feat: unify scoring and chat evidence pages

backend/wisegrade/rag.py

@@ -4,7 +4,8 @@ from pathlib import Path
 from sqlalchemy import cast, delete, func, or_, select
 
 from .config import get_settings
-from .models import KnowledgeChunk, KnowledgeDocument
+from .knowledge_pages import page_text, relative_image_path
+from .models import KnowledgeChunk, KnowledgeDocument, KnowledgePage
 
 
 INDEX_VERSION = 2
@@ -60,6 +61,7 @@ def ingest(db, *, course_version_id: int, project_id: int | None, submission_fil
     if len(vectors) != len(chunks):
         raise RuntimeError("嵌入向量数量与知识片段数量不一致")
     if existing:
+        db.execute(delete(KnowledgePage).where(KnowledgePage.document_id == existing.id))
         db.execute(delete(KnowledgeChunk).where(KnowledgeChunk.document_id == existing.id))
         doc = existing
         doc.document_type, doc.source_hash = category, source_hash
@@ -69,6 +71,9 @@ def ingest(db, *, course_version_id: int, project_id: int | None, submission_fil
         db.add(doc)
     doc.index_version, doc.status = INDEX_VERSION, "indexing"
     db.flush()
+    for source in pages:
+        db.add(KnowledgePage(document_id=doc.id, page=source["page_number"], text=page_text(source),
+                             image_path=relative_image_path(source.get("rendered_image_path"))))
     for chunk, vector in zip(chunks, vectors):
         db.add(KnowledgeChunk(document_id=doc.id, course_version_id=course_version_id, project_id=project_id,
                               document_type=category, page=chunk["page"], section=chunk["section"], text=chunk["text"], embedding=vector))