Merge commit '400392230b47fff5d011b55afd8b0f8b8083ade0'

* commit '400392230b47fff5d011b55afd8b0f8b8083ade0': (74 commits)
  fixed: variable reference error (langgenius#9722)
  add vdb py test (langgenius#9706)
  downgrade unstructured nltk version (langgenius#9726)
  remove ppt import (langgenius#9721)
  Modify characters (langgenius#9707)
  chore: update version to 0.10.1 (langgenius#9689)
  fix: refresh current page if url contains token (langgenius#9718)
  Revert "Feat: use file size limit from api" (langgenius#9714)
  feat: support user-defined configuration of log file size and retention count (langgenius#9610)
  build(deps): bump next from 14.2.4 to 14.2.10 in /web (langgenius#9713)
  Feat: use file size limit from api (langgenius#9711)
  feat(model_runtime): add new model 'claude-3-5-sonnet-20241022' (langgenius#9708)
  build(deps): bump mermaid from 10.4.0 to 10.9.3 in /web (langgenius#9709)
  nltk security issue and upgrade unstructured (langgenius#9558)
  feat: added claude 3.5 sonnet v2 model to Google Cloud Vertex AI (langgenius#9688)
  fix: revert ref usage in handleFormChange to fix IME input issues (langgenius#9672)
  Help documentation URL correction (langgenius#9704)
  fix: workflow [if node] checklist (langgenius#9699)
  feat(api): add video and audio file size limits to upload config (langgenius#9703)
  fix: remove email code login redirect (langgenius#9698)
  ...

# Conflicts:
#	web/yarn.lock

README.md

@@ -168,7 +168,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 > Before installing Dify, make sure your machine meets the following minimum system requirements:
 > 
 >- CPU >= 2 Core
->- RAM >= 4GB
+>- RAM >= 4 GiB
 
 </br>
 

README_CN.md

@@ -174,7 +174,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 在安装 Dify 之前，请确保您的机器满足以下最低系统要求：
 
 - CPU >= 2 Core
-- RAM >= 4GB
+- RAM >= 4 GiB
 
 ### 快速启动
 

api/.env.example

@@ -111,7 +111,7 @@ SUPABASE_URL=your-server-url
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb, upstash
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -220,6 +220,10 @@ BAIDU_VECTOR_DB_DATABASE=dify
 BAIDU_VECTOR_DB_SHARD=1
 BAIDU_VECTOR_DB_REPLICAS=3
 
+# Upstash configuration
+UPSTASH_VECTOR_URL=your-server-url
+UPSTASH_VECTOR_TOKEN=your-access-token
+
 # ViKingDB configuration
 VIKINGDB_ACCESS_KEY=your-ak
 VIKINGDB_SECRET_KEY=your-sk
@@ -239,6 +243,7 @@ UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 # Model Configuration
 MULTIMODAL_SEND_IMAGE_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
+CODE_GENERATION_MAX_TOKENS=1024
 
 # Mail configuration, support: resend, smtp
 MAIL_TYPE=
@@ -304,6 +309,10 @@ RESPECT_XFORWARD_HEADERS_ENABLED=false
 
 # Log file path
 LOG_FILE=
+# Log file max size, the unit is MB
+LOG_FILE_MAX_SIZE=20
+# Log file max backup count
+LOG_FILE_BACKUP_COUNT=5
 
 # Indexing configuration
 INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000

api/app.py

@@ -1,5 +1,7 @@
 import os
 
+from configs import dify_config
+
 if os.environ.get("DEBUG", "false").lower() != "true":
     from gevent import monkey
 
@@ -36,33 +38,27 @@
     time.tzset()
 
 
-# -------------
-# Configuration
-# -------------
-config_type = os.getenv("EDITION", default="SELF_HOSTED")  # ce edition first
-
-
 # create app
 app = create_app()
 celery = app.extensions["celery"]
 
-if app.config.get("TESTING"):
+if dify_config.TESTING:
     print("App is running in TESTING mode")
 
 
 @app.after_request
 def after_request(response):
     """Add Version headers to the response."""
     response.set_cookie("remember_token", "", expires=0)
-    response.headers.add("X-Version", app.config["CURRENT_VERSION"])
-    response.headers.add("X-Env", app.config["DEPLOY_ENV"])
+    response.headers.add("X-Version", dify_config.CURRENT_VERSION)
+    response.headers.add("X-Env", dify_config.DEPLOY_ENV)
     return response
 
 
 @app.route("/health")
 def health():
     return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": app.config["CURRENT_VERSION"]}),
+        json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.CURRENT_VERSION}),
         status=200,
         content_type="application/json",
     )

api/app_factory.py

@@ -10,9 +10,6 @@
     grpc.experimental.gevent.init_gevent()
 
 import json
-import logging
-import sys
-from logging.handlers import RotatingFileHandler
 
 from flask import Flask, Response, request
 from flask_cors import CORS
@@ -27,6 +24,7 @@
     ext_compress,
     ext_database,
     ext_hosting_provider,
+    ext_logging,
     ext_login,
     ext_mail,
     ext_migrate,
@@ -70,43 +68,7 @@ def create_flask_app_with_configs() -> Flask:
 
 def create_app() -> Flask:
     app = create_flask_app_with_configs()
-
-    app.secret_key = app.config["SECRET_KEY"]
-
-    log_handlers = None
-    log_file = app.config.get("LOG_FILE")
-    if log_file:
-        log_dir = os.path.dirname(log_file)
-        os.makedirs(log_dir, exist_ok=True)
-        log_handlers = [
-            RotatingFileHandler(
-                filename=log_file,
-                maxBytes=1024 * 1024 * 1024,
-                backupCount=5,
-            ),
-            logging.StreamHandler(sys.stdout),
-        ]
-
-    logging.basicConfig(
-        level=app.config.get("LOG_LEVEL"),
-        format=app.config.get("LOG_FORMAT"),
-        datefmt=app.config.get("LOG_DATEFORMAT"),
-        handlers=log_handlers,
-        force=True,
-    )
-    log_tz = app.config.get("LOG_TZ")
-    if log_tz:
-        from datetime import datetime
-
-        import pytz
-
-        timezone = pytz.timezone(log_tz)
-
-        def time_converter(seconds):
-            return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
-
-        for handler in logging.root.handlers:
-            handler.formatter.converter = time_converter
+    app.secret_key = dify_config.SECRET_KEY
     initialize_extensions(app)
     register_blueprints(app)
     register_commands(app)
@@ -117,6 +79,7 @@ def time_converter(seconds):
 def initialize_extensions(app):
     # Since the application instance is now created, pass it to each Flask
     # extension instance to bind it to the Flask application instance (app)
+    ext_logging.init_app(app)
     ext_compress.init_app(app)
     ext_code_based_extension.init()
     ext_database.init_app(app)
@@ -187,7 +150,7 @@ def register_blueprints(app):
 
     CORS(
         web_bp,
-        resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
+        resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}},
         supports_credentials=True,
         allow_headers=["Content-Type", "Authorization", "X-App-Code"],
         methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
@@ -198,7 +161,7 @@ def register_blueprints(app):
 
     CORS(
         console_app_bp,
-        resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
+        resources={r"/*": {"origins": dify_config.CONSOLE_CORS_ALLOW_ORIGINS}},
         supports_credentials=True,
         allow_headers=["Content-Type", "Authorization"],
         methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],

api/commands.py

@@ -277,6 +277,7 @@ def migrate_knowledge_vector_database():
         VectorType.TENCENT,
         VectorType.BAIDU,
         VectorType.VIKINGDB,
+        VectorType.UPSTASH,
     }
     page = 1
     while True:

api/configs/feature/__init__.py

@@ -32,6 +32,21 @@ class SecurityConfig(BaseSettings):
         default=5,
     )
 
+    LOGIN_DISABLED: bool = Field(
+        description="Whether to disable login checks",
+        default=False,
+    )
+
+    ADMIN_API_KEY_ENABLE: bool = Field(
+        description="Whether to enable admin api key for authentication",
+        default=False,
+    )
+
+    ADMIN_API_KEY: Optional[str] = Field(
+        description="admin api key for authentication",
+        default=None,
+    )
+
 
 class AppExecutionConfig(BaseSettings):
     """
@@ -304,6 +319,16 @@ class LoggingConfig(BaseSettings):
         default=None,
     )
 
+    LOG_FILE_MAX_SIZE: PositiveInt = Field(
+        description="Maximum file size for file rotation retention, the unit is megabytes (MB)",
+        default=20,
+    )
+
+    LOG_FILE_BACKUP_COUNT: PositiveInt = Field(
+        description="Maximum file backup count file rotation retention",
+        default=5,
+    )
+
     LOG_FORMAT: str = Field(
         description="Format string for log messages",
         default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",

api/configs/middleware/__init__.py

@@ -28,6 +28,7 @@
 from configs.middleware.vdb.relyt_config import RelytConfig
 from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
 from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
+from configs.middleware.vdb.upstash_config import UpstashConfig
 from configs.middleware.vdb.vikingdb_config import VikingDBConfig
 from configs.middleware.vdb.weaviate_config import WeaviateConfig
 
@@ -246,5 +247,6 @@ class MiddlewareConfig(
     ElasticsearchConfig,
     InternalTestConfig,
     VikingDBConfig,
+    UpstashConfig,
 ):
     pass

api/configs/middleware/vdb/upstash_config.py

@@ -0,0 +1,20 @@
+from typing import Optional
+
+from pydantic import Field
+from pydantic_settings import BaseSettings
+
+
+class UpstashConfig(BaseSettings):
+    """
+    Configuration settings for Upstash vector database
+    """
+
+    UPSTASH_VECTOR_URL: Optional[str] = Field(
+        description="URL of the upstash server (e.g., 'https://vector.upstash.io')",
+        default=None,
+    )
+
+    UPSTASH_VECTOR_TOKEN: Optional[str] = Field(
+        description="Token for authenticating with the upstash server",
+        default=None,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.10.0",
+        default="0.10.1",
     )
 
     COMMIT_SHA: str = Field(

api/constants/__init__.py

@@ -15,7 +15,9 @@
 
 if dify_config.ETL_TYPE == "Unstructured":
     DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
-    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "ppt", "xml", "epub"))
+    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    if dify_config.UNSTRUCTURED_API_URL:
+        DOCUMENT_EXTENSIONS.append("ppt")
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
 else:
     DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]

api/controllers/console/admin.py

@@ -1,10 +1,10 @@
-import os
 from functools import wraps
 
 from flask import request
 from flask_restful import Resource, reqparse
 from werkzeug.exceptions import NotFound, Unauthorized
 
+from configs import dify_config
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.wraps import only_edition_cloud
@@ -15,7 +15,7 @@
 def admin_required(view):
     @wraps(view)
     def decorated(*args, **kwargs):
-        if not os.getenv("ADMIN_API_KEY"):
+        if not dify_config.ADMIN_API_KEY:
             raise Unauthorized("API key is invalid.")
 
         auth_header = request.headers.get("Authorization")
@@ -31,7 +31,7 @@ def decorated(*args, **kwargs):
         if auth_scheme != "bearer":
             raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
 
-        if os.getenv("ADMIN_API_KEY") != auth_token:
+        if dify_config.ADMIN_API_KEY != auth_token:
             raise Unauthorized("API key is invalid.")
 
         return view(*args, **kwargs)

api/controllers/console/app/generator.py

@@ -52,4 +52,39 @@ def post(self):
         return rules
 
 
+class RuleCodeGenerateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("instruction", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("model_config", type=dict, required=True, nullable=False, location="json")
+        parser.add_argument("no_variable", type=bool, required=True, default=False, location="json")
+        parser.add_argument("code_language", type=str, required=False, default="javascript", location="json")
+        args = parser.parse_args()
+
+        account = current_user
+        CODE_GENERATION_MAX_TOKENS = int(os.getenv("CODE_GENERATION_MAX_TOKENS", "1024"))
+        try:
+            code_result = LLMGenerator.generate_code(
+                tenant_id=account.current_tenant_id,
+                instruction=args["instruction"],
+                model_config=args["model_config"],
+                code_language=args["code_language"],
+                max_tokens=CODE_GENERATION_MAX_TOKENS,
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+
+        return code_result
+
+
 api.add_resource(RuleGenerateApi, "/rule-generate")
+api.add_resource(RuleCodeGenerateApi, "/rule-code-generate")

api/controllers/console/auth/login.py

@@ -1,11 +1,10 @@
 from typing import cast
 
 import flask_login
-from flask import redirect, request
+from flask import request
 from flask_restful import Resource, reqparse
 
 import services
-from configs import dify_config
 from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import (
@@ -196,10 +195,7 @@ def post(self):
                     email=user_email, name=user_email, interface_language=languages[0]
                 )
             except WorkSpaceNotAllowedCreateError:
-                return redirect(
-                    f"{dify_config.CONSOLE_WEB_URL}/signin"
-                    "?message=Workspace not found, please contact system admin to invite you to join in a workspace."
-                )
+                return NotAllowedCreateWorkspace()
         token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
         AccountService.reset_login_error_rate_limit(args["email"])
         return {"result": "success", "data": token_pair.model_dump()}