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

# Ingest Manual Document

> Ingest a single document manually.

The document will be processed through the full pipeline:
1. Stored in PostgreSQL
2. Chunked into smaller pieces
3. Embedded with OpenAI embeddings
4. Entities and relations extracted
5. Knowledge graph updated in Neo4j

This is useful for:
- Testing with real transcripts
- Importing external documents
- Quick demos without OAuth setup



## OpenAPI

````yaml /openapi.json post /v1/ingest/manual/document
openapi: 3.1.0
info:
  title: Ontora API
  description: >-
    Ontora's public API. Covers interview campaigns, transcripts, synthesis
    reports, graph queries, webhooks, and workspace management. 


    **Authentication**: endpoints accept either a Clerk JWT (`Authorization:
    Bearer <token>`) or a workspace API key (`X-API-Key: ont_...`). Workspace
    keys are managed via `/v1/api-keys`.
  version: 0.1.0
servers: []
security:
  - ClerkJWT: []
  - WorkspaceApiKey: []
tags:
  - name: interviews
    description: Campaign CRUD, lifecycle, contacts, question sets.
  - name: campaign-insights
    description: Synthesis outputs — cartography, roadmap, personas, conversations.
  - name: interview-query
    description: Graph RAG query over campaign data.
  - name: interview-export
    description: Markdown / ZIP exports of transcripts and reports.
  - name: api-keys
    description: Manage workspace-scoped API keys for programmatic access.
  - name: webhook-endpoints
    description: Outbound webhook endpoints for automation.
  - name: booking
    description: Public self-scheduling endpoints for interview participants.
  - name: workspaces
    description: Workspace and membership management.
  - name: vaults
    description: Context vault management.
paths:
  /v1/ingest/manual/document:
    post:
      tags:
        - manual-ingest
      summary: Ingest Manual Document
      description: |-
        Ingest a single document manually.

        The document will be processed through the full pipeline:
        1. Stored in PostgreSQL
        2. Chunked into smaller pieces
        3. Embedded with OpenAI embeddings
        4. Entities and relations extracted
        5. Knowledge graph updated in Neo4j

        This is useful for:
        - Testing with real transcripts
        - Importing external documents
        - Quick demos without OAuth setup
      operationId: ingest_manual_document_v1_ingest_manual_document_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ManualIngestRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ManualIngestResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - HTTPBearer: []
components:
  schemas:
    ManualIngestRequest:
      properties:
        workspace_id:
          type: string
          format: uuid
          title: Workspace Id
          description: Target workspace
        vault_id:
          anyOf:
            - type: string
              format: uuid
            - type: 'null'
          title: Vault Id
          description: Optional vault to associate with
        content:
          type: string
          minLength: 10
          title: Content
          description: The text content to ingest
        title:
          type: string
          maxLength: 500
          minLength: 1
          title: Title
          description: Document title
        document_type:
          $ref: '#/components/schemas/ManualDocumentType'
          description: Type of document being ingested
          default: document
        author_name:
          anyOf:
            - type: string
            - type: 'null'
          title: Author Name
          description: Author name
        author_email:
          anyOf:
            - type: string
            - type: 'null'
          title: Author Email
          description: Author email
        source_url:
          anyOf:
            - type: string
            - type: 'null'
          title: Source Url
          description: Original source URL if applicable
        created_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Created At
          description: Original creation date
        tags:
          items:
            type: string
          type: array
          title: Tags
          description: Tags for categorization
        metadata:
          additionalProperties: true
          type: object
          title: Metadata
          description: Additional metadata
      type: object
      required:
        - workspace_id
        - content
        - title
      title: ManualIngestRequest
      description: Request to manually ingest a document.
    ManualIngestResponse:
      properties:
        document_id:
          type: string
          format: uuid
          title: Document Id
        status:
          type: string
          title: Status
        message:
          type: string
          title: Message
        processing_job_id:
          anyOf:
            - type: string
              format: uuid
            - type: 'null'
          title: Processing Job Id
      type: object
      required:
        - document_id
        - status
        - message
      title: ManualIngestResponse
      description: Response after manual ingestion.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ManualDocumentType:
      type: string
      enum:
        - transcript
        - notes
        - document
        - article
        - email
        - chat
      title: ManualDocumentType
      description: Types of manually ingested documents.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    ClerkJWT:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Clerk-issued RS256 JWT.
    WorkspaceApiKey:
      type: apiKey
      in: header
      name: X-API-Key
      description: 'Workspace-scoped API key (prefix: `ont_`).'
    HTTPBearer:
      type: http
      scheme: bearer

````