Delete Support Approach Analysis

[gona-sreelatha]

I’m planning to extend GraphRAG to support delete operations by introducing a custom workflow.

Proposed Approach

1. Delete the target document.
2. Delete its associated text_units.
3. Remove references to those text_units from entities and relationships.
   • If an entity/relationship has other text_unit references, update it accordingly.
   • If the entity/relationship is only linked to the deleted text_units, remove it entirely.
4. Re-run community generation and community summarization to ensure consistency.

Questions

1. Would this approach be sufficient to properly handle deletes?
2. Are there any pitfalls or edge cases I should watch out for?
3. Do you have any alternative suggestions or best practices for implementing deletes in GraphRAG?

I understand that if delete functionality were to be officially supported in the library, it would likely need to account for additional complexities such as handling covariates and providing more optimized delete strategies. My proposal here is focused only on an application-level implementation to support dynamic data. In my use case, I’m not working with covariates and I’m only generating default embeddings.
I would deeply appreciate any inputs, suggestions, and thoughts from maintainers and community.
Thanks for your input!

@natoverse @AlonsoGuevara @darthtrevino