Chris Coutinho
6fe5596c13
Replace custom keyword/fuzzy search algorithms with industry-standard BM25 sparse vectors, combined with dense semantic vectors using Qdrant's native Reciprocal Rank Fusion (RRF). This consolidates search architecture and improves relevance for both semantic and keyword queries. Key changes: - Add fastembed dependency for BM25 sparse vector generation - Update Qdrant collection schema to support named vectors (dense + sparse) - Create BM25SparseEmbeddingProvider using FastEmbed's Qdrant/bm25 model - Implement BM25HybridSearchAlgorithm with native Qdrant RRF prefetch - Update document processor to generate both dense and sparse embeddings - Simplify nc_semantic_search() tool to use BM25 hybrid only - Remove legacy keyword.py, fuzzy.py, and custom hybrid.py (736 lines) - Update ADR-014 with implementation notes and test results Benefits: - Consolidated architecture (single Qdrant database) - Native database-level RRF fusion (more efficient) - Industry-standard BM25 (replaces brittle custom keyword search) - Better relevance across semantic and keyword queries - Simplified codebase (-285 net lines) Tests: All 125 tests passing (118 unit, 7 integration) Implements ADR-014: Replace Custom Keyword Search with BM25 Hybrid Search 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
127 lines
4.2 KiB
TOML
127 lines
4.2 KiB
TOML
[project]
|
|
name = "nextcloud-mcp-server"
|
|
version = "0.36.0"
|
|
description = "Model Context Protocol (MCP) server for Nextcloud integration - enables AI assistants to interact with Nextcloud data"
|
|
authors = [
|
|
{name = "Chris Coutinho", email = "chris@coutinho.io"}
|
|
]
|
|
readme = "README.md"
|
|
license = {text = "AGPL-3.0-only"}
|
|
requires-python = ">=3.11"
|
|
keywords = ["nextcloud", "mcp", "model-context-protocol", "llm", "ai", "claude", "webdav", "caldav", "carddav"]
|
|
dependencies = [
|
|
"mcp[cli] (>=1.21,<1.22)",
|
|
"httpx (>=0.28.1,<0.29.0)",
|
|
"pillow (>=10.3.0,<12.0.0)", # Compatible with fastembed
|
|
"icalendar (>=6.0.0,<7.0.0)",
|
|
"pythonvcard4>=0.2.0",
|
|
"pydantic>=2.11.4",
|
|
"click>=8.1.8",
|
|
"caldav",
|
|
"pyjwt[crypto]>=2.8.0",
|
|
"aiosqlite>=0.20.0", # Async SQLite for refresh token storage
|
|
"authlib>=1.6.5",
|
|
"qdrant-client>=1.7.0",
|
|
"fastembed>=0.4.2", # BM25 sparse vector embeddings for hybrid search
|
|
# Observability dependencies
|
|
"prometheus-client>=0.21.0", # Prometheus metrics
|
|
"opentelemetry-api>=1.28.2", # OpenTelemetry API
|
|
"opentelemetry-sdk>=1.28.2", # OpenTelemetry SDK
|
|
"opentelemetry-instrumentation-asgi>=0.49b2", # Auto-instrument ASGI/Starlette
|
|
"opentelemetry-instrumentation-httpx>=0.49b2", # Auto-instrument httpx client
|
|
"opentelemetry-instrumentation-logging>=0.49b2", # Logging integration
|
|
"opentelemetry-exporter-otlp-proto-grpc>=1.28.2", # OTLP gRPC exporter
|
|
"python-json-logger>=3.2.0", # Structured JSON logging
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Intended Audience :: Developers",
|
|
"License :: OSI Approved :: GNU Affero General Public License v3",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Communications",
|
|
"Topic :: Internet :: WWW/HTTP",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/cbcoutinho/nextcloud-mcp-server"
|
|
Documentation = "https://github.com/cbcoutinho/nextcloud-mcp-server#readme"
|
|
Repository = "https://github.com/cbcoutinho/nextcloud-mcp-server"
|
|
"Bug Tracker" = "https://github.com/cbcoutinho/nextcloud-mcp-server/issues"
|
|
Changelog = "https://github.com/cbcoutinho/nextcloud-mcp-server/blob/master/CHANGELOG.md"
|
|
|
|
[tool.pytest.ini_options]
|
|
anyio_mode = "auto"
|
|
addopts = "-p no:asyncio -x" # Disable pytest-asyncio plugin, use only anyio
|
|
log_cli = 1
|
|
log_cli_level = "ERROR"
|
|
log_level = "ERROR"
|
|
markers = [
|
|
"unit: Fast unit tests with mocked dependencies",
|
|
"integration: Integration tests requiring Docker containers",
|
|
"oauth: OAuth tests requiring Playwright (slowest)",
|
|
"smoke: Critical path smoke tests for quick validation",
|
|
"keycloak: OAuth tests that utilize keycloak external identity provider",
|
|
]
|
|
testpaths = [
|
|
"tests",
|
|
]
|
|
# Timeout settings to prevent tests from hanging indefinitely
|
|
timeout = 180 # 3 minutes default timeout per test (includes fixture setup)
|
|
timeout_func_only = false # Timeout includes fixture setup/teardown
|
|
|
|
[tool.commitizen]
|
|
name = "cz_conventional_commits"
|
|
tag_format = "v$version"
|
|
version_scheme = "pep440"
|
|
version_provider = "uv"
|
|
update_changelog_on_bump = true
|
|
major_version_zero = true
|
|
version_files = [
|
|
"charts/nextcloud-mcp-server/Chart.yaml:appVersion",
|
|
"charts/nextcloud-mcp-server/Chart.yaml:version"
|
|
]
|
|
ignored_tag_formats = [
|
|
"nextcloud-mcp-server-*"
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
extend-select = ["I"]
|
|
|
|
[tool.uv.sources]
|
|
caldav = { git = "https://github.com/cbcoutinho/caldav", branch = "feature/httpx" }
|
|
|
|
[build-system]
|
|
requires = ["uv_build>=0.9.4,<0.10.0"]
|
|
build-backend = "uv_build"
|
|
|
|
[tool.uv.build-backend]
|
|
module-name = "nextcloud_mcp_server"
|
|
module-root = ""
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"commitizen>=4.8.2",
|
|
"ipython>=9.2.0",
|
|
"playwright>=1.49.1",
|
|
"pytest>=8.3.5",
|
|
"pytest-cov>=6.1.1",
|
|
"pytest-mock>=3.15.1",
|
|
"pytest-playwright-asyncio>=0.7.1",
|
|
"pytest-timeout>=2.3.1",
|
|
"ruff>=0.11.13",
|
|
"reportlab>=4.0.0",
|
|
"ty>=0.0.1a25",
|
|
]
|
|
|
|
[project.scripts]
|
|
nextcloud-mcp-server = "nextcloud_mcp_server.cli:run"
|
|
|
|
[[tool.uv.index]]
|
|
name = "testpypi"
|
|
url = "https://test.pypi.org/simple/"
|
|
publish-url = "https://test.pypi.org/legacy/"
|
|
explicit = true
|