Available on AWS Marketplace · Version 1.0.0
Assisted Business Document Type Suggestions (ES/PT/EN)
Version 1.0.0 · Available on AWS Marketplace.
Suggest two possible types for a person reviewing already extracted English,
Spanish or Portuguese business text. Useful after text extraction when a reviewer
needs to choose a downstream workflow, such as invoice extraction, order intake
or receipt handling. Selection and subsequent actions remain the caller's job.
Intended input and output
Input must be one document already known to belong to seven supported categories:
purchase order, delivery note, bank statement, utility bill, insurance policy,
invoice, or other business correspondence. The endpoint returns two ranked labels,
caller ID, analyzed code points/tokens and mandatory selection/review flags.
Rank does not express a calibrated probability or a final routing decision.
The service accepts text only, not PDF/image/audio or whole-file parsing.
Whole-document coverage is unknown. It does not validate whether an input belongs
to the supported scope, detect combined/unknown documents, verify authenticity,
extract fields, assess insurance eligibility, or decide payments or credit.
Out-of-scope text can receive plausible-looking suggestions. A reviewer must
reject unsuitable inputs rather than selecting one of the two suggestions.
Model and data provenance
| Component |
Frozen provenance |
| Encoder/tokenizer |
intfloat/multilingual-e5-small, revision 614241f622f53c4eeff9890bdc4f31cfecc418b3, MIT |
| Encoder SHA256 |
ca456c06b3a9505ddfd9131408916dd79290368331e7d76bb621f1cba6bc8665 |
| Tokenizer SHA256 |
0b44a9d7b51c3c62626640cda0e2c2f70fdacdc25bbbd68038369d14ebdf4c39 |
| Ridge head SHA256 |
1e438bdae0f1fd978e21cd6e58aaea7752c56771ee158edd6e4a4fab569ed87f |
| Fitting |
3,600 original fictional TRAIN rows plus 324 new Luna-authored TRAIN rows; source-balanced family means, fixed ridge penalty .01 |
| Ranking |
Project the unchanged nine-column head onto its seven supported columns; sort descending raw values with alphabetical ties; return two labels without scores |
| New final dataset SHA256 |
050149c2134bedf108767667c3793f3b28342b777615a7de9c3c15b469f5b90f |
| Software and original head |
Apache-2.0; dependency notices retained in the image |
IDs, filenames, language metadata, gold labels and reviewer judgments are not
features. No final/challenge examples were fitted. The head was selected using
exposed generated DEV results; the fresh generated final protocol was committed
before its authors began. The source ledger and pinned upstream card are in
the parent research directory; this card does not assert knowledge of every
upstream pretraining example.
All project document examples are fictional/model-authored. Separate authors
share the model, taxonomy and brief. Exact normalized duplicate checks passed
against all prior project corpora; they do not establish semantic independence.
There are zero native documents and zero independent human acceptance labels.
Two blinded local AI reviewers provide label diagnostics, not human adjudication.
Across all 324 final excerpts, Qwen agrees with the author on 322 and Gemma on
222. The two reviewers agree on 224 rows, including two supported examples where
both prefer invoice over the author's utility_bill; the two suggestions
include both alternatives in each case. One hundred reviewer disagreements
remain unresolved. No author label was changed and no row was excluded.
Generated final diagnostic
The fixed 0.6 prototype was evaluated once on 324 newly authored excerpts through
the exact offline HTTP image: 84 supported examples and 24 out-of-scope controls
per language, 12 examples per type/language. Every row is retained, all inputs
were admitted, and none were relabeled or excluded after inference.
| Language |
First suggestion matches provisional author |
Author label among two suggestions |
| English |
81/84 (96.4%) |
84/84 |
| Spanish |
79/84 (94.0%) |
84/84 |
| Portuguese |
80/84 (95.2%) |
84/84 |
The 1.0 release API preserves its head, ranking, input bounds and label behavior;
it removes prototype publication-state flags and keeps generated-only/native-zero
and mandatory review/selection metadata. Complete-cohort serving parity is a
separate engineering gate, not a repeated final-quality claim.
The declared generated diagnostic floors pass in every language/type. These
counts describe this dependent generated corpus only. They are not estimates of
customer-document accuracy, and no representative statistical confidence interval
is claimed. All 72 unknown/mixed controls receive suggestions and remain outside
the product claim; this does not count as successful detection. All 12 supported
first-suggestion disagreements and AI label-review disagreements remain visible
in the evidence. Model performance on real customer documents is unmeasured.
Sensitivity to reviewer labels matters: on the same fixed 84 author-supported
rows per language, the two suggestions contain Qwen's label on 84/84 in each
language, but Gemma's on EN 81/84, ES 76/84 and PT 71/84. These results are retained
alongside the author-label table; the weaker reviewer result must not be hidden
behind the 100% author-label coverage. There is no adjudicated gold set proving
which model is correct. The declared diagnostic floors are against provisional
author labels only, as frozen before evaluation.
Runtime, privacy and qualification
Bounds: 256 KiB request, 1–32 records, 16,000 code points/text, at most 256 complete
encoder tokens including prefix/special tokens. Overflow rejects the entire
batch, without truncation. Metadata is never fetched or used as a path/URL.
One inference runs at a time; contention returns 429. Errors are sanitized;
request text and paths are not logged. All weights are baked into the image.
Actual 0.6 SER9 execution used no network, UID 1000, read-only root, no-new-privileges,
two CPU and 3 GiB. HTTP/JSON Lines, filename invariance, whole-batch rejection,
recovery and SIGTERM passed. That image reports zero Trivy findings;
the exact archive/config chain and raw scan are retained. This is a point-in-time
scan, not a guarantee against all vulnerabilities or AWS certification.
The 1.0 image separately reproduced all 567 exposed reference suggestions with
zero differences, including all 126 controls. Its four executed runtime source
hashes match frozen Git commit 48ff1c31f4c3310e316d01efcf8afb294675e68b.
Trivy and the current ECR scan both report zero findings. SageMaker rejected the
initial OCI manifest before creating compute; conversion to Docker schema 2
preserved every config/layer byte. Qualified registry digest:
sha256:58d7c9ad8b9f56f1ccb2f313cc9380327a7e45d91a5af4dd972b7ea34d9da89b.
Actual private AWS checks in us-east-1, one ml.c5.xlarge:
- Real-time: 334 requests, zero failures, all 324 generated reference outputs
preserved; JSON Lines, 32-record envelope and five rejection/privacy probes pass.
- Supported sequential workload: 252 generated texts, 68–125 complete tokens;
Mac SDK end-to-end p50 69 ms and p95 123 ms, excluding warmups and with no SDK
retries. This is not a maximum-length, concurrency, sustained-load or latency-SLA
claim. Real customer workloads remain unmeasured.
- Marketplace model-package certification completed with three generated
language examples. A separate batch rehearsal through that completed package
retained all 324 generated rows and produced zero reference differences.
- Network isolation enabled, no container environment overrides, endpoint data
capture disabled. Temporary endpoint, batch model and cleanup guards removed;
retained private evidence/image storage remains billable.
AWS Marketplace made this assisted product public on 16 November 2026.
Software is USD 0.50 per ml.c5.xlarge instance-hour, with a 14-day software trial;
AWS infrastructure is separate. The released offer is authoritative.
The actual SDK notebook passed real-time and three-language batch inference in
the seller account through the product-associated package, then verified cleanup.
This is not an independent buyer checkout or entitlement test. All technical
qualification was in us-east-1; other listed regions have not been benchmarked.
Actual AWS checks do not establish native customer-document accuracy.