feat(data-process): 接入三种文档切分引擎

2026-07-25 18:00:21 +08:00
parent 4782981169
commit ea08478a37
9 changed files with 667 additions and 716 deletions
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -15,3 +15,6 @@ python-docx>=1.1.2
 openpyxl>=3.1.5
 python-pptx>=1.0.2
 llama-index-core==0.14.23
+llama-index-embeddings-huggingface==0.6.1
+docling==2.115.0
+tiktoken>=0.7.0