nw9663644-eng opened a new pull request, #359: URL: https://github.com/apache/hugegraph-ai/pull/359
## Purpose Closes #343. This PR makes the graph extraction split type configurable instead of always forcing `document`. ## Changes * Added shared valid split type constants for `document`, `paragraph`, and `sentence`. * Added `split_type` to `GraphExtractFlow.prepare()` and `build_flow()`, defaulting to `document`. * Updated `extract_graph()` to accept and forward the selected split type. * Added a demo dropdown for graph extraction split type. * Logged graph extraction `chunk_count` after splitting. * Added tests for default behavior, non-default split types, invalid split type handling, helper forwarding, and chunk count logging. ## Tests * `uv run ruff format --check .` * `uv run pytest src/tests/document/test_graph_extract_configurable_split.py` * `uv run pytest src/tests/document` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
