> ## 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 Datasets

> Datasets in cognee-rust: the scope every memory operation works in, with deterministic ids.

## What is a dataset

A dataset is a named container for data and the memory built from it. It is the scope that add, cognify, search, improve and forget work in.

## How datasets work in Rust

A **Dataset** is the organizational scope for memory operations: named, owned by
a user, optionally tenant-scoped. A `data` row belongs to exactly
one dataset (`data.dataset_id`) and gets a random `uuid4` id, so the same
content added to two datasets is two rows. add / cognify / search / delete all
operate within a dataset scope. Dataset IDs are deterministic (UUID5 of name,
owner and tenant) for cross-SDK reproducibility.

Rust: `Dataset` in [`cognee-models`](https://github.com/topoteretes/cognee-rs/blob/main/crates/models/); lifecycle helpers in
`DatasetManager` ([`cognee`](https://github.com/topoteretes/cognee-rs/blob/main/crates/lib/) `api::datasets`).

## Related

> [card] [Datasets and access](https://docs.cognee.ai/rust/configuration/datasets-and-access.md)
>
> Users, tenants and per-dataset storage

> [card] [Forget](https://docs.cognee.ai/rust/core-concepts/main-operations/forget.md)
>
> Remove a dataset

> [card] [Add](https://docs.cognee.ai/rust/core-concepts/main-operations/legacy-operations/add.md)
>
> Put data in a dataset


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