Context API Endpoints

This page documents all endpoints exposed by the Context API.

Base URL depends on your environment (see Base URLs for more information). All of the following endpoints are relative to that base URL.

Unless otherwise noted, all endpoints require Authorization: Bearer <access_token>.

GET /files/upload/presigned-url

Returns a presigned upload URL and an objectKey that uniquely identifies the file in storage.

Query parameters

Parameter	Type	Required	Description
`contentType`	`string`	Yes	MIME type of the file to upload (for example, `application/pdf`, `image/png`)

Request

GET /latest/api/context-enrichment/files/upload/presigned-url?contentType=application/pdf HTTP/1.1
Host: knowledge-enrichment.ai.app.hyland.com
Authorization: Bearer <access_token>

Response

Status: 200 OK

Field	Type	Description
`presignedUrl`	`string`	Presigned URL for uploading the file directly to storage.
`objectKey`	`string`	Unique identifier for the file in storage. Pass this in subsequent `POST /content/process` requests.

{
  "presignedUrl": "https://<storage-endpoint>/contents/abc123.pdf?<signature>",
  "objectKey": "testing/fae61283-571c-403a-b33f-c8d982158da9/documents/report.pdf"
}

PUT `{presignedUrl}`

Uploads the file to storage using the presigned URL from GET /files/upload/presigned-url. This request goes directly to storage, not to the Context API base URL.

Request

Header	Value
`Content-Type`	MIME type of the file (for example, `application/pdf`)

Body: Raw binary content of the file. Do not include Authorization.

Response

Status: 200 OK — empty body on success

POST /content/process

Submits an enrichment job for one or more files.

Request

POST /latest/api/context-enrichment/content/process HTTP/1.1
Host: knowledge-enrichment.ai.app.hyland.com
Authorization: Bearer <access_token>
Content-Type: application/json

Body:

Field	Type	Required	Description
`version`	`string`	Yes	Must be `"context.api/v2"`.
`objectKeys`	`array`	Yes	Array of file references. Each item must have either `path` (for files uploaded via presigned URL) or `documentId` (for files already in the Cloud Content Repository).
`actions`	`object`	Yes	Map of action names to action configuration. See Actions for all available actions and their parameters. Each text and image action accepts an optional `model` (`string`, beta) that chooses the AI model running it (see Model Selection (Beta) for more information).

objectKeys item:

Field	Type	Description
`path`	`string`	`objectKey` value returned by `GET /files/upload/presigned-url`
`documentId`	`string`	ID of a document already ingested via the Data Curation API

Example:

{
  "version": "context.api/v2",
  "objectKeys": [
    { "path": "testing/fae61283-571c-403a-b33f-c8d982158da9/documents/report.pdf" }
  ],
  "actions": {
    "textSummarization": { "maxWordCount": 150 },
    "textClassification": {
      "classes": ["Report", "Contract", "Invoice", "Other"]
    }
  }
}

Example with per-action model selection:

{
  "version": "context.api/v2",
  "objectKeys": [
    { "path": "testing/fae61283-571c-403a-b33f-c8d982158da9/documents/report.pdf" }
  ],
  "actions": {
    "textSummarization": { "model": "google-gemma-4-e2b", "maxWordCount": 150 },
    "textClassification": {
      "model": "nvidia-nemotron-super-3-120b",
      "classes": ["Report", "Contract", "Invoice", "Other"]
    }
  }
}

Response

Status: 200 OK

Field	Type	Description
`processingId`	`string`	Unique identifier for this processing job. Use to poll results.

{
  "processingId": "a3f9c821-4e3b-47e9-9b0c-1e7e29f87a12"
}

Error responses

400 Bad Request — validation error (invalid version, missing required fields). detail contains the validation messages joined with ; , and errors lists one entry per problem:

{
  "type": "https://tools.ietf.org/html/rfc9110#section-15.5.1",
  "title": "Validation error",
  "status": 400,
  "detail": "Version must be provided when using structured payload format.",
  "errors": [
    {
      "propertyName": "version",
      "errorMessage": "Version must be provided when using structured payload format."
    }
  ]
}

400 Bad Request — an action names a model that is unknown or not offered for that action. No action in the request is processed:

{
  "type": "https://tools.ietf.org/html/rfc9110#section-15.5.1",
  "title": "Validation error",
  "status": 400,
  "detail": "Model 'nvidia-nemotron-super-3-120b' is not available for action 'imageDescription'. Allowed models: bedrock-claude-haiku-4-5, openai-gpt-5-6-luna, google-gemma-4-e2b, google-gemma-4-26b-a4b, google-gemma-4-31b",
  "errors": [
    {
      "propertyName": "actions.imageDescription.model",
      "errorMessage": "Model 'nvidia-nemotron-super-3-120b' is not available for action 'imageDescription'. Allowed models: bedrock-claude-haiku-4-5, openai-gpt-5-6-luna, google-gemma-4-e2b, google-gemma-4-26b-a4b, google-gemma-4-31b"
    }
  ]
}

400 Bad Request — some objects don't exist or have incorrect content type:

{
  "title": "Request Processing Error",
  "detail": "Some objects specified in objectKeys do not exist or have an incorrect content type",
  "notExistingObjects": [
    "testing/abc123/documents/missing.pdf"
  ]
}

500 Internal Server Error — queue processing error:

{
  "title": "Request Processing Error",
  "detail": "An error occurred while sending a message to the queue",
  "status": 500
}

GET /content/process/`{processingId}`/results

Polls the status of an enrichment job and retrieves results when complete.

Path parameters

Parameter	Type	Description
`processingId`	`string` (GUID)	The `processingId` returned by `POST /content/process`

Request

GET /latest/api/context-enrichment/content/process/a3f9c821-4e3b-47e9-9b0c-1e7e29f87a12/results HTTP/1.1
Host: knowledge-enrichment.ai.app.hyland.com
Authorization: Bearer <access_token>

Response

Status: 202 Accepted (while in progress) or 200 OK (when complete)

Field	Type	Description
`id`	`string` (GUID)	The processing job ID
`timestamp`	`string`	ISO 8601 timestamp indicating when the result was generated
`status`	`string`	Job status (see the following values). May be `null` during early processing.
`inProgress`	`boolean`	`true` while the job is running. Stop polling when `false`.
`results`	`array`	Array of result objects per `objectKey`. Empty while `inProgress` is `true`.

Status values:

Value	Terminal	Description
`PROCESSING`	No	Job is being processed.
`SUCCESS`	Yes	All actions completed successfully.
`PARTIAL_FAILURE`	Yes	Job completed, but one or more actions failed; check `error` fields in individual action results.
`FAILURE`	Yes	Job failed entirely.

Action result structure:

Each action result is an object with the following structure:

Field	Type	Description
`isSuccess`	`boolean`	`true` if the action completed successfully, `false` if it failed
`result`	varies	The action result. Type depends on the action (see Actions for details). May be `null` if the action failed.
`error`	`object` or `null`	Error details if the action failed, `null` if successful.

Error object:

Field	Type	Description
`errorType`	`string`	Machine-readable error type identifying the category of failure.
`message`	`string`	Human-readable error message explaining what went wrong.

Error responses

404 Not Found — processing job does not exist or you don't have access:

{
  "title": "Request Processing Error",
  "detail": "Content processing result with specified ID does not exist",
  "status": 404
}

400 Bad Request — job completed but general processing errors occurred:

{
  "title": "Request Processing Error",
  "detail": "Content processing failed",
  "status": 400
}

Examples

While in progress (202 Accepted):

{
  "id": "a3f9c821-4e3b-47e9-9b0c-1e7e29f87a12",
  "timestamp": "2025-08-25T13:06:00.8286903+00:00",
  "status": "PROCESSING",
  "inProgress": true
}

When complete (200 OK):

{
  "id": "a3f9c821-4e3b-47e9-9b0c-1e7e29f87a12",
  "timestamp": "2025-08-25T13:06:00.8286903+00:00",
  "status": "SUCCESS",
  "inProgress": false,
  "results": [
    {
      "objectKey": "testing/fae61283-571c-403a-b33f-c8d982158da9/documents/report.pdf",
      "textSummary": {
        "isSuccess": true,
        "result": "This is a concise summary of the document content.",
        "error": null
      },
      "textClassification": {
        "isSuccess": true,
        "result": "Report",
        "error": null
      }
    }
  ]
}

GET /content/process/actions

Returns the available content processing actions for the current environment. The response format depends on the requested API version.

Query parameters

Parameter	Type	Required	Description
`version`	`string`	No	API version string (for example, `context.api/v2`). Defaults to the v1 format if not provided. Pass `context.api/v2` to get the models each action accepts in `availableModels`.

Request

GET /latest/api/context-enrichment/content/process/actions HTTP/1.1
Host: knowledge-enrichment.ai.app.hyland.com
Authorization: Bearer <access_token>

Response

Status: 200 OK

Without version=context.api/v2, returns an array of available action names:

[
  "imageDescription",
  "imageMetadataGeneration",
  "textMetadataGeneration",
  "textClassification",
  "textSummarization",
  "imageClassification",
  "imageEmbeddings",
  "textEmbeddings",
  "namedEntityRecognitionImage",
  "namedEntityRecognitionText"
]

With ?version=context.api/v2, the response is an array of action objects:

Field	Type	Description
`name`	`string`	Action name to use as a key in the `actions` object of `POST /content/process`.
`availableModels`	`string[]`	Models that can be set in this action's `model` field. Present on text and image actions. Omitted on `textEmbeddings` and `imageEmbeddings`, which do not support model selection (see Model Selection (Beta) for more information).

The model list for text and image actions is the same for every customer and every environment. It does not reflect regional availability: not every listed model is deployed in Production (EU). See Regional Availability.

GET /latest/api/context-enrichment/content/process/actions?version=context.api/v2 HTTP/1.1
Host: knowledge-enrichment.ai.app.hyland.com
Authorization: Bearer <access_token>

[
  {
    "name": "textSummarization",
    "availableModels": [
      "bedrock-claude-haiku-4-5",
      "openai-gpt-5-6-luna",
      "google-gemma-4-e2b",
      "google-gemma-4-26b-a4b",
      "google-gemma-4-31b",
      "nvidia-nemotron-super-3-120b",
      "nvidia-nemotron-nano-3-30b",
      "openai-gpt-oss-120b",
      "openai-gpt-oss-20b"
    ]
  },
  {
    "name": "imageDescription",
    "availableModels": [
      "bedrock-claude-haiku-4-5",
      "openai-gpt-5-6-luna",
      "google-gemma-4-e2b",
      "google-gemma-4-26b-a4b",
      "google-gemma-4-31b"
    ]
  },
  { "name": "textEmbeddings" },
  { "name": "imageEmbeddings" }
]

This example shows four of the returned actions. The other text actions (textClassification, textMetadataGeneration, namedEntityRecognitionText) return the same availableModels as textSummarization. The other image actions (imageClassification, imageMetadataGeneration, namedEntityRecognitionImage) return the same availableModels as imageDescription.

Error responses

400 Bad Request — invalid version parameter:

{
  "title": "Validation error",
  "detail": "Version must be null or one of the supported values (context.api/v2)."
}

GET /healthy

Health check endpoint. Returns 200 OK when the service is healthy. Returns 503 Service Unavailable if unhealthy. No authentication required.

Response

Status: 200 OK (healthy)

Body: "Healthy"

Status: 503 Service Unavailable (unhealthy)

Body: Status description string

GET /files/upload/presigned-url​

Query parameters​

Request​

Response​

PUT {presignedUrl}​

Request​

Response​

POST /content/process​

Request​

Response​

Error responses​

GET /content/process/{processingId}/results​

Path parameters​

Request​

Response​

Error responses​

Examples​

GET /content/process/actions​

Query parameters​

Request​

Response​

Error responses​

GET /healthy​

Response​

GET /files/upload/presigned-url

Query parameters

Request

Response

PUT `{presignedUrl}`

Request

Response

POST /content/process

Request

Response

Error responses

GET /content/process/`{processingId}`/results

Path parameters

Request

Response

Error responses

Examples

GET /content/process/actions

Query parameters

Request

Response

Error responses

GET /healthy

Response