Pipelines — overview

A pipeline is a graph of blocks (layout detection, OCR models, conditions, transcription…) that the platform runs on a document or an audio file. This section describes the gateway routes.

Base URL and authentication

Base URL: https://api-endpoints.alphaedge-ai.com

Authentication: X-API-Key: <key> or Authorization: Bearer <key> header. Only the GET /pipelines/capabilities route is public.

Two ways to run a pipeline

Saved pipelineRaw graph
WhenPipeline created or chosen in the Studio (e.g. "IDP — Quality")You build the graph yourself
RoutePOST /api/pipelines/{org}/{id}/run/POST /api/pipelines/custom/{kind}/run/
GraphStored on the AlphaEdge sideSent in the pipeline field

Response format

Your choice: JSON (default) or an SSE stream (stream=true with Accept: text/event-stream). Pipeline responses do not display any price.

Limits

LimitValue
Nodes per graph40
Links per graph80
Graph size64 KiB
Pages per document100
Execution time3600 s
Regions processed in parallel8

The effective limits are always available in GET /pipelines/capabilities (limits field).

Routes

RouteRole
POST /api/pipelines/{org}/{id}/run/Run a saved pipeline
GET /pipelines/capabilitiesBlocks and tests that can be used right now (public)
POST /pipelines/{kind}/validateValidate a graph without a document or consumption
POST /api/pipelines/custom/{kind}/run/Run a custom graph (Enterprise plan)
POST /documents/classify, POST /documents/splitClassify or split a batch of pages
POST /pipelines/words/writing_typePrinted or handwritten, word by word

Errors are described on the "Error codes" page (invalid_pipeline and pipeline_error families).