Merge branch 'langgenius:main' into lindorm-vdb

.github/workflows/expose_service_ports.sh

@@ -9,5 +9,6 @@ yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compos
 yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
+yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/docker-compose.yaml
 
-echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"
+echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"

.github/workflows/vdb-tests.yml

@@ -51,7 +51,7 @@ jobs:
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Stores (TiDB, Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
         uses: hoverkraft-tech/compose-action@v2.0.2
         with:
           compose-file: |
@@ -67,6 +67,7 @@ jobs:
             pgvector
             chroma
             elasticsearch
+            tidb
 
       - name: Test Vector Stores
         run: poetry run -C api bash dev/pytest/pytest_vdb.sh

api/.env.example

@@ -60,17 +60,8 @@ DB_DATABASE=dify
 STORAGE_TYPE=opendal
 
 # Apache OpenDAL storage configuration, refer to https://github.com/apache/opendal
-STORAGE_OPENDAL_SCHEME=fs
-# OpenDAL FS
+OPENDAL_SCHEME=fs
 OPENDAL_FS_ROOT=storage
-# OpenDAL S3
-OPENDAL_S3_ROOT=/
-OPENDAL_S3_BUCKET=your-bucket-name
-OPENDAL_S3_ENDPOINT=https://s3.amazonaws.com
-OPENDAL_S3_ACCESS_KEY_ID=your-access-key
-OPENDAL_S3_SECRET_ACCESS_KEY=your-secret-key
-OPENDAL_S3_REGION=your-region
-OPENDAL_S3_SERVER_SIDE_ENCRYPTION=
 
 # S3 Storage configuration
 S3_USE_AWS_MANAGED_IAM=false
@@ -313,8 +304,7 @@ UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
 UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 
 # Model configuration
-MULTIMODAL_SEND_IMAGE_FORMAT=base64
-MULTIMODAL_SEND_VIDEO_FORMAT=base64
+MULTIMODAL_SEND_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
 CODE_GENERATION_MAX_TOKENS=1024
 
@@ -399,6 +389,8 @@ LOG_FILE_BACKUP_COUNT=5
 LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S
 # Log Timezone
 LOG_TZ=UTC
+# Log format
+LOG_FORMAT=%(asctime)s,%(msecs)d %(levelname)-2s [%(filename)s:%(lineno)d] %(req_id)s %(message)s
 
 # Indexing configuration
 INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
@@ -431,3 +423,7 @@ RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
 
 CREATE_TIDB_SERVICE_JOB_ENABLED=false
 
+# Maximum number of submitted thread count in a ThreadPool for parallel node execution
+MAX_SUBMIT_COUNT=100
+# Lockout duration in seconds
+LOGIN_LOCKOUT_DURATION=86400

api/app.py

@@ -1,13 +1,30 @@
-from app_factory import create_app
-from libs import threadings_utils, version_utils
+from libs import version_utils
 
 # preparation before creating app
 version_utils.check_supported_python_version()
-threadings_utils.apply_gevent_threading_patch()
+
+
+def is_db_command():
+    import sys
+
+    if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
+        return True
+    return False
+
 
 # create app
-app = create_app()
-celery = app.extensions["celery"]
+if is_db_command():
+    from app_factory import create_migrations_app
+
+    app = create_migrations_app()
+else:
+    from app_factory import create_app
+    from libs import threadings_utils
+
+    threadings_utils.apply_gevent_threading_patch()
+
+    app = create_app()
+    celery = app.extensions["celery"]
 
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=5001)

api/app_factory.py

@@ -1,5 +1,4 @@
 import logging
-import os
 import time
 
 from configs import dify_config
@@ -17,15 +16,6 @@ def create_flask_app_with_configs() -> DifyApp:
     dify_app = DifyApp(__name__)
     dify_app.config.from_mapping(dify_config.model_dump())
 
-    # populate configs into system environment variables
-    for key, value in dify_app.config.items():
-        if isinstance(value, str):
-            os.environ[key] = value
-        elif isinstance(value, int | float | bool):
-            os.environ[key] = str(value)
-        elif value is None:
-            os.environ[key] = ""
-
     return dify_app
 
 
@@ -98,3 +88,14 @@ def initialize_extensions(app: DifyApp):
         end_time = time.perf_counter()
         if dify_config.DEBUG:
             logging.info(f"Loaded {short_name} ({round((end_time - start_time) * 1000, 2)} ms)")
+
+
+def create_migrations_app():
+    app = create_flask_app_with_configs()
+    from extensions import ext_database, ext_migrate
+
+    # Initialize only required extensions
+    ext_database.init_app(app)
+    ext_migrate.init_app(app)
+
+    return app

api/configs/feature/__init__.py

@@ -439,6 +439,17 @@ class WorkflowConfig(BaseSettings):
     )
 
 
+class WorkflowNodeExecutionConfig(BaseSettings):
+    """
+    Configuration for workflow node execution
+    """
+
+    MAX_SUBMIT_COUNT: PositiveInt = Field(
+        description="Maximum number of submitted thread count in a ThreadPool for parallel node execution",
+        default=100,
+    )
+
+
 class AuthConfig(BaseSettings):
     """
     Configuration for authentication and OAuth
@@ -474,6 +485,11 @@ class AuthConfig(BaseSettings):
         default=60,
     )
 
+    LOGIN_LOCKOUT_DURATION: PositiveInt = Field(
+        description="Time (in seconds) a user must wait before retrying login after exceeding the rate limit.",
+        default=86400,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -649,14 +665,9 @@ class IndexingConfig(BaseSettings):
     )
 
 
-class VisionFormatConfig(BaseSettings):
-    MULTIMODAL_SEND_IMAGE_FORMAT: Literal["base64", "url"] = Field(
-        description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
-        default="base64",
-    )
-
-    MULTIMODAL_SEND_VIDEO_FORMAT: Literal["base64", "url"] = Field(
-        description="Format for sending videos in multimodal contexts ('base64' or 'url'), default is base64",
+class MultiModalTransferConfig(BaseSettings):
+    MULTIMODAL_SEND_FORMAT: Literal["base64", "url"] = Field(
+        description="Format for sending files in multimodal contexts ('base64' or 'url'), default is base64",
         default="base64",
     )
 
@@ -762,19 +773,20 @@ class FeatureConfig(
     FileAccessConfig,
     FileUploadConfig,
     HttpConfig,
-    VisionFormatConfig,
     InnerAPIConfig,
     IndexingConfig,
     LoggingConfig,
     MailConfig,
     ModelLoadBalanceConfig,
     ModerationConfig,
+    MultiModalTransferConfig,
     PositionConfig,
     RagEtlConfig,
     SecurityConfig,
     ToolConfig,
     UpdateConfig,
     WorkflowConfig,
+    WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     LoginConfig,
     # hosted services config

api/configs/middleware/storage/opendal_storage_config.py

@@ -1,51 +1,9 @@
-from enum import StrEnum
-from typing import Literal
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
 
-class OpenDALScheme(StrEnum):
-    FS = "fs"
-    S3 = "s3"
-
-
 class OpenDALStorageConfig(BaseSettings):
-    STORAGE_OPENDAL_SCHEME: str = Field(
-        default=OpenDALScheme.FS.value,
+    OPENDAL_SCHEME: str = Field(
+        default="fs",
         description="OpenDAL scheme.",
     )
-    # FS
-    OPENDAL_FS_ROOT: str = Field(
-        default="storage",
-        description="Root path for local storage.",
-    )
-    # S3
-    OPENDAL_S3_ROOT: str = Field(
-        default="/",
-        description="Root path for S3 storage.",
-    )
-    OPENDAL_S3_BUCKET: str = Field(
-        default="",
-        description="S3 bucket name.",
-    )
-    OPENDAL_S3_ENDPOINT: str = Field(
-        default="https://s3.amazonaws.com",
-        description="S3 endpoint URL.",
-    )
-    OPENDAL_S3_ACCESS_KEY_ID: str = Field(
-        default="",
-        description="S3 access key ID.",
-    )
-    OPENDAL_S3_SECRET_ACCESS_KEY: str = Field(
-        default="",
-        description="S3 secret access key.",
-    )
-    OPENDAL_S3_REGION: str = Field(
-        default="",
-        description="S3 region.",
-    )
-    OPENDAL_S3_SERVER_SIDE_ENCRYPTION: Literal["aws:kms", ""] = Field(
-        default="",
-        description="S3 server-side encryption.",
-    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.13.2",
+        default="0.14.0",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/app/model_config.py

@@ -65,7 +65,7 @@ def post(self, app_model):
                         provider_type=agent_tool_entity.provider_type,
                         identity_id=f"AGENT.{app_model.id}",
                     )
-                except Exception as e:
+                except Exception:
                     continue
 
                 # get decrypted parameters
@@ -97,7 +97,7 @@ def post(self, app_model):
                             app_id=app_model.id,
                             agent_tool=agent_tool_entity,
                         )
-                    except Exception as e:
+                    except Exception:
                         continue
 
                 manager = ToolParameterConfigurationManager(

api/controllers/console/app/ops_trace.py

@@ -1,4 +1,5 @@
 from flask_restful import Resource, reqparse
+from werkzeug.exceptions import BadRequest
 
 from controllers.console import api
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
@@ -26,7 +27,7 @@ def get(self, app_id):
                 return {"has_not_configured": True}
             return trace_config
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
     @setup_required
     @login_required
@@ -48,7 +49,7 @@ def post(self, app_id):
                 raise TracingConfigCheckError()
             return result
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
     @setup_required
     @login_required
@@ -68,7 +69,7 @@ def patch(self, app_id):
                 raise TracingConfigNotExist()
             return {"result": "success"}
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
     @setup_required
     @login_required
@@ -85,7 +86,7 @@ def delete(self, app_id):
                 raise TracingConfigNotExist()
             return {"result": "success"}
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
 
 api.add_resource(TraceAppConfigApi, "/apps/<uuid:app_id>/trace-config")

api/controllers/console/datasets/datasets_document.py

@@ -948,7 +948,7 @@ def post(self, dataset_id):
                 if document.indexing_status == "completed":
                     raise DocumentAlreadyFinishedError()
                 retry_documents.append(document)
-            except Exception as e:
+            except Exception:
                 logging.exception(f"Failed to retry document, document id: {document_id}")
                 continue
         # retry document

api/controllers/console/explore/recommended_app.py

@@ -4,6 +4,7 @@
 from constants.languages import languages
 from controllers.console import api
 from controllers.console.wraps import account_initialization_required
+from libs.helper import AppIconUrlField
 from libs.login import login_required
 from services.recommended_app_service import RecommendedAppService
 
@@ -12,6 +13,7 @@
     "name": fields.String,
     "mode": fields.String,
     "icon": fields.String,
+    "icon_url": AppIconUrlField,
     "icon_background": fields.String,
 }
 

api/controllers/console/files.py

@@ -1,6 +1,7 @@
 from flask import request
 from flask_login import current_user
 from flask_restful import Resource, marshal_with
+from werkzeug.exceptions import Forbidden
 
 import services
 from configs import dify_config
@@ -58,6 +59,9 @@ def post(self):
         if not file.filename:
             raise FilenameNotExistsError
 
+        if source == "datasets" and not current_user.is_dataset_editor:
+            raise Forbidden()
+
         if source not in ("datasets", None):
             source = None