Get workflow
Workflow details including columns and documents (requires workflows:read).
path Parameters
workflow_idGet workflow › Responses
Successful Response
nameWorkflow name
app_idApplication ID (e.g., 'deal-screening')
entity_idllm_modelLLM model (empty = use provider default)
llm_providerLLM provider name
Workflow description
Extensible metadata
idstatusWorkflow lifecycle status
is_extractingOverall extraction status: not_started, pending, complete, has_failures
Documents whose extraction has fully resolved, including ones whose cells failed
Documents in the workflow
List workflow columns
path Parameters
workflow_idList workflow columns › Responses
Successful Response
nameColumn name
column_typeColumn data type
promptNatural language extraction prompt
workflow_idDoc generation settings when task_type is generate
fallback_behaviorHow option fields handle values outside their declared options
Value to use when no option matches and default_value is selected
orderDisplay order
Column width in UI
Tag options [{id, label, color, stageId}]
inputsList of column IDs this column depends on
Task type for this column
Model ID for this column
Sub-field definitions for table columns [{name, type, prompt}]
idis_deletedList workflow documents
path Parameters
workflow_idquery Parameters
document_idReturn only documents with the specific ID. Should be used for filtering
collection_idFilter to documents in a collection.
Filter to documents in a collection.
List workflow documents › Responses
Successful Response
idnameworkflow_idstatusDocument processing pipeline status
Upload documents
Upload documents directly to this workflow, optionally into one collection. collection_id and collection_name target a single collection for the whole call and are mutually exclusive; validation_data requires one of them and applies to every uploaded document. To upload files for multiple people or groups, each with its own reference data, use POST /documents/bulk instead.
path Parameters
workflow_idquery Parameters
collection_idcollection_nameName of the collection to upload the documents to. If not existing, a new collection will be created.
Upload documents › Request Body
filesBinary files to upload. File Blobs. Not 1s and 0s, but actual files
file_namesDisplay names for each uploaded file, parallel to the files array.
JSON object with customer reference data for validation columns
Upload documents › Responses
Successful Response
idnameworkflow_idstatusDocument processing pipeline status
Bulk upload documents with per-item validation data
Upload files for many people or groups in one call. Each manifest item lists the files for one person or group: a single file with no collection target becomes a standalone document; several files, or a named collection_id/collection_name, becomes a collection. validation_data is stored on whichever the item becomes. Every uploaded file must be referenced by exactly one item, validated independently, so matched is reported per item. Limits: 100 files and 100 items per request, 100 MB per file. Partial success returns HTTP 200; a failed item has no documents and any files it uploaded are rolled back. Extraction does not start automatically unless extract_when_ready is set on the request; otherwise poll GET .../documents until documents reach converted, then call POST .../extract. Requires the workflows:write scope. See /documents/confirm/bulk for the signed URL equivalent.
path Parameters
workflow_idBulk upload documents with per-item validation data › Request Body
filesBinary files to upload. Every file referenced by any manifest item must be included here.
manifestJSON array of upload groups, one item per person or group. Item fields: files (required, list of uploaded filenames or zero-based indexes into files[]), collection_name or collection_id (optional, mutually exclusive; several files, or naming a collection, make the item a collection), validation_data (optional object with reference data for that item), file_names (optional display names parallel to the item files). An item with more than one file must set collection_name or collection_id. validation_data is capped at 50 keys and 4096 bytes. Omit validation_data to leave the reference data on an existing collection untouched. Sending it with a collection_id replaces the stored object wholesale, so send the complete object rather than a partial update. Every uploaded file must be referenced by exactly one item; use indexes when filenames repeat or when a file was uploaded without a name. Example: [{"files": ["claim1.pdf", "claim1-photos.pdf"], "collection_name": "Claim 1001", "validation_data": {"policy_number": "POL-1"}}, {"files": ["claim2.pdf"], "validation_data": {"policy_number": "POL-2"}}]
extract_when_readyStart extraction automatically once every document in this batch has converted or failed conversion. A document counts as ready either way, so one bad file cannot stall the batch; documents from multiple uploads that become ready together are extracted in a single run. If the account has insufficient credits, extraction does not start and the reason is recorded on the affected documents' error_message.
Bulk upload documents with per-item validation data › Responses
Successful Response. Returned even when some items failed; check error on each item.
uploaded_countDocuments created across all items; an item with three files adds three
failed_countNumber of items that failed; see error on each item
Signed upload URLs
path Parameters
workflow_idSigned upload URLs › Request Body
File metadata for each upload
Signed upload URLs › Responses
Confirm signed URL uploads
path Parameters
workflow_idConfirm signed URL uploads › Request Body
file_idsFile IDs to confirm
Add documents to existing collection
Create new collection and add documents
Customer reference JSON to validate extractions against
Confirm signed URL uploads › Responses
Successful Response
nameDocument name
workflow_idMIME type of document content
Signed GCS GET URL for document content
TTL for content_url in seconds
ID-enriched LLM context
First 1000 characters of the LLM context, for thumbnails
Per-page dimensions the segment bboxes are expressed in
Document segments with bboxes
Customer reference data for validation, stored on standalone documents
Associated file ID
Current workflow stage
is_collectionIs this a collection
Parent document ID for collections
Collection ID this document belongs to
Order within collection
User-defined label for the document
idstatusDocument processing pipeline status
File URL from associated file
Confirm bulk signed URL uploads
Confirm files uploaded to signed URLs from /documents/upload-url, grouped the same way as /documents/bulk: one items entry per person or group, each with its own file_ids, optional collection_id or collection_name, and optional validation_data. Confirming enqueues conversion automatically. Set extract_when_ready on the request to start extraction automatically once every document in the batch has converted or failed. Semantics, limits, and the BulkUploadResponse shape match /documents/bulk. Requires the workflows:write scope.
path Parameters
workflow_idConfirm bulk signed URL uploads › Request Body
One entry per person or group being confirmed
extract_when_readyStart extraction automatically once every document in this batch has converted or failed conversion. A document counts as ready either way, so one bad file cannot stall the batch; documents from multiple uploads that become ready together are extracted in a single run. If the account has insufficient credits, extraction does not start and the reason is recorded on the affected documents' error_message.
Confirm bulk signed URL uploads › Responses
Successful Response. Returned even when some items failed; check error on each item.
uploaded_countDocuments created across all items; an item with three files adds three
failed_countNumber of items that failed; see error on each item
Delete document
Delete a document and its file from the workflow. Pass collection_id when deleting from a specific collection; the document must belong to that collection.
path Parameters
workflow_iddocument_idquery Parameters
collection_idWhen set, the document must belong to this collection.
When set, the document must belong to this collection.
Delete document › Responses
Successful Response
statusOperation status
Deleted workflow ID
Deleted column ID
Deleted document ID