hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-15 22:06:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

py lint (#12102)

Browse Source 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
This commit is contained in:
Jyong
2024-12-26 00:16:35 +08:00
committed by GitHub
parent bb35818976
commit 84ac004772
20 changed files with 264 additions and 210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
api/core/rag/docstore/dataset_docstore.py
View File

@@ -122,26 +122,27 @@ class DatasetDocumentStore:
db.session.add(segment_document)
db.session.flush()
if save_child:
for postion, child in enumerate(doc.children, start=1):
child_segment = ChildChunk(
tenant_id=self._dataset.tenant_id,
dataset_id=self._dataset.id,
document_id=self._document_id,
segment_id=segment_document.id,
position=postion,
index_node_id=child.metadata["doc_id"],
index_node_hash=child.metadata["doc_hash"],
content=child.page_content,
word_count=len(child.page_content),
type="automatic",
created_by=self._user_id,
)
db.session.add(child_segment)
if doc.children:
for postion, child in enumerate(doc.children, start=1):
child_segment = ChildChunk(
tenant_id=self._dataset.tenant_id,
dataset_id=self._dataset.id,
document_id=self._document_id,
segment_id=segment_document.id,
position=postion,
index_node_id=child.metadata.get("doc_id"),
index_node_hash=child.metadata.get("doc_hash"),
content=child.page_content,
word_count=len(child.page_content),
type="automatic",
created_by=self._user_id,
)
db.session.add(child_segment)
else:
segment_document.content = doc.page_content
if doc.metadata.get("answer"):
segment_document.answer = doc.metadata.pop("answer", "")
segment_document.index_node_hash = doc.metadata["doc_hash"]
segment_document.index_node_hash = doc.metadata.get("doc_hash")
segment_document.word_count = len(doc.page_content)
segment_document.tokens = tokens
if save_child and doc.children:
@@ -160,8 +161,8 @@ class DatasetDocumentStore:
document_id=self._document_id,
segment_id=segment_document.id,
position=position,
index_node_id=child.metadata["doc_id"],
index_node_hash=child.metadata["doc_hash"],
index_node_id=child.metadata.get("doc_id"),
index_node_hash=child.metadata.get("doc_hash"),
content=child.page_content,
word_count=len(child.page_content),
type="automatic",