feat: persist reviewed chunks and index publication versions

2026-10-16 08:44:30 +08:00
parent 3f25ffab83
commit 41b3ae0e41
20 changed files with 1027 additions and 16 deletions
@@ -151,15 +151,19 @@ def load_corpus(db: Session, category: str | None) -> list[dict]:
    return corpus


+def corpus_fingerprint(corpus: list[dict]) -> str:
+    return hashlib.sha256(
+        json.dumps(corpus, ensure_ascii=False, sort_keys=True, separators=(",", ":")).encode()
+    ).hexdigest()
+
+
 def retrieve(db: Session, payload: RetrievalRequest) -> RetrievalResponse:
    started = perf_counter()
    terms = list(dict.fromkeys(tokenize(payload.query)))
    if not terms:
        raise HTTPException(422, "问题中没有可检索词，请补充具体关键词")
    corpus = load_corpus(db, payload.category)
-    fingerprint = hashlib.sha256(
-        json.dumps(corpus, ensure_ascii=False, sort_keys=True, separators=(",", ":")).encode()
-    ).hexdigest()
+    fingerprint = corpus_fingerprint(corpus)
    counters = [
        Counter(tokenize(item["title"]) * CONFIG.title_weight + tokenize(item["content"]))
        for item in corpus