odoo_ocr

fegger/odoo_ocr

Fork 0

Commit Graph

Author	SHA1	Message	Date
fegger	e2becd6219	Add review stage coverage and fix XML tax deduplication - Reviewer now sends all pages to the review VLM alongside extracted JSON. - XML builder deduplicates account.tax records by rate. - XML builder raises on confidence below min_confidence_threshold. - Adds fractional tax-rate support with stable external IDs. - Adds expected_invoice.xml fixture, reviewer tests, and XML regression tests.	2026-08-21 16:44:25 +02:00
fegger	7e706793fa	Initial scaffold: local invoice OCR pipeline with Ollama, classifier branches, structured extraction, review, and Odoo XML export - Add AGENTS.md and project-specific Zed skills (odoo-ocr-pipeline, odoo-xml-import, local-vlm-client). - Implement Pydantic schemas for documents, invoices, review results, and VLM responses. - Add unified BaseVLMClient with Ollama implementation and llama.cpp stub. - Build pipeline stages: loader, classifier, digital_pdf/scanned_print/handwritten/mixed_unknown branches, extractor, reviewer, xml_builder. - Add CLI entry point with sidecar JSON and confidence-gated XML output. - Include prompts for classifier, OCR, extraction, and review models. - Add tests with FakeVLMClient; pytest, ruff, and mypy all pass.	2026-08-21 14:04:42 +02:00

Author

SHA1

Message

Date

fegger

e2becd6219

Add review stage coverage and fix XML tax deduplication

- Reviewer now sends all pages to the review VLM alongside extracted JSON.

- XML builder deduplicates account.tax records by rate.

- XML builder raises on confidence below min_confidence_threshold.

- Adds fractional tax-rate support with stable external IDs.

- Adds expected_invoice.xml fixture, reviewer tests, and XML regression tests.

2026-08-21 16:44:25 +02:00

fegger

7e706793fa

Initial scaffold: local invoice OCR pipeline with Ollama, classifier branches, structured extraction, review, and Odoo XML export

- Add AGENTS.md and project-specific Zed skills (odoo-ocr-pipeline, odoo-xml-import, local-vlm-client).
- Implement Pydantic schemas for documents, invoices, review results, and VLM responses.
- Add unified BaseVLMClient with Ollama implementation and llama.cpp stub.
- Build pipeline stages: loader, classifier, digital_pdf/scanned_print/handwritten/mixed_unknown branches, extractor, reviewer, xml_builder.
- Add CLI entry point  with sidecar JSON and confidence-gated XML output.
- Include prompts for classifier, OCR, extraction, and review models.
- Add tests with FakeVLMClient; pytest, ruff, and mypy all pass.

2026-08-21 14:04:42 +02:00

2 Commits