opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: fix create-by-file doc_form (#31346)

This commit is contained in:
wangxiaolei 2026-01-23 11:34:47 +08:00 committed by GitHub
parent c8ae6e39d2
commit 056095238b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 24 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
api/controllers/service_api/dataset/document.py
View File

@ -261,17 +261,6 @@ class DocumentAddByFileApi(DatasetApiResource):
@cloud_edition_billing_rate_limit_check("knowledge", "dataset")
def post(self, tenant_id, dataset_id):
"""Create document by upload file."""
args = {}
if "data" in request.form:
args = json.loads(request.form["data"])
if "doc_form" not in args:
args["doc_form"] = "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).where(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
@ -280,6 +269,18 @@ class DocumentAddByFileApi(DatasetApiResource):
if dataset.provider == "external":
raise ValueError("External datasets are not supported.")
args = {}
if "data" in request.form:
args = json.loads(request.form["data"])
if "doc_form" not in args:
args["doc_form"] = dataset.chunk_structure or "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
indexing_technique = args.get("indexing_technique") or dataset.indexing_technique
if not indexing_technique:
raise ValueError("indexing_technique is required.")
@ -370,17 +371,6 @@ class DocumentUpdateByFileApi(DatasetApiResource):
@cloud_edition_billing_rate_limit_check("knowledge", "dataset")
def post(self, tenant_id, dataset_id, document_id):
"""Update document by upload file."""
args = {}
if "data" in request.form:
args = json.loads(request.form["data"])
if "doc_form" not in args:
args["doc_form"] = "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).where(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
@ -389,6 +379,18 @@ class DocumentUpdateByFileApi(DatasetApiResource):
if dataset.provider == "external":
raise ValueError("External datasets are not supported.")
args = {}
if "data" in request.form:
args = json.loads(request.form["data"])
if "doc_form" not in args:
args["doc_form"] = dataset.chunk_structure or "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
# indexing_technique is already set in dataset since this is an update
args["indexing_technique"] = dataset.indexing_technique