Rhizome Ai Documents API

openapi: 3.2.0
info:
  title: Rhizome AI Documents API
  description: Search and retrieve regulatory and clinical documents via API. The Rhizome AI API exposes keyword search (BM25 ranking) over regulatory document corpora from health authorities (FDA, EMA, Health Canada, Swissmedic, MHRA, TGA, and others) and full-text page-by-page document retrieval. API access requires an enterprise plan.
  version: 1.0.0
  contact:
    name: Rhizome AI Support
    email: support@rhizomeai.com
    url: https://rhizomeai.com
  x-apievangelist-generated: '2026-07-21'
  x-apievangelist-method: generated
  x-apievangelist-source: https://docs.rhizomeai.com
servers:
- url: https://rhizomeai.com/api
  description: Production
security:
- apiKeyAuth: []
tags:
- name: Documents
  description: Search and retrieve regulatory and clinical documents.
paths:
  /search:
    post:
      operationId: searchDocuments
      summary: Search documents
      description: Search across regulatory documents with keyword matching (BM25 ranking) and get page-level results ordered by relevance score.
      tags:
      - Documents
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SearchRequest'
            example:
              query_text: FDA approval process
      responses:
        '200':
          description: Search results ordered by relevance.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SearchResponse'
        '400':
          description: Invalid request body.
        '401':
          description: Missing or invalid API key.
        '429':
          description: Rate limit exceeded (50 requests/minute).
        '500':
          description: Internal server error.
  /contents:
    post:
      operationId: getDocumentContents
      summary: Get document contents
      description: Retrieve the full text of any document, page by page, by document ID.
      tags:
      - Documents
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ContentsRequest'
            example:
              doc_id: nda/2017/208264Orig1s000ChemR.pdf
      responses:
        '200':
          description: Document contents by page.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ContentsResponse'
        '400':
          description: Invalid request body.
        '401':
          description: Missing or invalid API key.
        '404':
          description: Document not found.
        '429':
          description: Rate limit exceeded (50 requests/minute).
        '500':
          description: Internal server error.
components:
  schemas:
    SearchResponse:
      type: object
      properties:
        results:
          type: array
          description: Search results ordered by relevance score.
          items:
            $ref: '#/components/schemas/SearchResult'
        total:
          type: integer
          description: Total matching results, for pagination.
    ContentsResponse:
      type: object
      properties:
        doc_id:
          type: string
        dataset:
          type: string
        name:
          type: string
        url:
          type: string
        company:
          type: string
        year_decision:
          type: integer
        pages:
          type: array
          items:
            $ref: '#/components/schemas/DocumentPage'
        total_pages:
          type: integer
          description: Total page count for pagination.
    SearchRequest:
      type: object
      required:
      - query_text
      properties:
        query_text:
          type: string
          description: The search query text. Searches document content using BM25 ranking.
        top_k:
          type: integer
          description: Maximum results returned.
          default: 20
          minimum: 1
          maximum: 100
        offset:
          type: integer
          description: Results to skip for pagination.
          default: 0
          minimum: 0
        dataset_to_search:
          type: array
          items:
            type: string
          description: Filter by specific datasets; an empty array searches all available datasets.
        year_from:
          type: integer
          description: Filter results from this year onwards (inclusive).
        year_to:
          type: integer
          description: Filter results through this year (inclusive).
    ContentsRequest:
      type: object
      required:
      - doc_id
      properties:
        doc_id:
          type: string
          description: Document identifier from search results (e.g., file path or FDA URL).
        top_k:
          type: integer
          description: Maximum number of pages to return.
          default: 10
          minimum: 1
          maximum: 100
        offset:
          type: integer
          description: Number of pages to skip for pagination.
          default: 0
          minimum: 0
    SearchResult:
      type: object
      properties:
        id:
          type: string
        doc_id:
          type: string
        dataset:
          type: string
        page_num:
          type: integer
        score:
          type: number
        name:
          type: string
        url:
          type: string
        company:
          type: string
        year_decision:
          type: integer
        text:
          type: string
        highlight:
          type: string
    DocumentPage:
      type: object
      properties:
        page_num:
          type: integer
          description: Zero-indexed page number.
        text:
          type: string
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: API key authentication. Create a key at https://rhizomeai.com/api-keys and send it in the x-api-key header. API access requires an enterprise plan.