graphrag
graphrag copied to clipboard
text unit sources are not deduplicated
Hello,
when creating the text unit sources in the LocalSearchMixedContext, the sources are not deduplicated:
While there is a text_unit_ids_set in the code, it is never used:
Line 335 of mixed_context.py
I fixed it by adding:
text_unit_ids_set.add(text_id)
in line 337.
tried to create a PR for the issue: https://github.com/microsoft/graphrag/pull/1468 My first PR, please be kind :)