Core API

This page lists the objects that most programs use. Each row gives the import line and links to the full reference for that package.

The top-level agrag package exports only __version__. Import each other name from the package in the table.

Entry points

Object	Import	Role
Graph	from agrag.ingestion import Graph	Opens a graph. Adds, updates, and deletes documents. Consolidates duplicates and detects communities. See agrag.ingestion.
GraphSchema, DEFAULT_SCHEMA, OPERATIONS, LEGAL	from agrag.common.data_models import DEFAULT_SCHEMA, GraphSchema, LEGAL, OPERATIONS	The entity types, relation types, and valid patterns of a graph. DEFAULT_SCHEMA has nine entity types and eight relation types. OPERATIONS and LEGAL add entity types to it. See agrag.common.
Neo4jGraphStore	from agrag.graphdb import Neo4jGraphStore, build_graph_store	The graph store. It reads the NEO4J_* settings. See agrag.graphdb.
build_embedder	from agrag.embedding import build_embedder	Builds a dense embedder from a model name. See agrag.embedding.
Extractors	from agrag.ingestion import GlinerExtractor, BAMLExtractor	Read one chunk and return entities and relations. GLiNER runs locally. BAML calls an LLM. Graph selects extractors by mode and can build an LLM extractor from environment settings. See Choose an extraction mode.
ErrorPolicy	from agrag.loaders import ErrorPolicy	The action for a source that fails: RAISE, SKIP, or QUARANTINE. See agrag.loaders.
SearchEngine, RetrievalSettings	from agrag.retrieval import SearchEngine, RetrievalSettings	Runs retrieval recipes over the graph. See agrag.retrieval.
Evidence functions	from agrag.evidence import discover, fetch, navigate, find_entities, explore, check_citations, render_citations, source_status	Find passages, fetch the exact text behind an evidence id, move between passages, find entities, and check citations. source_status reports a document's current, pending, failed, deleted, or unknown state. See agrag.evidence.
TaskMemory, DecisionMemory	from agrag.memory import TaskMemory, DecisionMemory	Record task events and steps, and record, replace, review, and search decisions. See agrag.memory.
build_agent	from agrag.agents import build_agent	Builds the task-scoped evidence agent. Accessing it needs the agents extra. See agrag.agents.
get_tracer	from agrag.observability import get_tracer	Returns the tracer you pass, or a no-op tracer. See agrag.observability.

Tracing

Components that record spans accept an OpenTelemetry Tracer in a tracer= argument. None uses a no-op tracer, so the component records no spans. Components do not all expose tracing.

Results and settings

Object	Import	Role
AddResult	from agrag.ingestion import AddResult	The counts and failures that Graph.add returns.
AgentRunResult	from agrag.agents import AgentRunResult	What an agent run returns: the answer with numbered sources, the status, the validated citations, the invalid citations, any recording failures, the task name with its last event number, and the messages.
AgentLLMSettings	from agrag.agents import AgentLLMSettings	The LLM clients that the agent uses.
SearchFilters	from agrag.retrieval import SearchFilters	Limits a search to labels, documents, or properties.

Environment variables for every settings class are in the Configuration reference.

Other packages

• agrag.candidates: list, approve, reject, and prune extraction candidates, and write schema patches.
• agrag.chunking: the chunkers, Chunking rules, and the default preset.
• agrag.eval: metrics that score answers, retrieval, and agent runs. Needs the eval extra.

Related

• Tutorial: Quickstart.
• How-to: Ingest documents, Retrieve and answer.
• Explanation: Architecture.