Google

Cloud Document AI API

Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer…

AI & machine learning#openapi#analytics#media

Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.

Overview

Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer vision, translation, and AutoML.

Endpoints 26

projects.operations

  • GETGets the latest state of a long-running operation/v1/:nameGets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

projects.locations.schemas.schemaVersions

  • DELETEDeletes a schema version./v1/:nameDeletes a schema version.
  • PATCHUpdates a schema version/v1/:name?updateMask=stringUpdates a schema version. Editable fields are: - display_name - labels
  • GETLists SchemaVersions./v1/:parent/schemaVersions?pageSize=0&pageToken=stringLists SchemaVersions.
  • POSTCreates a schema version./v1/:parent/schemaVersionsCreates a schema version.
  • POSTGenerates a schema version./v1/:parent/schemaVersions:generateGenerates a schema version.

projects.locations

  • GETFetches processor types/v1/:parent:fetchProcessorTypesFetches processor types. Note that we don't use ListProcessorTypes here, because it isn't paginated.
  • GETLists information about the supported locations for this service/v1/:name/locations?extraLocationTypes=string&filter=string&pageSize=0&pageToken=stringLists information about the supported locations for this service. This method lists locations based on the resource scope provided in the…

projects.locations.operations

  • POSTStarts asynchronous cancellation on a long-running operation/v1/:name:cancelStarts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the…

projects.locations.processorTypes

  • GETLists the processor types that exist./v1/:parent/processorTypes?pageSize=0&pageToken=stringLists the processor types that exist.

projects.locations.processors.processorVersions

  • POSTLRO endpoint to batch process many documents/v1/:name:batchProcessLRO endpoint to batch process many documents. The output is written to Cloud Storage as JSON in the [Document] format.
  • POSTProcesses a single document./v1/:name:processProcesses a single document.
  • POSTDeploys the processor version./v1/:name:deployDeploys the processor version.
  • POSTEvaluates a ProcessorVersion against annotated documents, producing an Evaluation./v1/:processorVersion:evaluateProcessorVersionEvaluates a ProcessorVersion against annotated documents, producing an Evaluation.
  • GETLists all versions of a processor./v1/:parent/processorVersions?pageSize=0&pageToken=stringLists all versions of a processor.
  • POSTTrains a new processor version/v1/:parent/processorVersions:trainTrains a new processor version. Operation metadata is returned as TrainProcessorVersionMetadata.
  • POSTUndeploys the processor version./v1/:name:undeployUndeploys the processor version.

projects.locations.processors

  • GETLists all processors which belong to this project./v1/:parent/processors?pageSize=0&pageToken=stringLists all processors which belong to this project.
  • POSTCreates a processor from the ProcessorType provided/v1/:parent/processorsCreates a processor from the ProcessorType provided. The processor will be at ENABLED state by default after its creation. Note that this method requires the…
  • POSTDisables a processor/v1/:name:disableDisables a processor
  • POSTEnables a processor/v1/:name:enableEnables a processor
  • POSTSet the default (active) version of a Processor that will be used in ProcessDocument and BatchProcessDocuments./v1/:processor:setDefaultProcessorVersionSet the default (active) version of a Processor that will be used in ProcessDocument and BatchProcessDocuments.

projects.locations.processors.humanReviewConfig

  • POSTSend a document for Human Review/v1/:humanReviewConfig:reviewDocumentSend a document for Human Review. The input document should be processed by the specified processor.

projects.locations.processors.processorVersions.evaluations

  • GETRetrieves a set of evaluations for a given processor version./v1/:parent/evaluations?pageSize=0&pageToken=stringRetrieves a set of evaluations for a given processor version.

projects.locations.schemas

  • GETLists Schemas./v1/:parent/schemas?pageSize=0&pageToken=stringLists Schemas.
  • POSTCreates a schema./v1/:parent/schemasCreates a schema.

API details

Base URL
https://documentai.googleapis.com
Authentication
OAuth 2.0 (authorization code flow) with 1 scope
An API key in the key query parameter
Operations
26 operations on 21 pathsPOST 15GET 9PATCH 1DELETE 1
Main resources
projects.locations.processors.processorVersions 7projects.locations.processors 5projects.locations.schemas.schemaVersions 5projects.locations 2projects.locations.schemas 2projects.locations.operations 1projects.locations.processorTypes 1projects.locations.processors.humanReviewConfig 1projects.locations.processors.processorVersions.evaluations 1projects.operations 1
Response formats
application/json
Description format
Google API Discovery, API version v1

How to test the Cloud Document AI API in Swastik Codes

  1. Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
  2. Fork it into your workspaceChoose a workspace. You get your own copy of the Cloud Document AI API collection, without the publisher's secrets.
  3. Add your credentialsThis API uses OAuth 2.0 (authorization code flow) with 1 scope. Add yours in the collection's variables or an environment; the requests already reference it.
  4. Send a requestPick an endpoint, for example “Gets the latest state of a long-running operation” (GET /v1/:name), and press Send. Check the response, add tests and run the whole collection with the runner.

Frequently asked questions

What is the Cloud Document AI API?

Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer… It is listed under AI & machine learning and has 26 endpoints.

Who publishes the Cloud Document AI API?

It is listed from Google's public API description (an OpenAPI document), not published by Google on Swastik Codes. Anyone who controls googleapis.com can claim the profile by adding a DNS TXT record.

What is the base URL of the Cloud Document AI API?

Requests go to https://documentai.googleapis.com. Endpoint paths are added to this base URL.

How do I authenticate with the Cloud Document AI API?

It accepts 2 methods: OAuth 2.0 (authorization code flow) with 1 scope; an API key in the key query parameter.

How many endpoints does the Cloud Document AI API have?

26 operations on 21 paths (15 POST, 9 GET, 1 PATCH, 1 DELETE). The largest groups are projects.locations.processors.processorVersions, projects.locations.processors, projects.locations.schemas.schemaVersions, projects.locations.

Is forking the Cloud Document AI API free?

Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.

Suggest an API

Tell us which public API is missing. We check it, then add it here with its endpoints when it has an OpenAPI (Swagger) description.