[버그 수정]

crawler_platform/app/core/extractor/ai_provider.py

@@ -149,6 +149,7 @@ class LLMJsonExtractor(AIExtractor):
                     {"role": "user", "content": prompt},
                 ],
                 "temperature": 0,
+                "response_format": extraction_response_format(),
             },
             timeout=self.timeout_seconds,
         )
@@ -266,6 +267,55 @@ Page text:
 """.strip()
 
 
+def extraction_response_format() -> dict[str, Any]:
+    return {
+        "type": "json_schema",
+        "json_schema": {
+            "name": "ontology_extraction",
+            "schema": {
+                "type": "object",
+                "properties": {
+                    "entities": {
+                        "type": "array",
+                        "items": {
+                            "type": "object",
+                            "properties": {
+                                "entity_type": {"type": "string"},
+                                "type": {"type": "string"},
+                                "name": {"type": "string"},
+                                "attributes": {"type": "object"},
+                                "confidence": {"type": "number"},
+                                "evidence_text": {"type": "string"},
+                            },
+                            "required": ["name"],
+                        },
+                    },
+                    "claims": {
+                        "type": "array",
+                        "items": {
+                            "type": "object",
+                            "properties": {
+                                "subject_name": {"type": "string"},
+                                "subject_type": {"type": "string"},
+                                "predicate": {"type": "string"},
+                                "object_name": {"type": ["string", "null"]},
+                                "object_type": {"type": ["string", "null"]},
+                                "object_value": {},
+                                "evidence_text": {"type": ["string", "null"]},
+                                "evidence_summary": {"type": ["string", "null"]},
+                                "confidence": {"type": "number"},
+                                "confidence_reason": {"type": ["string", "null"]},
+                            },
+                            "required": ["subject_name", "subject_type", "predicate"],
+                        },
+                    },
+                },
+                "required": ["entities", "claims"],
+            },
+        },
+    }
+
+
 def parse_json_content(content: str, retry=None) -> dict[str, Any]:
     try:
         return json.loads(content)