> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Rust SDK Core Concepts

> The vocabulary behind cognee-rust: the stores that hold memory, the building blocks that produce it, and the terms shared across the API, CLI, and config.

The vocabulary behind cognee-rust: the stores that hold memory, the building
blocks that produce it, and the terms that show up across the API, CLI, and
config. This page is the map of the Core Concepts pages — API/type detail lives in rustdoc
(`cargo doc --no-deps --open`). For *what the system does* see
[operations](https://docs.cognee.ai/rust/core-concepts/main-operations/overview.md); for *how it fits together* see
[architecture](https://docs.cognee.ai/rust/core-concepts/architecture.md).

## Architecture: three stores

Cognee keeps memory in three complementary backends. Every cognify run writes to
all three; search reads across them.

| Store | Role | Crate | Default backend |
| - | - | - | - |
| **Relational** | Document tracking, deduplication, provenance/lineage, sessions | [`cognee-database`](https://github.com/topoteretes/cognee-rs/blob/main/crates/database/) | SQLite via SeaORM (Postgres supported) |
| **Vector** | Semantic similarity over embeddings (chunks, entities, summaries, edge types) | [`cognee-vector`](https://github.com/topoteretes/cognee-rs/blob/main/crates/vector/) | LanceDB embedded (brute-force on Android / `:memory:`; pgvector via feature) |
| **Graph** | Entity relationships — the knowledge graph itself | [`cognee-graph`](https://github.com/topoteretes/cognee-rs/blob/main/crates/graph/) | Embedded Ladybug |

Backend selection and connection settings are covered in
[tools/backends](https://docs.cognee.ai/rust/tools/backends.md) and
[configuration](https://docs.cognee.ai/rust/configuration.md); the layering is in
[architecture](https://docs.cognee.ai/rust/core-concepts/architecture.md).

## Building blocks

| Page | What it covers |
| - | - |
| [DataPoints](https://docs.cognee.ai/rust/core-concepts/building-blocks/datapoints.md) | The storage-layer unit every graph node embeds, with provenance and indexing |
| [Tasks](https://docs.cognee.ai/rust/core-concepts/building-blocks/tasks.md) | Reusable units of work in eight execution flavours |
| [Pipelines](https://docs.cognee.ai/rust/core-concepts/building-blocks/pipelines.md) | Ordered task sequences, and the add, cognify and search pipelines |
| [PipelineContext](https://docs.cognee.ai/rust/core-concepts/building-blocks/pipeline-context.md) | The run identity and data item every task can read |

## Operations

| Page | What it covers |
| - | - |
| [Operations](https://docs.cognee.ai/rust/core-concepts/main-operations/overview.md) | The memory API at a glance, additional operations, and the operation → interface map |
| [Remember](https://docs.cognee.ai/rust/core-concepts/main-operations/remember.md), [Recall](https://docs.cognee.ai/rust/core-concepts/main-operations/recall.md), [Improve](https://docs.cognee.ai/rust/core-concepts/main-operations/improve.md), [Forget](https://docs.cognee.ai/rust/core-concepts/main-operations/forget.md) | The memory API |
| [Add](https://docs.cognee.ai/rust/core-concepts/main-operations/legacy-operations/add.md), [Cognify](https://docs.cognee.ai/rust/core-concepts/main-operations/legacy-operations/cognify.md), [Search](https://docs.cognee.ai/rust/core-concepts/main-operations/legacy-operations/search.md), [Memify (removed)](https://docs.cognee.ai/rust/core-concepts/main-operations/legacy-operations/memify.md) | The lower-level pipeline |

## Key concepts

| Page | What it covers |
| - | - |
| [Data Flows](https://docs.cognee.ai/rust/core-concepts/data-flows.md) | How ingestion, session learning and self-improvement write memory, and how recall reads it |
| [Datasets](https://docs.cognee.ai/rust/core-concepts/further-concepts/datasets.md) | The scope every operation works in |
| [Sessions](https://docs.cognee.ai/rust/core-concepts/sessions-and-caching.md) | Temporary conversational memory, session context and personalization |
| [NodeSets](https://docs.cognee.ai/rust/core-concepts/further-concepts/node-sets.md) | Tags on ingested data, used to scope search |
| [Ontologies](https://docs.cognee.ai/rust/core-concepts/further-concepts/ontologies.md) | Grounding extracted entities in RDF/OWL knowledge |
| [Loaders & Chunkers](https://docs.cognee.ai/rust/core-concepts/further-concepts/loaders-and-chunkers.md) | Reading files at add and splitting text at cognify |

## See also

* [operations](https://docs.cognee.ai/rust/core-concepts/main-operations/overview.md) — what the pipelines and memory API actually do
* [configuration](https://docs.cognee.ai/rust/configuration.md) — env vars and runtime config for every concept above
* [architecture](https://docs.cognee.ai/rust/core-concepts/architecture.md) — crate layering and design patterns
* [tools/backends](https://docs.cognee.ai/rust/tools/backends.md) — choosing relational / vector / graph backends
* [roadmap/README.md](https://github.com/topoteretes/cognee-rs/blob/main/docs/roadmap/README.md) — what is partial or not yet implemented


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.