Crate graphrag 

graphrag

Meta-crate that re-exports graphrag_core for library users and provides the graphrag binary (backed by graphrag_cli).

Installation

cargo install graphrag

This installs the graphrag binary which is the full-featured TUI and CLI for GraphRAG operations.

Library usage

[dependencies]
graphrag = "0.1"

All types from graphrag-core are re-exported:

use graphrag::GraphRAG;

Modules

async_graphrag

Async GraphRAG implementation Async GraphRAG System

async_processing

Async processing pipelines Async processing utilities for GraphRAG operations

builder

Builder pattern implementations GraphRAG builder module

caching

Caching utilities for LLM responses High-performance LLM response caching system

config

Configuration management and loading

core

Core traits and types Core data structures and abstractions for GraphRAG

critic

RAG answer evaluation and criticism

embeddings

Embedding generation and providers Embedding generation for GraphRAG

entity

Entity extraction and management

evaluation

Evaluation framework for query results and pipeline validation Evaluation framework for GraphRAG system

generation

Text generation and LLM interactions (async feature only)

graph

Graph data structures and algorithms

incremental

Incremental graph updates Incremental Graph Updates

inference

Inference module for model predictions Implicit relationship inference system

lightrag

LightRAG dual-level retrieval optimization LightRAG: Simple and Fast Retrieval-Augmented Generation

monitoring

Monitoring, benchmarking, and performance tracking Monitoring and benchmarking utilities for GraphRAG

nlp

Natural language processing utilities Advanced NLP Module

ollama

Ollama LLM integration Ollama LLM integration

optimization

Graph optimization (weight optimization, DW-GRPO) Graph optimization module

parallel

Parallel processing utilities for GraphRAG

persistence

Persistence layer for knowledge graphs (workspace management always available) Persistence layer for GraphRAG knowledge graphs

pipeline

Data processing pipelines Pipeline Module

pipeline_executor

Composable pipeline executor for build-graph operations Composable pipeline executor for GraphRAG operations

prelude

Prelude module containing the most commonly used types

query

Query processing and execution

reranking

Reranking utilities for improving search result quality Reranking module for improving retrieval accuracy

retrieval

Retrieval strategies and implementations

rograg

ROGRAG (Robustly Optimized GraphRAG) implementation ROGRAG (Robustly Optimized GraphRAG) module - Reasoning on Graphs for RAG

storage

Storage backends and persistence Storage layer for GraphRAG

summarization

Text summarization capabilities

text

Text processing and chunking

vector

Vector operations and embeddings

Macros

config_error

Helper macros for creating specific error types

generation_error

Creates a generation error with a message

retrieval_error

Creates a retrieval error with a message

storage_error

Creates a storage error with a message

Structs

ChunkId

Unique identifier for text chunks

ConfidenceCrossEncoder

Confidence-based cross-encoder implementation (Restored Fallback)

Config

Configuration for the GraphRAG system

CrossEncoderConfig

Configuration for cross-encoder reranking

Document

A document in the system

DocumentId

Unique identifier for documents

DualLevelKeywords

Dual-level keywords for retrieval

DualLevelRetriever

LightRAG-style dual-level retriever

DualRetrievalConfig

Configuration for dual-level retrieval

DualRetrievalResults

Dual-level retrieval results

Entity

An entity extracted from text

EntityId

Unique identifier for entities

EntityMention

A mention of an entity in text

ErrorSuggestion

Structured suggestion for error recovery

Fact

Fact triple for knowledge graph

GraphRAG

Main GraphRAG system

GraphRAGBuilder

Builder for GraphRAG instances

HierarchicalCommunities

Hierarchical community detection results

HippoRAGConfig

Configuration for HippoRAG PPR retrieval

HippoRAGRetriever

HippoRAG retrieval system using Personalized PageRank

KeywordExtractor

Keyword extractor for dual-level retrieval

KeywordExtractorConfig

Configuration for keyword extraction

KnowledgeGraph

Knowledge graph containing entities and their relationships

LeidenCommunityDetector

Leiden community detection algorithm

LeidenConfig

Configuration for Leiden algorithm

MemoryStorage

In-memory storage implementation for development and testing

PageRankConfig

Configuration for PageRank algorithm

PageRankRetrievalSystem

High-performance PageRank-based retrieval system implementing fast-GraphRAG approach

PersonalizedPageRank

Personalized PageRank implementation with optimizations for graph retrieval

RankedResult

Result of cross-encoder reranking with confidence score

Relationship

Relationship between entities

RerankingStats

Statistics about reranking performance

ScoredResult

A result with multiple scoring signals

TextChunk

A chunk of text from a document

Enums

ErrorSeverity

Error severity levels for logging and monitoring

GraphRAGError

Main error type for the GraphRAG system

MergeStrategy

Strategy for merging high and low level results

Traits

CrossEncoder

Cross-encoder trait for reranking retrieved results

Embedder

Text embedding abstraction for converting text to vector representations

EntityExtractor

Entity extraction abstraction for identifying entities in text

ErrorContext

Trait for adding context to errors

GraphStore

Graph operations abstraction for knowledge graph management

LanguageModel

Large Language Model abstraction for text generation

Retriever

Text retrieval abstraction for finding relevant content

SemanticSearcher

Semantic search interface that combines embedder and vector store

Storage

Core storage abstraction for persisting and retrieving entities, documents, and graph data

VectorStore

Vector similarity search abstraction for finding similar embeddings

Type Aliases

Result

Convenient Result type alias