Cognee datasets API

openapi: 3.2.0
info:
  title: Cognee REST agents Datasets API
  description: 'The Cognee REST API provides endpoints for the complete AI memory lifecycle, including data ingestion, knowledge graph construction, and semantic retrieval. Core endpoints cover adding raw text or documents, triggering the cognify pipeline that extracts entities and relationships via LLM, executing multi-mode search queries, managing datasets, and creating agent identities. The API uses X-Api-Key header authentication for cloud deployments and Bearer token auth for self-hosted instances.

    '
  version: 1.0.0
  contact:
    name: Cognee Support
    url: https://docs.cognee.ai/api-reference/introduction
  license:
    name: Apache 2.0
    url: https://github.com/topoteretes/cognee/blob/main/LICENSE
servers:
- url: https://api.cognee.ai
  description: Cognee Cloud (managed)
- url: http://localhost:8000
  description: Self-hosted (Docker / local)
security:
- BearerAuth: []
- ApiKeyAuth: []
tags:
- name: datasets
  description: Dataset management and introspection
paths:
  /api/v1/datasets:
    get:
      operationId: getDatasets
      summary: List all accessible datasets
      description: 'Retrieves all datasets the authenticated user has read permission for, including metadata such as ID, name, creation time, and owner.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      responses:
        '200':
          description: List of datasets
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Dataset'
        '418':
          description: Error retrieving datasets
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
    post:
      operationId: createDataset
      summary: Create a new dataset
      description: 'Creates a new dataset with the specified name. If a dataset with the same name already exists for the user, returns the existing dataset. The user is automatically granted all permissions on the created dataset.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - name
              properties:
                name:
                  type: string
                  description: Name for the new dataset
                  example: my_documents
      responses:
        '200':
          description: Created or existing dataset
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '418':
          description: Error creating dataset
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
    delete:
      operationId: deleteAllDatasets
      summary: Delete all user datasets
      description: 'Permanently deletes all datasets and associated data owned by the authenticated user. If no datasets exist, this operation is a no-op.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      responses:
        '200':
          description: All datasets deleted
  /api/v1/datasets/status:
    get:
      operationId: getDatasetStatus
      summary: Get dataset processing status
      description: 'Retrieves the current processing status for one or more datasets. If one pipeline is specified, returns a flat {dataset_id: status} map. If multiple pipelines are specified, returns a nested {dataset_id: {pipeline: status}} map.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - name: dataset
        in: query
        style: form
        explode: true
        schema:
          type: array
          items:
            type: string
            format: uuid
        description: List of dataset UUIDs to check
      - name: pipeline
        in: query
        style: form
        explode: true
        schema:
          type: array
          items:
            type: string
            enum:
            - add_pipeline
            - cognify_pipeline
        description: Pipeline names to check (default cognify_pipeline)
      responses:
        '200':
          description: Status map for requested datasets
          content:
            application/json:
              schema:
                type: object
                additionalProperties:
                  type: string
                  enum:
                  - pending
                  - running
                  - completed
                  - failed
        '500':
          description: Error retrieving status
  /api/v1/datasets/{dataset_id}:
    delete:
      operationId: deleteDataset
      summary: Delete a dataset by ID
      description: 'Permanently deletes a dataset and all its associated data. Requires delete permissions on the dataset.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      responses:
        '200':
          description: Dataset deleted
        '404':
          description: Dataset not found or access denied
        '500':
          description: Error during deletion
  /api/v1/datasets/{dataset_id}/data:
    get:
      operationId: getDatasetData
      summary: List all data items in a dataset
      description: 'Returns metadata for all data items (documents, files, etc.) in the specified dataset. Each item includes name, type, MIME type, and storage location.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      responses:
        '200':
          description: List of data items
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/DataItem'
        '404':
          description: Dataset not found
        '500':
          description: Internal error
  /api/v1/datasets/{dataset_id}/data/{data_id}:
    delete:
      operationId: deleteDataItem
      summary: Delete a specific data item from a dataset
      description: 'Removes a specific data item from a dataset while keeping the dataset intact. Requires delete permissions on the dataset.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      - name: data_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
        description: Unique identifier of the data item
      responses:
        '200':
          description: Data item deleted
        '404':
          description: Dataset or data item not found
        '500':
          description: Error during deletion
  /api/v1/datasets/{dataset_id}/data/{data_id}/raw:
    get:
      operationId: downloadRawData
      summary: Download the raw data file for a data item
      description: 'Returns the original unprocessed data file for a specific data item. Supports local filesystem and S3 storage backends.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      - name: data_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
        description: Unique identifier of the data item
      responses:
        '200':
          description: Raw file download
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
        '404':
          description: Dataset or data item not found
        '501':
          description: Storage scheme not supported
  /api/v1/datasets/{dataset_id}/graph:
    get:
      operationId: getDatasetGraph
      summary: Get knowledge graph for a dataset
      description: 'Retrieves the knowledge graph visualization data for a specific dataset, including all nodes and edges representing entity relationships.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      responses:
        '200':
          description: Knowledge graph nodes and edges
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Graph'
        '404':
          description: Dataset not found
        '500':
          description: Error retrieving graph
  /api/v1/datasets/{dataset_id}/schema:
    get:
      operationId: getDatasetSchema
      summary: Get graph schema for a dataset
      description: Returns the stored graph schema and custom prompt for a dataset.
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      responses:
        '200':
          description: Dataset schema and custom prompt
          content:
            application/json:
              schema:
                type: object
                properties:
                  graph_schema:
                    type:
                    - object
                    - 'null'
                  custom_prompt:
                    type:
                    - string
                    - 'null'
        '404':
          description: Dataset not found
    put:
      operationId: updateDatasetSchema
      summary: Update graph schema for a dataset
      description: 'Store or update the graph schema and custom prompt for a dataset. Requires write permissions on the dataset.

        '
      tags:
      - datasets
      security:
      - BearerAuth: []
      - ApiKeyAuth: []
      parameters:
      - $ref: '#/components/parameters/DatasetId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                graph_schema:
                  type:
                  - object
                  - 'null'
                  description: JSON schema for the knowledge graph structure
                custom_prompt:
                  type:
                  - string
                  - 'null'
                  description: Custom extraction prompt for this dataset
      responses:
        '200':
          description: Schema updated
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
                    example: ok
        '404':
          description: Dataset not found
components:
  parameters:
    DatasetId:
      name: dataset_id
      in: path
      required: true
      schema:
        type: string
        format: uuid
      description: Unique identifier of the dataset
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Short error message
        detail:
          type:
          - string
          - 'null'
          description: Detailed error description
      required:
      - error
    DataItem:
      type: object
      properties:
        id:
          type: string
          format: uuid
        name:
          type: string
        created_at:
          type: string
          format: date-time
        updated_at:
          type:
          - string
          - 'null'
          format: date-time
        extension:
          type: string
        mime_type:
          type: string
        raw_data_location:
          type: string
        dataset_id:
          type: string
          format: uuid
      required:
      - id
      - name
      - created_at
      - extension
      - mime_type
      - raw_data_location
      - dataset_id
    GraphNode:
      type: object
      properties:
        id:
          type: string
          format: uuid
        label:
          type: string
        type:
          type: string
        properties:
          type: object
      required:
      - id
      - label
      - type
      - properties
    Dataset:
      type: object
      properties:
        id:
          type: string
          format: uuid
        name:
          type: string
        created_at:
          type: string
          format: date-time
        updated_at:
          type:
          - string
          - 'null'
          format: date-time
        owner_id:
          type: string
          format: uuid
      required:
      - id
      - name
      - created_at
      - owner_id
    Graph:
      type: object
      properties:
        nodes:
          type: array
          items:
            $ref: '#/components/schemas/GraphNode'
        edges:
          type: array
          items:
            $ref: '#/components/schemas/GraphEdge'
      required:
      - nodes
      - edges
    GraphEdge:
      type: object
      properties:
        source:
          type: string
          format: uuid
        target:
          type: string
          format: uuid
        label:
          type: string
      required:
      - source
      - target
      - label
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Bearer token authentication for self-hosted instances
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-Api-Key
      description: API key authentication for Cognee Cloud deployments
externalDocs:
  description: Cognee API Reference
  url: https://docs.cognee.ai/api-reference/introduction