canonical: https://jentic.com/apis/abbyy.com/abbyy

# Abbyy Vantage processing REST API

Jentic publishes the only available OpenAPI specification for Vantage processing REST API, keeping it validated and agent-ready. ABBYY Vantage is an intelligent document processing platform that turns unstructured documents into structured data using configurable skills (invoices, receipts, IDs, custom forms). The Vantage processing REST API exposes 31 endpoints to start transactions, upload source files, attach catalogs, run skills, and retrieve extracted document fields. It supports the US, EU, and Australia hosting regions and is gated by OAuth 2.0.

## For AI agents

Submit documents to ABBYY Vantage skills and retrieve structured field extractions via OAuth 2.0. Use it to automate invoice, receipt, and form processing.

## Scope

Does not handle e-signing, document storage as a primary system of record, or generative AI text generation - use for OCR-driven document processing and field extraction only.

## Capabilities

- Start a processing transaction and attach source files for a chosen skill
- Trigger skill execution and poll until extraction completes
- Retrieve extracted fields, confidence scores, and the source page mapping
- Manage catalogs of reference records used during extraction (e.g., vendor lists)
- Search catalog records by prefix to validate extracted values
- Reindex a catalog after bulk record changes
- List available skills and inspect their input/output schema before processing

## Use cases

### Invoice Data Extraction

Finance teams want to convert inbound invoice PDFs into structured records ready for AP automation. The Vantage processing REST API supports the full flow: POST /transactions creates the transaction, the documents and sourceFiles endpoints attach the PDF, and the result endpoints return supplier, totals, and line items as JSON. Confidence scores let downstream systems route low-confidence rows to human review.

Example prompt: Create a Vantage transaction for the invoice skill, attach invoice.pdf, run the skill, and return the extracted vendor name and total amount

### ID and KYC Document Processing

Compliance workflows process passports, driving licences, and national IDs to populate KYC records. ABBYY Vantage provides skills tuned to ID layouts in many countries; the REST API drives them with the same transaction-and-document pattern. Catalog endpoints can validate extracted fields against an internal allow list before the record is persisted.

Example prompt: Run the ID skill on a passport scan, extract the document number and expiry, and validate them against an internal catalog

### Catalog-Backed Validation

Many extraction projects need to match free-text fields (vendor name, GL code, country) against a controlled list. The catalog endpoints under /catalogs/{catalogId}/records support adding, deleting, and prefix-searching records, and the reindex endpoint refreshes the search index after bulk changes. This keeps extraction outputs aligned with the customer's master data.

Example prompt: Add 500 supplier records to catalog ID 'suppliers', call the reindex endpoint, and verify with a prefix search for 'Acm'

### Agent-Driven Document Processing via Jentic

AI agents pick up document jobs from a queue and want a single tool call to extract structured data. Through Jentic, an agent searches for an extraction intent, loads the Vantage operation, and executes the transaction lifecycle without managing OAuth refresh logic. This collapses a multi-step direct integration into a few agent calls.

Example prompt: Search Jentic for 'extract data from an invoice', load the Vantage skill operation, attach the file, and return structured fields

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /api/publicapi/v1/transactions | Create a processing transaction |
| POST | /api/publicapi/v1/transactions/{transactionId}/documents | Create a document inside a transaction |
| POST | /api/publicapi/v1/transactions/{transactionId}/documents/{documentId}/sourceFiles | Attach a source file to a document |
| GET | /api/publicapi/v1/skills | List available skills |
| GET | /api/publicapi/v1/catalogs/{catalogId}/search | Prefix-search records in a catalog |
| POST | /api/publicapi/v1/catalogs/{catalogId}/reindex | Reindex a catalog after bulk changes |

## Key resources

- **Transactions** — Create processing transactions and retrieve their status and extracted documents
- **Documents** — Group source files within a transaction and download originals
- **Source Files** — Upload PDFs, images, and office files into a document for processing
- **Skills** — List available skills and inspect their schema before running
- **Catalogs** — Manage reference data records used during extraction and run reindex operations
- **Invites** — Create invites for new tenants

## Why Jentic

- **Setup:** Wiring the Vantage processing REST API by hand means running its OAuth 2.0 client-credentials flow, choosing the right US, EU, or Australia host, and orchestrating transaction, document, and source-file steps yourself. Through Jentic you install once, import the Vantage processing REST API from the API Directory, store the client credentials once, and your agent calls it.
- **Permission scoping:** Vantage puts the transaction and catalog id in the URL path (/transactions/{transactionId}/documents, /catalogs/{catalogId}/search), so a rule can pin your agent to one transaction or catalog. You choose the operations it may call, so a catalog reindex is not included unless you add it.
- **Credential handling:** Your ABBYY Vantage OAuth client secret is stored once, encrypted, by your own Jentic One instance and used to mint and refresh access tokens at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'extract data from an invoice' or 'search a Vantage catalog', and Jentic returns the matching Vantage operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **AWS Textract** — AWS's OCR and document analysis service for forms, tables, and queries.
- **Google Cloud Vision** — Google's vision API for OCR, document text detection, and image labelling.
- **Mindee** — Mindee's parsing APIs for invoices, receipts, IDs, and custom documents.
- **Rossum** — Rossum's transactional document automation API focused on invoices.

## FAQ

### Why is there no official OpenAPI spec for Vantage processing REST API?

ABBYY publishes Vantage reference docs but not a discoverable OpenAPI specification at the catalog level. Jentic generates and maintains this spec so that AI agents and developers can call Vantage processing REST API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

### What authentication does the Vantage processing REST API use?

The API uses OAuth 2.0 via the OAuth2Security scheme. Clients exchange tenant credentials for an access token and pass it as a bearer token. Through Jentic, the OAuth secret stays in your Jentic One instance and tokens are minted at execution time, so the agent never holds the raw secret.

### Can I extract data from invoices with the Vantage processing REST API?

Yes. Create a transaction with POST /api/publicapi/v1/transactions for the invoice skill, attach the file via the documents and sourceFiles endpoints, then poll the transaction until the extracted document is available with structured supplier, totals, and line-item fields.

### How do I list the skills available in my Vantage tenant?

Call GET /api/publicapi/v1/skills for a list, or GET /api/publicapi/v1/skills/{skillId} for the schema of a single skill. The schema describes the input options and output fields the extraction will return.

### How do I run a Vantage extraction through Jentic?

Search Jentic for 'extract data from a document', load the Vantage transaction operation, and execute it with the skill ID and file. Jentic handles OAuth refresh and returns the structured extraction once processing completes.

### What hosting regions does the Vantage processing REST API support?

The spec lists three base URLs: https://vantage-us.abbyy.com, https://vantage-eu.abbyy.com, and https://vantage-au.abbyy.com. Choose the region that matches your tenant; the endpoint paths are identical across regions.

### Can I limit what my agent is allowed to do with the Vantage processing REST API?

Yes. Because you run Jentic One yourself, your own rules decide which Vantage operations and credentials the agent may use. Vantage puts the transaction and catalog ID in the URL path, such as /transactions/{transactionId}/documents and /catalogs/{catalogId}/search, so a rule can pin the agent to a single transaction or catalog. You also choose the exact operations it may call, so an action like a catalog reindex stays out of reach unless you add it.