Metadata-Version: 2.4
Name: sharepoint-knowledge
Version: 0.2.1
Summary: SharePoint connector for the grounded-Q&A engine — site pages + document libraries, Entra device-code sign-in, local models, cited answers
License: Apache-2.0
Project-URL: Homepage, https://github.com/nkunal1992/agents
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: confluence-knowledge[files]>=0.5.1
Requires-Dist: msal>=1.31
Requires-Dist: httpx>=0.27
Requires-Dist: mcp>=1.8
Provides-Extra: models
Requires-Dist: confluence-knowledge[models]>=0.5.1; extra == "models"
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: ruff>=0.5; extra == "dev"
Requires-Dist: python-docx>=1.1; extra == "dev"
Requires-Dist: python-pptx>=1.0; extra == "dev"
Requires-Dist: openpyxl>=3.1; extra == "dev"
Requires-Dist: pypdf>=5.0; extra == "dev"

# sharepoint-knowledge

SharePoint connector on the shared grounded-Q&A engine — Site Pages +
document libraries (docx/pdf/pptx/xlsx/csv/txt/md/html), Entra device-code
sign-in, local models, cited answers. Same engine as
[`confluence-knowledge`](../confluence-knowledge) and
[`local-knowledge`](../local-knowledge).

- `sharepoint_knowledge/auth_sp.py` — MSAL device-code flow, token cache in
  the OS keyring (protected-file fallback), silent refresh
- `sharepoint_knowledge/client_sp.py` — GET-only Graph client; downloads go
  through `@microsoft.graph.downloadUrl` WITHOUT the Bearer header
- `sharepoint_knowledge/crawl_sp.py` — durable BFS site → pages + libraries
- `sharepoint_knowledge/server_sp.py` — the `sharepoint-knowledge/*` tools
- `sharepoint_knowledge/cli_sp.py` — setup/doctor/prepare-models/register/
  update/serve/clean

See `docs/sharepoint-knowledge.md` for the full guide.
