Skip to main content

Context API Reference

The Context API applies enrichment operations to already-curated content. Operations, or actions, include summarization, classification, named entity recognition, image description, embeddings, and more.

Processing is asynchronous. Submit a job with POST /content/process, poll GET /content/process/{processingId}/results until inProgress is false, and then read the results array.


Base URLs

EnvironmentBase URL
Production (US)https://knowledge-enrichment.ai.app.hyland.com/latest/api/context-enrichment
Production (EU)https://knowledge-enrichment.ai.app.hyland.eu/latest/api/context-enrichment

All of the following endpoints are relative to the base URL for your environment.


Authentication

All requests require a Bearer token in the Authorization header:

Authorization: Bearer <access_token>

Obtain a token using the client credentials OAuth 2.0 flow against the token endpoint for your environment:

EnvironmentToken endpoint
Production (US)https://auth.app.hyland.com/idp/connect/token
Production (EU)https://auth.app.hyland.eu/idp/connect/token

See Authentication for step-by-step instructions.


Communication methods

REST API endpoints

The Context API provides REST endpoints for content processing requests.

MethodPathDescription
GET/files/upload/presigned-urlGet a presigned upload URL and objectKey (valid for 1 hour).
PUT<presignedUrl>Upload file to storage (direct to storage, not this base URL).
POST/content/processSubmit enrichment job (asynchronous).
GET/content/process/{processingId}/resultsPoll job status and retrieve results.
GET/content/process/actionsList available actions.
GET/healthyCheck the health of the API.

For full request/response schemas see Endpoints.

Asynchronous queue communication

For high-volume or batch processing scenarios, the Context API supports asynchronous communication through Amazon SQS. This method is ideal for:

  • Large-scale content processing
  • Integration with data curation pipelines
  • Batch processing workflows

Pages in this section

PageDescription
ActionsAll supported actions with input schemas and constraints
EmbeddingsEmbedding format, vector dimensions, v2 behavior
EndpointsFull endpoint reference with schemas and examples
Code SamplesPython, C#, JavaScript

Limits and constraints

PropertyValue
Max objectKeys per request30
Presigned URL expiration1 hour — the upload link expires and cannot be reused
Uploaded file retention in S31 day — files uploaded via presigned URL are automatically deleted after 24 hours
Processing result retention in S31 day — results returned by /content/process are automatically deleted after 24 hours
File overwrite behaviorAllowed — uploading to the same objectKey replaces the previous file
Supported image formatsJPEG, PNG
Content-Type normalizationimage/jpg is automatically converted to image/jpeg
Supported text file formats
  • ACCDB
  • BALANCED_SETS
  • C
  • C4
  • CELL
  • CLP
  • CSV
  • CT
  • CUR
  • DB
  • DBF
  • DOC
  • DOCX
  • DOX
  • DXL
  • DWG
  • EML
  • EMF
  • EPUB
  • FFT
  • FW3
  • GDP
  • GUL
  • HTM
  • HTML
  • HWP
  • HWPX
  • IGS
  • IMT
  • JAVA
  • JTD
  • KEY
  • M11
  • MD
  • MDB
  • MHT
  • MPP
  • MSG
  • MSO
  • NCR
  • NUMBERS
  • OBJ
  • ODP
  • ODS
  • ODT
  • OLK15MSGSOURCE
  • ONE
  • OXPS
  • PAGES
  • PDF
  • PLIST
  • PPT
  • PPTX
  • PUB
  • QPW
  • RAR
  • RFT
  • RTF
  • SAM
  • SDW
  • SGML
  • SHW
  • SVG
  • SVM
  • TXT
  • VCF
  • VSD
  • VSDX
  • WKS
  • WP5
  • WPD
  • WPS
  • WRI
  • WS
  • WSD
  • X_T
  • XLS
  • XLSB
  • XLSX
  • XML
  • XPS
  • XXE
  • XY
  • ZIP

Image size and dimension limits vary by action. See Actions for per-action constraints.