fix: improve OCR indexing and evidence review

backend/wisegrade/rag.py

@@ -7,9 +7,13 @@ from .config import get_settings
 from .models import KnowledgeChunk, KnowledgeDocument
 
 
+INDEX_VERSION = 2
+
+
 def split_pages(pages: list[dict], *, size=650, overlap=100):
     for page in pages:
-        blocks = [block.strip() for block in page.get("text", "").split("\n\n") if block.strip()]
+        text = page.get("text", "").strip()
+        blocks = [text] if text else []
         for table in page.get("tables", []):
             blocks.append("表格: " + str(table.get("rows", table)))
         for block in blocks:
@@ -49,18 +53,22 @@ def ingest(db, *, course_version_id: int, project_id: int | None, submission_fil
     existing = db.scalar(select(KnowledgeDocument).where(KnowledgeDocument.course_version_id == course_version_id,
                     KnowledgeDocument.project_id == project_id, KnowledgeDocument.submission_file_id == submission_file_id,
                     KnowledgeDocument.title == title))
-    if existing and existing.source_hash == source_hash and existing.status == "ready":
+    if existing and existing.source_hash == source_hash and existing.index_version == INDEX_VERSION and existing.status == "ready":
         return existing
-    if existing:
-        db.execute(delete(KnowledgeChunk).where(KnowledgeChunk.document_id == existing.id))
-        db.delete(existing)
-        db.flush()
-    doc = KnowledgeDocument(course_version_id=course_version_id, project_id=project_id, submission_file_id=submission_file_id,
-                            title=title, document_type=category, source_hash=source_hash, status="indexing")
-    db.add(doc)
-    db.flush()
     chunks = list(split_pages(pages))
     vectors = embedder([chunk["text"] for chunk in chunks])
+    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(KnowledgeChunk).where(KnowledgeChunk.document_id == existing.id))
+        doc = existing
+        doc.document_type, doc.source_hash = category, source_hash
+    else:
+        doc = KnowledgeDocument(course_version_id=course_version_id, project_id=project_id, submission_file_id=submission_file_id,
+                                title=title, document_type=category, source_hash=source_hash)
+        db.add(doc)
+    doc.index_version, doc.status = INDEX_VERSION, "indexing"
+    db.flush()
     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))