Upload schemas/generic_document.json with huggingface_hub

schemas/generic_document.json

@@ -0,0 +1,107 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "german-ocr-3/schemas/generic_document.json",
+  "title": "GermanOCR3 Generic Document",
+  "description": "Allgemeines deutsches Dokument-Extraktionsschema. Felder dürfen null sein, wenn nicht eindeutig erkennbar.",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["document_type", "language", "raw_text", "confidence"],
+  "properties": {
+    "document_type": {
+      "description": "z.B. invoice, receipt, letter, form, contract, id_card, other, unknown",
+      "type": ["string", "null"]
+    },
+    "language": {
+      "description": "BCP-47 Sprachcode des Dokuments (typisch 'de').",
+      "type": "string",
+      "default": "de"
+    },
+    "sender": {
+      "type": ["object", "null"],
+      "additionalProperties": false,
+      "properties": {
+        "name": {"type": ["string", "null"]},
+        "address": {"type": ["string", "null"]},
+        "email": {"type": ["string", "null"]},
+        "phone": {"type": ["string", "null"]},
+        "tax_id": {"type": ["string", "null"]},
+        "vat_id": {"type": ["string", "null"]}
+      }
+    },
+    "recipient": {
+      "type": ["object", "null"],
+      "additionalProperties": false,
+      "properties": {
+        "name": {"type": ["string", "null"]},
+        "address": {"type": ["string", "null"]},
+        "customer_id": {"type": ["string", "null"]}
+      }
+    },
+    "date": {
+      "description": "Hauptdatum des Dokuments im Format YYYY-MM-DD, falls eindeutig erkennbar.",
+      "type": ["string", "null"]
+    },
+    "reference_numbers": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["label", "value"],
+        "properties": {
+          "label": {"type": "string"},
+          "value": {"type": "string"}
+        }
+      },
+      "default": []
+    },
+    "amounts": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["label", "value"],
+        "properties": {
+          "label": {"type": "string"},
+          "value": {"type": ["number", "string"]},
+          "currency": {"type": ["string", "null"]}
+        }
+      },
+      "default": []
+    },
+    "tables": {
+      "type": "array",
+      "default": [],
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["headers", "rows"],
+        "properties": {
+          "title": {"type": ["string", "null"]},
+          "headers": {"type": "array", "items": {"type": "string"}},
+          "rows": {
+            "type": "array",
+            "items": {
+              "type": "array",
+              "items": {"type": ["string", "number", "null"]}
+            }
+          }
+        }
+      }
+    },
+    "raw_text": {
+      "description": "Roher OCR-Text, möglichst layouterhaltend, deutsche Originalschreibweise behalten.",
+      "type": ["string", "null"]
+    },
+    "confidence": {
+      "description": "Subjektive Selbsteinschätzung 0..1.",
+      "type": ["number", "null"],
+      "minimum": 0,
+      "maximum": 1
+    },
+    "notes": {
+      "type": "array",
+      "items": {"type": "string"},
+      "default": []
+    }
+  }
+}