Skip to main content

agrag.ingestion.resolve.resolution.resolve_persisted

resolve_persisted(entities:list[Entity], *, graph_store:GraphStore, embedder:Embedder, vector_store:VectorStore | None, vector_collection:str, entity_labels:Sequence[str], tracer:Tracer | None, max_llm_pairs:int, error_policy:ErrorPolicy) -> tuple[ResolutionResult, list[StageFailure]]

Resolve persisted entities against each other.

ANN search bounds the pairs the resolver compares.

Parameters:

  • entities (list[Entity]) – The persisted entities to compare, all of one label.
  • graph_store (GraphStore) – Where the candidate and neighbor reads run.
  • embedder (Embedder) – Embeds entity names for candidate search and fuzzy review.
  • vector_store (VectorStore | None) – Optional vector store the candidate search reads.
  • vector_collection (str) – Collection name for the candidate search.
  • entity_labels (Sequence[str]) – The labels the schema defines.
  • tracer (Tracer | None) – Traces the resolver.
  • max_llm_pairs (int) – The most ambiguous pairs per label sent to the LLM.
  • error_policy (ErrorPolicy) – RAISE propagates a failed candidate read; any other policy records it and leaves that entity out of this pass.

Returns:

  • ResolutionResult – The resolver result, indexed like entities, and one StageFailure
  • list[StageFailure] – per entity whose candidate read failed.

Raises:

  • Exception – A candidate read failed and error_policy is RAISE.