admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat: knowledge pipeline (#25360)

Browse Source 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: jyong <718720800@qq.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
Co-authored-by: lyzno1 <yuanyouhuilyz@gmail.com>
Co-authored-by: quicksand <quicksandzn@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: lyzno1 <92089059+lyzno1@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Yongtao Huang <yongtaoh2022@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Hanqing Zhao <sherry9277@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry <xh001x@hotmail.com>
This commit is contained in:
-LAN-
2025-09-18 12:49:10 +08:00
committed by GitHub
parent 7dadb33003
commit 85cda47c70
1772 changed files with 102407 additions and 31710 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
api/controllers/service_api/dataset/document.py
View File

@@ -124,7 +124,12 @@ class DocumentAddByTextApi(DatasetApiResource):
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
)
upload_file = FileService.upload_text(text=str(text), text_name=str(name))
if not current_user:
raise ValueError("current_user is required")
upload_file = FileService(db.engine).upload_text(
text=str(text), text_name=str(name), user_id=current_user.id, tenant_id=tenant_id
)
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -134,6 +139,9 @@ class DocumentAddByTextApi(DatasetApiResource):
# validate args
DocumentService.document_create_args_validate(knowledge_config)
if not current_user:
raise ValueError("current_user is required")
try:
documents, batch = DocumentService.save_document_with_dataset_id(
dataset=dataset,
@@ -199,7 +207,11 @@ class DocumentUpdateByTextApi(DatasetApiResource):
name = args.get("name")
if text is None or name is None:
raise ValueError("Both text and name must be strings.")
upload_file = FileService.upload_text(text=str(text), text_name=str(name))
if not current_user:
raise ValueError("current_user is required")
upload_file = FileService(db.engine).upload_text(
text=str(text), text_name=str(name), user_id=current_user.id, tenant_id=tenant_id
)
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -301,8 +313,9 @@ class DocumentAddByFileApi(DatasetApiResource):
if not isinstance(current_user, EndUser):
raise ValueError("Invalid user account")
upload_file = FileService.upload_file(
if not current_user:
raise ValueError("current_user is required")
upload_file = FileService(db.engine).upload_file(
filename=file.filename,
content=file.read(),
mimetype=file.mimetype,
@@ -390,10 +403,14 @@ class DocumentUpdateByFileApi(DatasetApiResource):
if not file.filename:
raise FilenameNotExistsError
if not current_user:
raise ValueError("current_user is required")
if not isinstance(current_user, EndUser):
raise ValueError("Invalid user account")
try:
if not isinstance(current_user, EndUser):
raise ValueError("Invalid user account")
upload_file = FileService.upload_file(
upload_file = FileService(db.engine).upload_file(
filename=file.filename,
content=file.read(),
mimetype=file.mimetype,
@@ -571,7 +588,7 @@ class DocumentApi(DatasetApiResource):
response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
elif metadata == "without":
dataset_process_rules = DatasetService.get_process_rules(dataset_id)
document_process_rules = document.dataset_process_rule.to_dict()
document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
data_source_info = document.data_source_detail_dict
response = {
"id": document.id,
@@ -604,7 +621,7 @@ class DocumentApi(DatasetApiResource):
}
else:
dataset_process_rules = DatasetService.get_process_rules(dataset_id)
document_process_rules = document.dataset_process_rule.to_dict()
document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
data_source_info = document.data_source_detail_dict
response = {
"id": document.id,