From 7656de0cc4059ddd446020ee81ee59871b17f497 Mon Sep 17 00:00:00 2001
From: "LASTA_DEV01\\lasta" <lasta@rpgrepublic.co.kr>
Date: Fri, 8 May 2026 17:44:11 +0900
Subject: [PATCH] =?UTF-8?q?[=EB=B2=84=EA=B7=B8=20=EC=88=98=EC=A0=95]?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 crawler_platform.db-journal                   | Bin 8720 -> 0 bytes
 .../app/core/extractor/ai_provider.py         |  50 ++++++++++++++++++
 2 files changed, 50 insertions(+)
 delete mode 100644 crawler_platform.db-journal

diff --git a/crawler_platform.db-journal b/crawler_platform.db-journal
deleted file mode 100644
index 8a9558b76cd425bfe290982506a2144ee2762d33..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 8720
zcmeHNPm3c(6z`cu+!b{cyex|ldM|s}37uqmlF4PrfO}9@2i==4O{M!KQ%-kRZ&h_>
zL&!%Eudd*?5d0K-_TXLc;%D%^s`Q_PthgWxN)-cL^<Jgk`~9lkujyhuuW1in{`?z`
zCZ2bQj}ID$>;0b@ID8M$9o+uZ!#~#?1C9a5fMdWh;23ZWye0$R4-Rg7;k}<enM?|h
zvoeE7l~WZ<UT7}zjcw%@QhW=sj&hcPKkoSZCi@RNej+l)^VSS9Y9{BPBgi$^929!L
z_AhNTa$iW6C)D{|XrSjLj)gRq$3mFrSHP6W$@fJZGliM?PjN8gkS2CLlNg$&)nZx{
zQH~2L`c=l0B!y-?WvVq|CZ3&$0VB=kW}r;edMGxbYeOM<Y!a5R;BXUN!}10bS0*<l
zN*P<QE5D*m%w|01ER9T>k>VDxUKWPc%1tS2St=c+uz(Z^3%X|^p`*M@NtV1!Q?#%&
z6*rJX1=ClC3F4(-Qh}shm_rVjB`r7u9bZ|igl8ovZ9qz<Axe41b%dK5Wjrr2sd1+t
z;BO?Tg0@|Xsn9CY&oz25Ggv?DG^jEruR#|nvuspocFjA0M!5bP#M2}G{u!RlcJA(u
zHSgP-;TwkX_gh0JK;&AaV!p)fTKT5%mJ#jCzf^n};Y)MoiH*yu3@)We%2;2rIhYbC
zBqTh>^JSx6F;$m3_MeENDtH_{HWk`3T;Ne}4I52>g}4S)DT6AxX44cN3E7B5%UJ6L
zCaUn1r%XN(l(iCRa<QZyMz0}Y-vay0*0RCDQjW<Gh?U>S3Rc%PiY<|`-W^oHBuc0e
zrG5UEDp_}%gG!{Vr=cUO6$?E(+_dxyoh?=xs<uUKdsdsfO-<AiXVci`YK^LZB^HY;
zgFIpM0<oO6^xqysG`HUXH^AptC`Uvv9-0|QJUNCaH1)f5+}T3#q%j^3jJ26eG~nc3
zm&$x2+%Z-G7|H5&`)IDQwjF`Vx-2kXhzgPN*cMH##gr7sh2#QtJ7G&oa}W^Jw!rP1
zHMD%tyTL%)U8Q%jUa$K>|MWNrkAqPs7>>iUad^`0h5g~#sO=ez`-5?K+C3W#hGFpF
z<uBjii~cRT2e|eAuinuQM<G63a|}2J90QI4$ADwNG2j?*3^)cH1C9a5z<-E=r{COq
z*SmB7uJ`txgAXT@&CLVd#@X)q?=#chS-s-p`E(TQ|9B4jqaa|1wEF$c>aB11R`>jm
y7u0?{di@YR{BoZiV2HuTn-JAaLhI7EGM)cvp?vhJI47f^xAz_(q&W2dAAbQzw&j8V

diff --git a/crawler_platform/app/core/extractor/ai_provider.py b/crawler_platform/app/core/extractor/ai_provider.py
index 24d497d..35f6faf 100644
--- a/crawler_platform/app/core/extractor/ai_provider.py
+++ b/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)