# FalkorDB Docs > Official FalkorDB documentation — the high-performance graph database for GraphRAG, Cypher queries, and knowledge graphs powering accurate GenAI applications. > ## Agent Instructions > FalkorDB is a graph database that speaks the Redis protocol. Queries are issued as OpenCypher through the GRAPH.QUERY and GRAPH.RO_QUERY commands, not over Bolt or a SQL connection. > FalkorDB implements a subset of OpenCypher with proprietary extensions. Do not assume Neo4j-only syntax or procedures are available — check /cypher/cypher-support and /cypher/known-limitations before using a clause. > FalkorDB is the successor to RedisGraph, but they are separate products. Do not present RedisGraph commands, versions, or limitations as current FalkorDB behavior. > Use the official clients listed in /getting-started/clients rather than generic Redis or Neo4j drivers, and prefer the language the user is already working in. > Configuration parameters are set with GRAPH.CONFIG SET or at startup; cite the exact parameter name from /getting-started/configuration rather than inventing one. > This site covers four products: FalkorDB (core), FalkorDB Cloud, FalkorDB Enterprise, and the GraphRAG SDK. Name which one an answer applies to, since setup and operations differ. - [FalkorDB (193 pages)](https://docs.falkordb.com/_llms/falkor-db.md): The open source graph database, Cypher language, and tooling. - [FalkorDB Cloud (221 pages)](https://docs.falkordb.com/_llms/falkor-db-cloud.md): The managed FalkorDB service and its provisioning API. - [FalkorDB Enterprise (156 pages)](https://docs.falkordb.com/_llms/falkor-db-enterprise.md): Self-managed FalkorDB on your own Kubernetes clusters. ## GraphRAG SDK ### Documentation #### Home - [GraphRAG SDK](https://docs.falkordb.com/graphrag/index.md): The most accurate Graph RAG framework. Build knowledge graphs from documents and query them with natural language, on FalkorDB. - [Getting Started](https://docs.falkordb.com/graphrag/getting-started.md): A step-by-step tutorial for building a knowledge graph from documents and querying it with natural language. - [Architecture](https://docs.falkordb.com/graphrag/architecture.md): How the strategy-based ingestion and retrieval pipelines fit together. - [Reducing LLM Hallucinations](https://docs.falkordb.com/graphrag/reducing-llm-hallucinations.md): How grounded retrieval, source provenance, and an explicit abstention path make GraphRAG SDK answers verifiable instead of guessed. - [Configuration](https://docs.falkordb.com/graphrag/configuration.md): Comprehensive reference for every configurable component, its parameters, defaults, and usage. #### Pipeline - [Ingestion](https://docs.falkordb.com/graphrag/ingestion.md): How documents become a knowledge graph through the 9-step ingestion pipeline. - [Structured Ingestion](https://docs.falkordb.com/graphrag/structured-ingestion.md): Ingest CSVs and other tabular sources by declaring a mapping in the ontology, so rows become typed entities in the same graph as your documents. - [Extraction](https://docs.falkordb.com/graphrag/extraction.md): How raw text chunks are turned into entities and the relationships between them. - [Retrieval](https://docs.falkordb.com/graphrag/retrieval.md): How questions get answered using multiple parallel retrieval paths. - [Storage](https://docs.falkordb.com/graphrag/storage.md): How GraphStore, VectorStore, and EntityDeduplicator persist data in FalkorDB. - [Graph Schema](https://docs.falkordb.com/graphrag/graph-schema.md): The node types, edges, properties, and indexes that make up the knowledge graph. #### Ontology - [Ontology Discovery](https://docs.falkordb.com/graphrag/ontology-discovery.md): Bootstrap an ontology from a corpus and propose schema additions as new documents arrive. - [Ontology Evolution](https://docs.falkordb.com/graphrag/ontology-evolution.md): Safely evolve the schema of an already-populated knowledge graph. - [Incremental Updates](https://docs.falkordb.com/graphrag/incremental-updates.md): Update, delete, and re-index documents in an existing graph without a full re-ingest. #### Reference - [Strategy Reference](https://docs.falkordb.com/graphrag/strategies.md): Every swappable strategy ABC and its built-in implementations. - [Providers](https://docs.falkordb.com/graphrag/providers.md): Configure LLM and embedder providers, including LiteLLM and OpenRouter. - [API Reference](https://docs.falkordb.com/graphrag/api-reference.md): Complete reference for every public class and method exported by graphrag_sdk. - [Reliability and Grounding](https://docs.falkordb.com/graphrag/reliability-and-grounding.md): Grounded retrieval, source provenance, evidence trails, confidence thresholds, abstention and retrieval validation — mapped to the APIs that implement them. - [GraphRAG Accuracy Benchmark: FalkorDB vs Vector RAG for Reliable LLM Answers](https://docs.falkordb.com/graphrag/graphrag-accuracy-benchmark.md): GraphRAG-SDK on FalkorDB scores 71.48 overall on GraphRAG-Bench vs 55.39 for vector RAG with reranking — full models, datasets, evaluation definition, reproduction steps and limitations. - [Benchmark](https://docs.falkordb.com/graphrag/benchmark.md): GraphRAG-SDK results on GraphRAG-Bench, with full methodology and configuration. ## OpenAPI Specs - [admin-server](/enterprise/api-reference/admin-server.json) > The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages. ## Indexes - [FalkorDB (193 pages)](https://docs.falkordb.com/_llms/falkor-db.md): The open source graph database, Cypher language, and tooling. - [FalkorDB / Documentation (140 pages)](https://docs.falkordb.com/_llms/falkor-db/documentation.md): Documentation for FalkorDB / Documentation. - [FalkorDB Cloud (221 pages)](https://docs.falkordb.com/_llms/falkor-db-cloud.md): The managed FalkorDB service and its provisioning API. - [FalkorDB Cloud / API Reference (209 pages)](https://docs.falkordb.com/_llms/falkor-db-cloud/api-reference.md): Documentation for FalkorDB Cloud / API Reference. - [FalkorDB Enterprise (156 pages)](https://docs.falkordb.com/_llms/falkor-db-enterprise.md): Self-managed FalkorDB on your own Kubernetes clusters.