youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-05 09:58:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

support images and tables extract from docx (#4619)

Browse Source
This commit is contained in:
Jyong
2024-05-23 18:05:23 +08:00
committed by GitHub
parent 5893ebec55
commit 233c4150d1
10 changed files with 163 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/indexing_runner.py
View File

@ -428,7 +428,7 @@ class IndexingRunner:
chunk_size=segmentation["max_tokens"],
chunk_overlap=chunk_overlap,
fixed_separator=separator,
separators=["\n\n", "。", ".", " ", ""],
separators=["\n\n", "。", ". ", " ", ""],
embedding_model_instance=embedding_model_instance
)
else:
@ -436,7 +436,7 @@ class IndexingRunner:
character_splitter = EnhanceRecursiveCharacterTextSplitter.from_encoder(
chunk_size=DatasetProcessRule.AUTOMATIC_RULES['segmentation']['max_tokens'],
chunk_overlap=DatasetProcessRule.AUTOMATIC_RULES['segmentation']['chunk_overlap'],
separators=["\n\n", "。", ".", " ", ""],
separators=["\n\n", "。", ". ", " ", ""],
embedding_model_instance=embedding_model_instance
)