From ce2996e7d41974b49e2dda5745c1eb120bd66180 Mon Sep 17 00:00:00 2001
From: Jyong <76649700+JohnJyong@users.noreply.github.com>
Date: Mon, 19 Jun 2023 16:32:03 +0800
Subject: [PATCH] Fix/dataset init (#409)

---
 api/.env.example                | 6 ++++++
 api/services/dataset_service.py | 7 ++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/api/.env.example b/api/.env.example
index b9c819535c..51a74b0ddd 100644
--- a/api/.env.example
+++ b/api/.env.example
@@ -85,3 +85,9 @@ SENTRY_DSN=
 # DEBUG
 DEBUG=false
 SQLALCHEMY_ECHO=false
+
+# Notion import configuration, support public and internal
+NOTION_INTEGRATION_TYPE=public
+NOTION_CLIENT_SECRET=you-client-secret
+NOTION_CLIENT_ID=you-client-id
+NOTION_INTERNAL_SECRET=you-internal-secret
\ No newline at end of file
diff --git a/api/services/dataset_service.py b/api/services/dataset_service.py
index 2619cdcbe1..10f1fc2f35 100644
--- a/api/services/dataset_service.py
+++ b/api/services/dataset_service.py
@@ -78,7 +78,7 @@ class DatasetService:
             raise DatasetNameDuplicateError(
                 f'Dataset with name {name} already exists.')
 
-        dataset = Dataset(name=name, indexing_technique=indexing_technique, data_source_type='upload_file')
+        dataset = Dataset(name=name, indexing_technique=indexing_technique)
         # dataset = Dataset(name=name, provider=provider, config=config)
         dataset.created_by = account.id
         dataset.updated_by = account.id
@@ -374,6 +374,11 @@ class DocumentService:
     def save_document_with_dataset_id(dataset: Dataset, document_data: dict,
                                       account: Account, dataset_process_rule: Optional[DatasetProcessRule] = None,
                                       created_from: str = 'web'):
+        # if dataset is empty, update dataset data_source_type
+        if not dataset.data_source_type:
+            dataset.data_source_type = document_data["data_source"]["type"]
+            db.session.commit()
+
         if not dataset.indexing_technique:
             if 'indexing_technique' not in document_data \
                     or document_data['indexing_technique'] not in Dataset.INDEXING_TECHNIQUE_LIST: