Document Intelligence

This example processes synthetic invoices and a purchase order through explicit ingestion, classification, extraction, reconciliation, and reporting activities. It verifies totals and duplicate invoice identifiers rather than stopping after text extraction.

Document Intelligence. Nodes in the same column can run in parallel once their dependencies complete.

Inputs

Versioned semi-structured invoices
Purchase-order fixture

Outputs

Document inventory
Classifications
Extracted fields and line items
Reconciliation JSON and CSV
Aggregate report

Provenance to preserve

Source hashes
Document-to-record mapping
Balance checks
Duplicate checks
Gross total

Run this example locally

Read the bundled business documents, classify them, extract structured fields, reconcile invoice lines, and publish a checked report. Every stage performs local data processing and passes its files to the next activity.

Install Go and Python 3.12 or newer.

git clone https://github.com/UFFeScience/akoflow-examples.git &&
cd akoflow-examples &&
git checkout --detach d890c3171e3661890305b763b8fc3ede48bb61b4 &&
cd document-ai/document-intelligence &&
./prepare.sh &&
./run.sh

Run the block from the directory where you keep your repositories. If you already cloned the repository, enter this example's directory and run ./prepare.sh && ./run.sh.

Preparation downloads the Go module and any declared Python packages once. The workload then runs locally with offline input data. Every meaningful step is a separate process; independent activities run in parallel after their dependencies complete.

Read outputs/manifest.json for the generated artifacts, outputs/dag-validation.json for dependency waves, and outputs/stage-<activity>.json for each activity's observed result. A failed stage stops the run and prevents a successful final manifest.

Expected outputs: ingested.json, classified.json, extracted.json, reconciliation.json, invoice-summary.csv, report.json.

Run the same activities in Desktop

Start your local AkôFlow daemon with Docker available and configure AKOFLOW_API_TOKEN in your shell. From this example's directory, run:

go run ../../tools/daemon-local -root ../.. -example document-ai/document-intelligence

This command validates the daemon connection, builds the declared image, registers the local environment and workflow, and submits a real run. The daemon owns execution and file transfers. Open the printed run ID in Desktop to inspect each activity.