update text spliter

This commit is contained in:
jyong
2024-11-26 18:36:11 +08:00
parent 9ca453f7f7
commit 495163d5b3
2 changed files with 6 additions and 2 deletions

View File

@ -1467,7 +1467,9 @@ class SegmentService:
if dataset.indexing_technique == "high_quality" and embedding_model:
# calc embedding use tokens
if document.doc_form == "qa_model":
tokens = embedding_model.get_text_embedding_num_tokens(texts=[content + segment_item["answer"]])[0]
tokens = embedding_model.get_text_embedding_num_tokens(
texts=[content + segment_item["answer"]]
)[0]
else:
tokens = embedding_model.get_text_embedding_num_tokens(texts=[content])[0]
segment_document = DocumentSegment(