agrag.ingestion

The ingestion package.

Modules:

• community – Community detection: hierarchical Leiden over the entity graph.
• extract – The Extractor interface: reads one Chunk and produces an ExtractionResult.
• graph – The public Graph API for ingestion.
• materialize – Non-destructive match persistence and resolved-entity computation.
• merge – Merge mechanics: computing how a resolved group of mentions and entities combine.
• reports – Reports returned by Graph pipeline operations.
• resolve – Entity resolution public API.
• resolved_embeddings – Embedding and vector synchronization for materialized resolved entities.
• settings – Configuration for the Cutover Job crash-recovery machine.
• stats – Per-stage observability types for the ingestion pipeline.

Classes:

• AddResult – Graph.add()'s return type — one summary per pipeline stage.
• BAMLExtractor – Extracts with an LLM, via a BAML function and a runtime ClientRegistry.
• CommunityDetectionReport – Report from Graph.detect_communities().
• ConsolidationReport – Report from Graph.consolidate().
• EscalatingExtractor – Runs a cheap primary extractor first, escalating per chunk when it's weak.
• ExtractionLLMSettings – Env-backed LLM client config for the extraction role.
• Extractor – Reads one Chunk and produces the entities and relations it contains.
• ExtractorMissingExtraError – An Extractor needs a package extra that is not installed.
• GlinerExtractor – Extracts locally with a GLiNER2.5 model. No network call.
• Graph – A knowledge graph that a caller can open and add content to.
• ReevaluationReport – Report from Graph.reevaluate().
• UpdateResult – Summary of an update or soft deletion.