Aleph Alpha Collection API

openapi: 3.2.0
info:
  title: Aleph Alpha Document Index Collection API
  version: 0.0.0
  description: 'The Document Index is a service that provides semantic search over your knowledge base. It

    takes care of the chunking and embedding of your documents, and it keeps these embeddings in

    sync when your documents change.

    '
  contact:
    email: support@aleph-alpha.com
servers:
- url: '{host}/v1/studio/search'
  variables:
    host:
      default: https://api.pharia.example.com
tags:
- name: Collection
  description: Management of document collections
paths:
  /collections/{namespace}:
    get:
      tags:
      - Collection
      security:
      - token: []
      summary: List collections in namespace.
      description: List all collections that exist in the given namespace
      parameters:
      - $ref: '#/components/parameters/namespace'
      responses:
        '200':
          description: A list of collection names
          content:
            application/json:
              schema:
                type: array
                items:
                  type: string
                example:
                - collection_1
                - collection_2
  /collections/{namespace}/{collection}:
    put:
      tags:
      - Collection
      security:
      - token: []
      summary: Create a collection.
      description: 'Creates a collection with a path given as namespace/collection.

        Collections need to be created explicitly before documents can be put into a collection.

        '
      parameters:
      - $ref: '#/components/parameters/namespace'
      - $ref: '#/components/parameters/collection'
      responses:
        '200':
          description: Collection successfully created.
    delete:
      tags:
      - Collection
      security:
      - token: []
      summary: Delete collection.
      description: 'Deletes a collection identified by the namespace/collection.

        If the delete request returns successfully, the collection is deleted, i.e. it cannot be found

        any more neither by collection-path nor through search/lookup. However if the delete request fails

        either deletion failed or the collection will be deleted eventually.

        '
      parameters:
      - $ref: '#/components/parameters/namespace'
      - $ref: '#/components/parameters/collection'
      responses:
        '200':
          description: Collection successfully deleted.
  /collections/{namespace}/{collection}/progress:
    get:
      tags:
      - Collection
      security:
      - token: []
      summary: Get count of all documents in a collection that are not yet embedded.
      description: 'Gets count of all documents in a collection that are saved in the knowledge base, but not embedded for search yet.

        The count is not exact but an upper boundary of the exact number of documents to be embedded.

        '
      parameters:
      - $ref: '#/components/parameters/namespace'
      - $ref: '#/components/parameters/collection'
      responses:
        '200':
          description: Number of unembedded documents
          content:
            application/json:
              schema:
                type: integer
  /collections/{namespace}/{collection}/transitioning:
    get:
      tags:
      - Collection
      security:
      - token: []
      summary: Get count of all documents in a collection that are not yet embedded or not yet archived.
      description: 'Gets count of all documents in a collection where the target state does not equal the current state.

        The count is not exact but an upper boundary of the exact number of documents to be embedded/archived.

        '
      parameters:
      - $ref: '#/components/parameters/namespace'
      - $ref: '#/components/parameters/collection'
      responses:
        '200':
          description: Number of unembedded documents
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/transitioningResult'
components:
  parameters:
    collection:
      description: 'Collection containing documents. A search/lookup request always refers to a single collection, i.e.

        only a single collection can be searched with a single search/lookup request. The name of the collection

        must be unique within a namespace.

        Collections may only contain alphanumeric characters (a-z, A-Z, -, . and 0-9) and cannot be longer

        then 100 characters.

        '
      name: collection
      in: path
      schema:
        type: string
        maxLength: '100'
        pattern: ^[a-zA-Z0-9\-\.]+$
      required: 'true'
      example: wikipedia-de
    namespace:
      description: 'Namespace for collections of documents. Namespaces support preventing naming conflicts

        for collections. A namespace typically corresponds to an organisation.

        Namespaces may only contain alphanumeric characters (a-z, A-Z, -, . and 0-9) and

        cannot be longer than 100 characters.

        '
      name: namespace
      in: path
      schema:
        type: string
        maxLength: '100'
        pattern: ^[a-zA-Z0-9\-\.]+$
      required: 'true'
      example: aleph-alpha
  schemas:
    transitioningResult:
      description: 'The result for a transitioning documents query.

        '
      type: object
      properties:
        currently_embedding:
          type: integer
        currently_archiving:
          type: integer
      required:
      - currently_embedding
      - currently_archiving
  securitySchemes:
    token:
      type: http
      scheme: bearer
      description: Can be generated in your [Aleph Alpha profile](https://app.aleph-alpha.com/profile)