Available on AWS Marketplace · Version 1.0.0
Reviewing document type suggestions
Deploy through your AWS Marketplace subscription and use the regional
model-package ARN shown in the product configuration. The seller's source
qualification ARN is not a buyer subscription ARN. The complete downloadable
notebook defaults to no AWS calls; explicitly enable deployment only after
reading its cost, access and cleanup instructions.
- Extract the text with your own authorized PDF/OCR component, preserving its
actual content. This service receives no file and does not perform extraction.
- Establish that the text comes from a single supported business document.
Combined, unrelated or insufficient text can still receive two suggestions.
- Send one JSON envelope to the
/invocations endpoint. The complete
text must fit the token limit; do not silently clip a document to obtain a label.
- Present both suggestions to a reviewer. Require an explicit choice or rejection
before invoking a downstream processor. Rank is not confidence.
- Evaluate your own authorized examples before relying on the suggestions.
Real customer-document accuracy is unmeasured; existing diagnostics use
model-authored examples and provisional labels.
Example request structure:
{"instances":[{"id":"business-review-1","text":"Your already extracted source text","filename":"optional-metadata.txt"}]}
The response includes predictions, preserving each ID. Each prediction has two
distinct suggestions with rank and document_type, mandatory needs_review
and selection_required, input_tokens, analyzed_codepoints,
whole_document_coverage=unknown, truncated=false,
unknown_mixed_detection=not_provided and validation_basis=generated_only.
The API declares zero independent acceptance rows. Publication status is recorded
in the product listing rather than asserted by inference results. It returns no definitive selected document_type or probability.
The exact image passed private real-time and full-cohort Batch Transform checks
on ml.c5.xlarge in us-east-1. See the model card for actual workload/latency limits;
these are not customer accuracy or service-level guarantees.
HTTP limits and handling:
| Status |
Action |
| 400 |
Correct the complete malformed/invalid envelope; no partial predictions |
| 413 |
Reduce request size or batch count while preserving complete documents |
| 415 |
Use JSON or one-envelope-per-line JSON Lines without content encoding |
| 422 |
Complete text exceeds 256 encoder tokens; use a separately designed workflow |
| 429 |
Back off and retry the same request; inference is stateless |
| 500 |
Retry boundedly or surface the service failure for review |
JSON Lines requires exactly one complete envelope per invocation. Qualified
Batch Transform configuration uses one ml.c5.xlarge, line splitting, SingleRecord,
line assembly, MaxConcurrentTransforms=1 and MaxPayloadInMB=1. Each envelope
still obeys the smaller 256 KiB/32-record runtime bounds. MultiRecord is unsupported.
Set a task-owned S3 input/output prefix and execution role. The notebook documents
real-time setup, invocation and exact-resource cleanup; delete the endpoint when
finished. Stopping a notebook does not stop endpoint billing.
Buyer-controlled account access, encryption, retention, authorized source use and
downstream decisions remain part of your application design.
Complete SDK examples
The public GitHub notebook includes both real-time and optional Batch Transform
examples with fictional ES/PT/EN inputs, actual certified-image output samples,
explicit opt-in, cost notes and cleanup. Batch uses your existing authorized
us-east-1 S3 bucket; it creates no bucket or role and retains its unique example
prefix for inspection. Default Run All makes no AWS calls. Use a current boto3
release supporting conditional S3 PutObject (IfNoneMatch) before opting in.
Public examples and notebook.