endfor %}\n """ trim = true footer = """ <!-- generated by git-cliff --> """ postprocessors = [ { pattern = '<REPO>', replace = "https://github.com/EOSC-Data-Commons/data-commons-search" }, ] [build-system] requires = ["hatchling"] build-backend = "hatchling.build"