Pluggable Backends - Cognee Documentation

cognee-rust is built on trait abstractions so each storage/compute backend can be swapped via configuration. Pick providers with the env vars / config keys in Configuration; the trait + adapter detail is in rustdoc (cargo doc -p <crate> --no-deps --open).

Concern	Trait (crate)	Providers	Selected by
LLM	`Llm` (`cognee-llm`)	`OpenAIAdapter` (OpenAI/Ollama/vLLM/llama.cpp), `MockLlm` (`testing`)	`LLM_PROVIDER`, `LLM_MODEL`, `LLM_ENDPOINT`
Embeddings	`EmbeddingEngine` (`cognee-embedding`)	`OnnxEmbeddingEngine` (local BGE-Small), `OpenAICompatibleEmbeddingEngine`, `OllamaEmbeddingEngine`, `MockEmbeddingEngine`	`EMBEDDING_PROVIDER` (+ `MOCK_EMBEDDING`)
Vector DB	`VectorDB` (`cognee-vector`)	`LanceDbAdapter` (embedded, persistent, default on non-Android), `BruteForceVectorDB` (in-memory; Android or `:memory:`), `PgVectorAdapter` (feature `pgvector`), `MockVectorDB` (`testing`)	`VECTOR_DB_PROVIDER` (`lancedb`/`brute-force`/`pgvector`)
Graph DB	`GraphDBTrait` (`cognee-graph`)	`LadybugAdapter` (embedded), `PgGraphAdapter` (feature `postgres`)	`GRAPH_DATABASE_PROVIDER` (`ladybug`/`kuzu`/`postgres`)
Relational DB	`IngestDb`/`SearchHistoryDb`/`DeleteDb` (`cognee-database`)	`DatabaseConnection` — SQLite / Postgres via SeaORM	`DB_PROVIDER`, `DATABASE_URL`
File storage	`StorageTrait` (`cognee-storage`)	`LocalStorage` (`file://`), `MockStorage`	`STORAGE_BACKEND`
Session store	`SessionStore` (`cognee-session`)	`FsSessionStore`, `RedisSessionStore`, `SeaOrmSessionStore`	`COGNEE_SESSION_STORE` (server)
Ontology	`OntologyResolver` (`cognee-ontology`)	`RdfLibOntologyResolver`, `NoOpOntologyResolver`	`ONTOLOGY_RESOLVER`
Tokenizer (chunking)	`TokenCounter` (`cognee-chunking`)	`WordCounter`, `HuggingFaceTokenCounter` (feature), `TikTokenCounter` (feature)	`COGNEE_TOKEN_COUNTER`

Notes:

Embedded by default. A plain build runs entirely locally: LanceDB vector index, embedded Ladybug (graph), SQLite (relational), local file storage. The brute-force vector index is used on Android or with VECTOR_DB_URL=:memory:.
Feature gates. pgvector, pggraph/postgres, and the hf-tokenizer/tiktoken counters are cargo features, on by default in cognee-lib/cognee-cli — see Architecture: feature strategy.
Closed-source companions. Embedded Qdrant (cognee-vector-qdrant) and on-device LiteRT inference (cognee-llm-litert, Android) live in the closed cognee-cloud-rs repository and are not part of OSS.
Full Postgres stack (relational + graph + vector on one Postgres) is the one remaining adapter milestone — see roadmap/.

MockEmbeddingEngine, MockGraphDB, MockVectorDB, and MockStorage (the testing feature) back the test suite — see test patterns.