diff --git a/api/db/services/document_service.py b/api/db/services/document_service.py index 301db2f03..a2681ba29 100644 --- a/api/db/services/document_service.py +++ b/api/db/services/document_service.py @@ -334,7 +334,7 @@ class DocumentService(CommonService): def begin2parse(cls, docid): cls.update_by_id( docid, {"progress": random.random() * 1 / 100., - "progress_msg": "Task dispatched...", + "progress_msg": "Task is queued...", "process_begin_at": get_format_time() }) diff --git a/rag/nlp/rag_tokenizer.py b/rag/nlp/rag_tokenizer.py index 378b67849..75541f599 100644 --- a/rag/nlp/rag_tokenizer.py +++ b/rag/nlp/rag_tokenizer.py @@ -171,7 +171,7 @@ class RagTokenizer: F += freq L += 0 if len(tk) < 2 else 1 tks.append(tk) - F /= len(tks) + #F /= len(tks) L /= len(tks) logging.debug("[SC] {} {} {} {} {}".format(tks, len(tks), L, F, B / len(tks) + L + F)) return tks, B / len(tks) + L + F