LlamaParse Extract API

openapi: 3.0.3
info:
  title: Llama Platform Agent Data Extract API
  version: 0.1.0
tags:
- name: Extract
paths:
  /api/v2/extract/schema/validation:
    post:
      tags:
      - Extract
      summary: Validate Extraction Schema
      description: Validate a JSON schema for extraction.
      operationId: validate_extraction_schema_api_v2_extract_schema_validation_post
      security:
      - HTTPBearer: []
      parameters:
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractV2SchemaValidateRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractV2SchemaValidateResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v2/extract/schema/generate:
    post:
      tags:
      - Extract
      summary: Generate Extraction Schema
      description: Generate a JSON schema and return a product configuration request.
      operationId: generate_extraction_schema_api_v2_extract_schema_generate_post
      security:
      - HTTPBearer: []
      parameters:
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractV2SchemaGenerateRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ConfigurationCreateRequest'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v2/extract:
    post:
      tags:
      - Extract
      summary: Create Extract Job
      description: 'Create an extraction job.


        Extracts structured data from a document using either a saved

        configuration or an inline JSON Schema.


        ## Input


        Provide exactly one of:

        - `configuration_id` — reference a saved extraction config

        - `configuration` — inline configuration with a `data_schema`


        ## Document input


        Set `file_input` to a file ID (`dfl-...`) or a

        completed parse job ID (`pjb-...`).


        The job runs asynchronously. Poll `GET /extract/{job_id}` or

        register a webhook to monitor completion.'
      operationId: create_extract_job_api_v2_extract_post
      security:
      - HTTPBearer: []
      parameters:
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractV2JobCreate'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractV2Job'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    get:
      tags:
      - Extract
      summary: List Extract Jobs
      description: 'List extraction jobs with optional filtering and pagination.


        Filter by `configuration_id`, `status`, `file_input`,

        or creation date range. Results are returned newest-first.

        Use `expand=configuration` to include the full configuration used,

        and `expand=extract_metadata` for per-field metadata.'
      operationId: list_extract_jobs_api_v2_extract_get
      security:
      - HTTPBearer: []
      parameters:
      - name: document_input_type
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by document input type (file_id or parse_job_id)
          title: Document Input Type
        description: Filter by document input type (file_id or parse_job_id)
      - name: file_input
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by file input value
          title: File Input
        description: Filter by file input value
      - name: document_input_value
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: 'Deprecated: use file_input instead'
          deprecated: true
          title: Document Input Value
        description: 'Deprecated: use file_input instead'
        deprecated: true
      - name: status
        in: query
        required: false
        schema:
          anyOf:
          - enum:
            - PENDING
            - THROTTLED
            - RUNNING
            - COMPLETED
            - FAILED
            - CANCELLED
            type: string
          - type: 'null'
          description: Filter by status
          title: Status
        description: Filter by status
      - name: page_size
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: 'null'
          description: Number of items per page
          title: Page Size
        description: Number of items per page
      - name: page_token
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Token for pagination
          title: Page Token
        description: Token for pagination
      - name: job_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
          - type: 'null'
          description: Filter by specific job IDs
          title: Job Ids
        description: Filter by specific job IDs
      - name: expand
        in: query
        required: false
        schema:
          type: array
          items:
            type: string
          description: 'Additional fields to include: configuration, extract_metadata'
          title: Expand
        description: 'Additional fields to include: configuration, extract_metadata'
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: configuration_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by configuration ID
          examples:
          - cfg-11111111-2222-3333-4444-555555555555
          title: Configuration Id
        description: Filter by configuration ID
      - name: created_at_on_or_after
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: Include items created at or after this timestamp (inclusive)
          title: Created At On Or After
        description: Include items created at or after this timestamp (inclusive)
      - name: created_at_on_or_before
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: Include items created at or before this timestamp (inclusive)
          title: Created At On Or Before
        description: Include items created at or before this timestamp (inclusive)
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractV2JobQueryResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v2/extract/{job_id}:
    get:
      tags:
      - Extract
      summary: Get Extract Job
      description: 'Get a single extraction job by ID.


        Returns the job status and results when complete.

        Use `expand=configuration` to include the full configuration used,

        and `expand=extract_metadata` for per-field metadata.'
      operationId: get_extract_job_api_v2_extract__job_id__get
      security:
      - HTTPBearer: []
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
          title: Job Id
      - name: expand
        in: query
        required: false
        schema:
          type: array
          items:
            type: string
          description: 'Additional fields to include: configuration, extract_metadata'
          title: Expand
        description: 'Additional fields to include: configuration, extract_metadata'
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractV2Job'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Extract
      summary: Delete Extract Job
      description: Delete an extraction job and its results.
      operationId: delete_extract_job_api_v2_extract__job_id__delete
      security:
      - HTTPBearer: []
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
          title: Job Id
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v2/extract/{job_id}/cancel:
    post:
      tags:
      - Extract
      summary: Cancel Extract Job
      description: 'Cancel a running extraction job.


        Stops processing and marks the job as CANCELLED. Returns the updated job. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled.'
      operationId: cancel_extract_job_api_v2_extract__job_id__cancel_post
      security:
      - HTTPBearer: []
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
          title: Job Id
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractV2Job'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    ExtractV2Parameters:
      properties:
        target_pages:
          anyOf:
          - type: string
          - type: 'null'
          title: Target Pages
          description: Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.
          examples:
          - 1,3,5-7
          - 1-3,8-10
        max_pages:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: Max Pages
          description: Maximum number of pages to process. Omit for no limit.
          examples:
          - 10
        tier:
          type: string
          enum:
          - cost_effective
          - agentic
          title: Tier
          description: 'Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page)'
          default: cost_effective
          examples:
          - cost_effective
          - agentic
        version:
          type: string
          title: Version
          description: Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date.
          default: latest
          examples:
          - latest
        data_schema:
          additionalProperties:
            anyOf:
            - additionalProperties: true
              type: object
            - items: {}
              type: array
            - type: string
            - type: integer
            - type: number
            - type: boolean
            - type: 'null'
          type: object
          title: Data Schema
          description: JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.
        extraction_target:
          type: string
          enum:
          - per_doc
          - per_page
          - per_table_row
          title: Extraction Target
          description: 'Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row'
          default: per_doc
          examples:
          - per_doc
          - per_page
          - per_table_row
        system_prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: System Prompt
          description: Custom system prompt to guide extraction behavior
          examples:
          - Extract all monetary values in USD. If a currency is not specified, assume USD.
        cite_sources:
          type: boolean
          title: Cite Sources
          description: Include citations in results
          default: false
        confidence_scores:
          type: boolean
          title: Confidence Scores
          description: Include confidence scores in results
          default: false
        parse_tier:
          anyOf:
          - type: string
          - type: 'null'
          title: Parse Tier
          description: Parse tier to use before extraction. Defaults to the extract tier if not specified.
          examples:
          - fast
          - cost_effective
        parse_config_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Parse Config Id
          description: Saved parse configuration ID to control how the document is parsed before extraction
          examples:
          - cfg-11111111-2222-3333-4444-555555555555
        product_type:
          type: string
          const: extract_v2
          title: Product Type
          description: Product type.
      type: object
      required:
      - data_schema
      - product_type
      title: ExtractV2Parameters
      description: Typed parameters for an *extract v2* product configuration.
    SplitV1Parameters:
      properties:
        categories:
          items:
            $ref: '#/components/schemas/SplitCategory'
          type: array
          maxItems: 50
          minItems: 1
          title: Categories
          description: Categories to split documents into.
        splitting_strategy:
          $ref: '#/components/schemas/SplitStrategy'
          description: Strategy for splitting documents.
        product_type:
          type: string
          const: split_v1
          title: Product Type
          description: Product type.
      type: object
      required:
      - categories
      - product_type
      title: SplitV1Parameters
      description: Typed parameters for a *split v1* product configuration.
    ExtractV2SchemaGenerateRequest:
      properties:
        name:
          anyOf:
          - type: string
            maxLength: 255
          - type: 'null'
          title: Name
          description: Name for the generated configuration (auto-generated if omitted)
          examples:
          - invoice_extraction
        prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: Prompt
          description: Natural language description of the data structure to extract
          examples:
          - Extract vendor name, invoice number, line items, and total amount
        file_id:
          anyOf:
          - type: string
          - type: 'null'
          title: File Id
          description: Optional file ID to analyze for schema generation
          examples:
          - dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee
        data_schema:
          anyOf:
          - additionalProperties:
              anyOf:
              - additionalProperties: true
                type: object
              - items: {}
                type: array
              - type: string
              - type: integer
              - type: number
              - type: boolean
              - type: 'null'
            type: object
          - type: 'null'
          title: Data Schema
          description: Optional schema to validate, refine, or extend
      type: object
      title: ExtractV2SchemaGenerateRequest
      description: Request schema for generating an extraction schema.
      examples:
      - name: invoice_extraction
        prompt: Extract vendor name, invoice number, date, line items with descriptions and amounts, and total amount from invoices.
    ClassifyV2Rule:
      properties:
        type:
          type: string
          maxLength: 50
          minLength: 1
          title: Type
          description: Document type to assign when rule matches
          examples:
          - invoice
          - receipt
          - contract
          - report
          - proposal
        description:
          type: string
          maxLength: 500
          minLength: 10
          title: Description
          description: Natural language criteria for matching this rule
          examples:
          - contains invoice number, line items, and total amount
          - purchase receipt with transaction info and merchant details
          - legal contract with terms, conditions, and signatures
      type: object
      required:
      - type
      - description
      title: ClassifyV2Rule
      description: A rule for classifying documents.
    ExtractV2JobMetadata:
      properties:
        usage:
          anyOf:
          - $ref: '#/components/schemas/ExtractJobUsage'
          - type: 'null'
          description: Usage metrics
      additionalProperties: true
      type: object
      title: ExtractV2JobMetadata
      description: Job-level metadata.
    UntypedParameters:
      properties:
        product_type:
          type: string
          const: unknown
          title: Product Type
          description: Product type.
      additionalProperties: true
      type: object
      required:
      - product_type
      title: UntypedParameters
      description: 'Catch-all for configurations without a dedicated typed schema.


        Accepts arbitrary JSON fields alongside ``product_type``.'
    LlamaParseSpatialTextOptions:
      properties:
        preserve_layout_alignment_across_pages:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Preserve Layout Alignment Across Pages
          description: Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes
        preserve_very_small_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Preserve Very Small Text
          description: Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out
        do_not_unroll_columns:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Do Not Unroll Columns
          description: Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers
      additionalProperties: false
      type: object
      title: LlamaParseSpatialTextOptions
      description: 'Spatial text output options for preserving document layout.


        Spatial text maintains the visual positioning of text elements, useful for

        documents where layout conveys meaning (forms, tables, multi-column layouts).'
    LlamaParseProcessingControl:
      properties:
        timeouts:
          $ref: '#/components/schemas/LlamaParseTimeouts'
          description: Timeout settings for job execution. Increase for large or complex documents
        job_failure_conditions:
          $ref: '#/components/schemas/LlamaParseJobFailureConditions'
          description: Quality thresholds that determine when a job should fail vs complete with partial results
      additionalProperties: false
      type: object
      title: LlamaParseProcessingControl
      description: Job processing controls for timeouts and failure handling.
    LlamaParseFastOptions:
      properties: {}
      additionalProperties: false
      type: object
      title: LlamaParseFastOptions
      description: 'Options for fast tier parsing (rule-based, no AI).


        Fast tier uses deterministic algorithms for text extraction without AI enhancement.

        It''s the fastest and most cost-effective option, best suited for simple documents

        with standard layouts. Currently has no configurable options but reserved for

        future expansion.'
    LlamaParseInputOptions:
      properties:
        html:
          $ref: '#/components/schemas/LlamaParseHtmlOptions'
          description: HTML/web page parsing options (applies to .html, .htm files)
        pdf:
          $ref: '#/components/schemas/LlamaParsePdfOptions'
          description: PDF-specific parsing options (applies to .pdf files)
        spreadsheet:
          $ref: '#/components/schemas/LlamaParseSpreadsheetOptions'
          description: Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)
        presentation:
          $ref: '#/components/schemas/LlamaParsePresentationOptions'
          description: Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)
      additionalProperties: false
      type: object
      title: LlamaParseInputOptions
      description: 'Input format-specific parsing options.


        These options only apply when parsing documents of the corresponding format.

        LlamaParse automatically detects the input format based on file extension and content.'
    ExtractJobUsage:
      properties:
        num_pages_extracted:
          anyOf:
          - type: integer
          - type: 'null'
          title: Num Pages Extracted
          description: Number of pages extracted
      type: object
      title: ExtractJobUsage
      description: Extraction usage metrics.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    LlamaParseTables:
      properties:
        compact_markdown_tables:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Compact Markdown Tables
          description: Remove extra whitespace padding in markdown table cells for more compact output
        output_tables_as_markdown:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Output Tables As Markdown
          description: Output tables as markdown pipe tables instead of HTML <table> tags. Markdown tables are simpler but cannot represent complex structures like merged cells
        markdown_table_multiline_separator:
          anyOf:
          - type: string
          - type: 'null'
          title: Markdown Table Multiline Separator
          description: 'Separator string for multiline cell content in markdown tables. Example: ''<br>'' to preserve line breaks, '' '' to join with spaces'
        merge_continued_tables:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Merge Continued Tables
          description: Automatically merge tables that span multiple pages into a single table. The merged table appears on the first page with merged_from_pages metadata
      additionalProperties: false
      type: object
      title: LlamaParseTables
      description: Table formatting options for markdown output.
    ExtractV2SchemaValidateRequest:
      properties:
        data_schema:
          additionalProperties:
            anyOf:
            - additionalProperties: true
              type: object
            - items: {}
              type: array
            - type: string
            - type: integer
            - type: number
            - type: boolean
            - type: 'null'
          type: object
          title: Data Schema
          description: JSON Schema to validate for use with extract jobs
      type: object
      required:
      - data_schema
      title: ExtractV2SchemaValidateRequest
      description: Request schema for validating an extraction schema.
      examples:
      - data_schema:
          properties:
            vendor_name:
              description: Name of the vendor or supplier
              type: string
            invoice_number:
              description: Unique invoice identifier
              type: string
            total_amount:
              description: Total invoice amount in dollars
              type: number
            line_items:
              description: List of invoice line items
              items:
                properties:
                  description:
                    type: string
                  quantity:
                    type: integer
                  unit_price:
                    type: number
                required:
                - description
                - quantity
                - unit_price
                type: object
              type: array
          required:
          - vendor_name
          - invoice_number
          - total_amount
          type: object
    LlamaParsePresentationOptions:
      properties:
        out_of_bounds_content:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Out Of Bounds Content
          description: Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries
        skip_embedded_data:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Skip Embedded Data
          description: Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data
      additionalProperties: false
      type: object
      title: LlamaParsePresentationOptions
      description: Presentation (PowerPoint, Keynote, ODP) parsing options.
    LlamaParseJobFailureConditions:
      properties:
        allowed_page_failure_ratio:
          anyOf:
          - type: number
            maximum: 1.0
            exclusiveMinimum: 0.0
          - type: 'null'
          title: Allowed Page Failure Ratio
          description: 'Maximum ratio of pages allowed to fail before the job fails (0-1). Example: 0.1 means job fails if more than 10% of pages fail. Default is 0.05 (5%)'
        fail_on_image_extraction_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Image Extraction Error
          description: Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job
        fail_on_image_ocr_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Image Ocr Error
          description: Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image
        fail_on_markdown_reconstruction_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Markdown Reconstruction Error
          description: Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction
        fail_on_buggy_font:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Buggy Font
          description: Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters
      additionalProperties: false
      type: object
      title: LlamaParseJobFailureConditions
      description: 'Conditions that determine when a parsing job should fail vs complete with partial results.


        By default, jobs complete successfully even if some pages fail to parse.

        Use these settings to enforce stricter quality requirements.'
    LlamaParseOcrParameters:
      properties:
        languages:
          anyOf:
          - items:
              $ref: '#/components/schemas/ParserLanguages'
            type: array
          - type: 'null'
          title: Language

# --- truncated at 32 KB (95 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/llamaparse/refs/heads/main/openapi/llamaparse-extract-api-openapi.yml