github/DB-GPT
1
0
Fork 0
mirror of https://github.com/csunny/DB-GPT.git synced 2025-09-15 14:11:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

FIX:1598 Use PageTextSplitter for DatasourceKnowledge (#1599)

Browse Source 
Co-authored-by: shenk-b <shenk-b@glodon.com>
Co-authored-by: aries_ckt <916701291@qq.com>
This commit is contained in:
Kevin.Shin
2024-06-06 13:45:50 +08:00
committed by GitHub
parent 59b7aa790b
commit 20e7ccc831
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
dbgpt/rag/knowledge/datasource.py
View File

@@ -52,6 +52,7 @@ class DatasourceKnowledge(Knowledge):
return [
ChunkStrategy.CHUNK_BY_SIZE,
ChunkStrategy.CHUNK_BY_SEPARATOR,
ChunkStrategy.CHUNK_BY_PAGE,
]
@classmethod
@@ -63,3 +64,12 @@ class DatasourceKnowledge(Knowledge):
def document_type(cls) -> DocumentType:
"""Return document type."""
return DocumentType.DATASOURCE
@classmethod
def default_chunk_strategy(cls) -> ChunkStrategy:
"""Return default chunk strategy.
Returns:
ChunkStrategy: default chunk strategy
"""
return ChunkStrategy.CHUNK_BY_PAGE