hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-11 03:46:52 +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/tools/tool/dataset_retriever/dataset_multi_retriever_tool.py
View File

@@ -99,9 +99,9 @@ class DatasetMultiRetrieverTool(DatasetRetrieverBaseTool):
float('inf')))
for segment in sorted_segments:
if segment.answer:
document_context_list.append(f'question:{segment.content} answer:{segment.answer}')
document_context_list.append(f'question:{segment.get_sign_content()} answer:{segment.answer}')
else:
document_context_list.append(segment.content)
document_context_list.append(segment.get_sign_content())
if self.return_resource:
context_list = []
resource_number = 1

4
api/core/tools/tool/dataset_retriever/dataset_retriever_tool.py
View File

@@ -105,9 +105,9 @@ class DatasetRetrieverTool(DatasetRetrieverBaseTool):
float('inf')))
for segment in sorted_segments:
if segment.answer:
document_context_list.append(f'question:{segment.content} answer:{segment.answer}')
document_context_list.append(f'question:{segment.get_sign_content()} answer:{segment.answer}')
else:
document_context_list.append(segment.content)
document_context_list.append(segment.get_sign_content())
if self.return_resource:
context_list = []
resource_number = 1