AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-07-31 00:12:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix pandas indexing method for knowledge base imports (#12637) (#12638)

Browse Source 
Co-authored-by: CN-P5 <heibai2006@qq.com>
This commit is contained in:
CN-P5 2025-01-13 09:06:59 +08:00 committed by GitHub
parent d8f57bf899
commit cd257b91c5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/controllers/console/datasets/datasets_segments.py
View File

@ -375,9 +375,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
result = []
for index, row in df.iterrows():
if document.doc_form == "qa_model":
data = {"content": row[0], "answer": row[1]}
data = {"content": row.iloc[0], "answer": row.iloc[1]}
else:
data = {"content": row[0]}
data = {"content": row.iloc[0]}
result.append(data)
if len(result) == 0:
raise ValueError("The CSV file is empty.")

2
api/core/rag/index_processor/processor/qa_index_processor.py
View File

@ -112,7 +112,7 @@ class QAIndexProcessor(BaseIndexProcessor):
df = pd.read_csv(file)
text_docs = []
for index, row in df.iterrows():
data = Document(page_content=row[0], metadata={"answer": row[1]})
data = Document(page_content=row.iloc[0], metadata={"answer": row.iloc[1]})
text_docs.append(data)
if len(text_docs) == 0:
raise ValueError("The CSV file is empty.")

2
api/services/annotation_service.py
View File

@ -286,7 +286,7 @@ class AppAnnotationService:
df = pd.read_csv(file)
result = []
for index, row in df.iterrows():
content = {"question": row[0], "answer": row[1]}
content = {"question": row.iloc[0], "answer": row.iloc[1]}
result.append(content)
if len(result) == 0:
raise ValueError("The CSV file is empty.")

4
api/tasks/batch_create_segment_to_index_task.py
View File

@ -77,8 +77,8 @@ def batch_create_segment_to_index_task(
index_node_id=doc_id,
index_node_hash=segment_hash,
position=max_position + 1 if max_position else 1,
content=content,
word_count=len(content),
content=content_str,
word_count=len(content_str),
tokens=tokens,
created_by=user_id,
indexing_at=datetime.datetime.now(datetime.UTC).replace(tzinfo=None),