Orbii PDFs API
The PDFs API from Orbii — 4 operation(s) for pdfs.
OpenAPI Specification
openapi: 3.0.0
info:
title: Orbii KSA Business Category Assignment PDFs API
description: API for managing transactions, clients, and companies.
version: 1.0.3
servers:
- url: https://api.sa.orbii.ai/
description: Production server
tags:
- name: PDFs
paths:
/pdf-list:
get:
summary: Retrieve the list of PDFs with metadata and client details
description: 'Fetches the list of PDFs along with their metadata and client details.
'
tags:
- PDFs
parameters:
- name: user
in: query
required: true
schema:
type: string
description: Database username for authentication
- name: password
in: query
required: true
schema:
type: string
description: Database password for authentication
responses:
'200':
description: A JSON array of PDF records
content:
application/json:
schema:
type: array
items:
type: object
properties:
client_name:
type: string
example: Orbii Corp
customer_id:
type: string
example: '123456'
foldername:
type: string
example: reports_2024
filename:
type: string
example: financial_report.pdf
extraction_date:
type: string
format: date-time
example: '2024-01-20T15:30:00Z'
pdf_producer:
type: string
example: Adobe Acrobat
content_creator:
type: string
example: Finance Team
creation_date:
type: string
format: date-time
example: '2023-12-15T10:00:00Z'
modification_date:
type: string
format: date-time
example: '2024-01-10T14:00:00Z'
modified:
type: boolean
example: true
'400':
description: Invalid request, missing parameters
'500':
description: Internal server error, database connection issue
/pdf-list-from-date:
get:
summary: Retrieve PDFs extracted on or after a specific datetime
description: 'Returns the list of PDFs and their metadata where the extraction date is greater than or equal to the given datetime. If no datetime is provided, it defaults to 2025-05-01 00:00:00.000.
'
tags:
- PDFs
parameters:
- name: datetime
in: query
description: 'The datetime filter (format: YYYY-MM-DD HH:MM:SS.sss). Defaults to 2025-05-01 00:00:00.000 if not provided.
'
required: false
schema:
type: string
example: '2025-05-01 00:00:00.000'
- name: user
in: query
description: Database username (optional; defaults to environment variable)
required: false
schema:
type: string
- name: password
in: query
description: Database password (optional; defaults to environment variable)
required: false
schema:
type: string
responses:
'200':
description: A JSON array of PDF records extracted on or after the specified datetime
content:
application/json:
schema:
type: array
items:
type: object
properties:
client_name:
type: string
example: Orbii Corp
customer_id:
type: string
example: '123456'
foldername:
type: string
example: reports_2025
filename:
type: string
example: financial_report.pdf
extraction_date:
type: string
format: date-time
example: '2025-05-01T00:00:00Z'
pdf_producer:
type: string
example: Adobe Acrobat
content_creator:
type: string
example: Finance Team
creation_date:
type: string
format: date-time
example: '2025-04-30T10:00:00Z'
modification_date:
type: string
format: date-time
example: '2025-05-01T14:00:00Z'
modified:
type: boolean
example: true
'400':
description: Invalid datetime format
content:
application/json:
schema:
type: object
properties:
error:
type: string
example: Invalid datetime format. Expected 'YYYY-MM-DD HH:MM:SS.sss'
'500':
description: Internal server error, e.g., database connection issue
content:
application/json:
schema:
type: object
properties:
error:
type: string
/pdf-upload:
post:
summary: Upload multiple PDFs
description: "Allows users to upload multiple PDF files.\nThe uploaded files are stored in a dynamically generated directory with the format: \n`{customer_identifier}-{bank name}-{YYYYMMDD}` inside the container `{user}`.\nIf `bank name` is not provided, it defaults to `\"unspecified_bank\"`.\nIf `date` is not provided, it defaults to the current date in `YYYYMMDD` format.\n"
tags:
- PDFs
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
properties:
files:
type: array
items:
type: string
format: binary
description: List of PDF files to upload
user:
type: string
example: user
description: The user, which is also used as the Azure container name
customer_identifier:
type: string
example: customer
description: Must be a valid Unique identifier, GUID (UUID)
bank name:
type: string
example: bank name
description: Name of the bank (defaults to `"unspecified_bank"` if not provided)
date:
type: string
example: '20241117'
description: Date in `YYYYMMDD` format (defaults to today's date if not provided)
responses:
'200':
description: PDFs uploaded successfully
content:
application/json:
schema:
type: object
properties:
message:
type: string
example: Files uploaded successfully
folder:
type: string
example: customer-wio-20241117
container:
type: string
example: user
uploaded_files:
type: array
items:
type: string
example:
- file1.pdf
- file2.pdf
'400':
description: Invalid request, missing parameters or incorrect date format
'500':
description: Internal server error, failed to upload files
/start-pdf-extraction:
post:
summary: Trigger PDF extraction pipeline
description: 'Starts the pipeline to process PDF data for the specified customer. An optional `mode` parameter allows specifying whether to override or append to existing data (defaults to `Override`).
If a pipeline is already running for the same customer_id, this endpoint will return a 409 Conflict response.
'
tags:
- PDFs
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
required:
- user
- password
- customer_id
properties:
user:
type: string
example: dbuser
password:
type: string
example: mysecurepassword
customer_id:
type: string
format: uuid
example: 43d027ff-e6cc-4f77-ab7a-1a8f34259035
mode:
type: string
description: 'Optional. Determines how PDF data is processed in the pipeline. Allowed values are `Override` (default) and `Append`.
'
enum:
- Override
- Append
default: Override
example: Override
responses:
'200':
description: Pipeline triggered successfully
content:
application/json:
schema:
type: object
properties:
message:
type: string
example: PDF extraction pipeline triggered successfully
'400':
description: Missing or invalid parameters
content:
application/json:
schema:
type: object
properties:
error:
type: string
example: 'Missing required parameters: user, password, and customer_id'
'409':
description: A pipeline is already running for this customer_id
content:
application/json:
schema:
type: object
properties:
error:
type: string
example: A pipeline is already running for customer_id '43d027ff-e6cc-4f77-ab7a-1a8f34259035'.
'500':
description: Pipeline trigger failed or server error
content:
application/json:
schema:
type: object
properties:
error:
type: string
example: Pipeline trigger failed
response_text:
type: string
example: <Azure error message here>