feat: update login type info

* main: (77 commits)
  feat: add voyage ai as a new model provider (#8747)
  docs: add english versions for the files customizable_model_scale_out and predefined_model_scale_out (#8871)
  fix: #8843 event: tts_message_end always return in api streaming resp… (#8846)
  Add Jamba and Llama3.2 model support (#8878)
  fix(workflow): update tagging logic in GitHub Actions (#8882)
  chore: bump ruff to 0.6.8 for fixing violation in SIM910 (#8869)
  refactor: update Callback to an abstract class (#8868)
  feat: deprecate gte-Qwen2-7B-instruct embedding model (#8866)
  feat: add internlm2.5-20b and qwen2.5-coder-7b model (#8862)
  fix: customize model credentials were invalid despite the provider credentials being active (#8864)
  fix: update qwen2.5-coder-7b model name (#8861)
  fix(workflow/nodes/knowledge-retrieval/use-config): Preserve rerankin… (#8842)
  chore: fix wrong VectorType match case (#8857)
  feat: add min-connection and max-connection for pgvector (#8841)
  feat(Tools): add feishu tools (#8800)
  fix: delete harm catalog settings for gemini (#8829)
  Add Llama3.2 models in Groq provider (#8831)
  feat: deprecate mistral model for siliconflow (#8828)
  fix: AnalyticdbVector retrieval scores (#8803)
  fix: close log status option raise error (#8826)
  ...

.github/workflows/build-push.yml

@@ -125,7 +125,7 @@ jobs:
         with:
           images: ${{ env[matrix.image_name_env] }}
           tags: |
-            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') && !contains(github.ref, '-') }}
             type=ref,event=branch
             type=sha,enable=true,priority=100,prefix=,suffix=,format=long
             type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}

api/.env.example

@@ -291,4 +291,4 @@ POSITION_TOOL_EXCLUDES=
 
 POSITION_PROVIDER_PINS=
 POSITION_PROVIDER_INCLUDES=
-POSITION_PROVIDER_EXCLUDES=
+POSITION_PROVIDER_EXCLUDES=

api/configs/feature/__init__.py

@@ -1,6 +1,15 @@
 from typing import Annotated, Optional
 
-from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field
+from pydantic import (
+    AliasChoices,
+    Field,
+    HttpUrl,
+    NegativeInt,
+    NonNegativeInt,
+    PositiveFloat,
+    PositiveInt,
+    computed_field,
+)
 from pydantic_settings import BaseSettings
 
 from configs.feature.hosted_service import HostedServiceConfig
@@ -462,6 +471,11 @@ class MailConfig(BaseSettings):
         default=False,
     )
 
+    EMAIL_SEND_IP_LIMIT_PER_MINUTE: PositiveInt = Field(
+        description="Maximum number of emails allowed to be sent from the same IP address in a minute",
+        default=50,
+    )
+
 
 class RagEtlConfig(BaseSettings):
     """
@@ -598,6 +612,33 @@ class PositionConfig(BaseSettings):
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
 
+class LoginConfig(BaseSettings):
+    ENABLE_EMAIL_CODE_LOGIN: bool = Field(
+        description="whether to enable email code login",
+        default=False,
+    )
+    ENABLE_EMAIL_PASSWORD_LOGIN: bool = Field(
+        description="whether to enable email password login",
+        default=True,
+    )
+    ENABLE_SOCIAL_OAUTH_LOGIN: bool = Field(
+        description="whether to enable github/google oauth login",
+        default=False,
+    )
+    EMAIL_CODE_LOGIN_TOKEN_EXPIRY_HOURS: PositiveFloat = Field(
+        description="expiry time in hours for email code login token",
+        default=1 / 12,
+    )
+    ALLOW_REGISTER: bool = Field(
+        description="whether to enable register",
+        default=True,
+    )
+    ALLOW_CREATE_WORKSPACE: bool = Field(
+        description="whether to enable create workspace",
+        default=False,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
@@ -623,6 +664,7 @@ class FeatureConfig(
     WorkflowConfig,
     WorkspaceConfig,
     PositionConfig,
+    LoginConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/controllers/console/auth/activate.py

@@ -1,17 +1,15 @@
-import base64
 import datetime
-import secrets
 
+from flask import request
 from flask_restful import Resource, reqparse
 
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.error import AlreadyActivateError
 from extensions.ext_database import db
-from libs.helper import StrLen, email, timezone
-from libs.password import hash_password, valid_password
-from models.account import AccountStatus
-from services.account_service import RegisterService
+from libs.helper import StrLen, email, get_remote_ip, timezone
+from models.account import AccountStatus, Tenant
+from services.account_service import AccountService, RegisterService
 
 
 class ActivateCheckApi(Resource):
@@ -27,8 +25,18 @@ class ActivateCheckApi(Resource):
         token = args["token"]
 
         invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
-
-        return {"is_valid": invitation is not None, "workspace_name": invitation["tenant"].name if invitation else None}
+        if invitation:
+            data = invitation.get("data", {})
+            tenant: Tenant = invitation.get("tenant", None)
+            workspace_name = tenant.name if tenant else None
+            workspace_id = tenant.id if tenant else None
+            invitee_email = data.get("email") if data else None
+            return {
+                "is_valid": invitation is not None,
+                "data": {"workspace_name": workspace_name, "workspace_id": workspace_id, "email": invitee_email},
+            }
+        else:
+            return {"is_valid": False}
 
 
 class ActivateApi(Resource):
@@ -38,7 +46,6 @@ class ActivateApi(Resource):
         parser.add_argument("email", type=email, required=False, nullable=True, location="json")
         parser.add_argument("token", type=str, required=True, nullable=False, location="json")
         parser.add_argument("name", type=StrLen(30), required=True, nullable=False, location="json")
-        parser.add_argument("password", type=valid_password, required=True, nullable=False, location="json")
         parser.add_argument(
             "interface_language", type=supported_language, required=True, nullable=False, location="json"
         )
@@ -54,15 +61,6 @@ class ActivateApi(Resource):
         account = invitation["account"]
         account.name = args["name"]
 
-        # generate password salt
-        salt = secrets.token_bytes(16)
-        base64_salt = base64.b64encode(salt).decode()
-
-        # encrypt password with salt
-        password_hashed = hash_password(args["password"], salt)
-        base64_password_hashed = base64.b64encode(password_hashed).decode()
-        account.password = base64_password_hashed
-        account.password_salt = base64_salt
         account.interface_language = args["interface_language"]
         account.timezone = args["timezone"]
         account.interface_theme = "light"
@@ -70,7 +68,9 @@ class ActivateApi(Resource):
         account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
-        return {"result": "success"}
+        token = AccountService.login(account, ip_address=get_remote_ip(request))
+
+        return {"result": "success", "data": token}
 
 
 api.add_resource(ActivateCheckApi, "/activate/check")

api/controllers/console/auth/error.py

@@ -27,5 +27,29 @@ class InvalidTokenError(BaseHTTPException):
 
 class PasswordResetRateLimitExceededError(BaseHTTPException):
     error_code = "password_reset_rate_limit_exceeded"
-    description = "Password reset rate limit exceeded. Try again later."
+    description = "Too many password reset emails have been sent. Please try again in 5 minutes."
+    code = 429
+
+
+class EmailCodeError(BaseHTTPException):
+    error_code = "email_code_error"
+    description = "Email code is invalid or expired."
+    code = 400
+
+
+class EmailOrPasswordMismatchError(BaseHTTPException):
+    error_code = "email_or_password_mismatch"
+    description = "The email or password is mismatched."
+    code = 400
+
+
+class EmailPasswordLoginLimitError(BaseHTTPException):
+    error_code = "email_code_login_limit"
+    description = "The account was locked for 24 hours because the password was entered too many times."
+    code = 429
+
+
+class EmailCodeLoginRateLimitExceededError(BaseHTTPException):
+    error_code = "email_code_login_rate_limit_exceeded"
+    description = "Too many login emails have been sent. Please try again in 5 minutes."
     code = 429

api/controllers/console/auth/forgot_password.py

@@ -1,65 +1,80 @@
 import base64
-import logging
 import secrets
 
+from flask import request
 from flask_restful import Resource, reqparse
 
+from configs import dify_config
+from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import (
+    EmailCodeError,
     InvalidEmailError,
     InvalidTokenError,
     PasswordMismatchError,
-    PasswordResetRateLimitExceededError,
 )
+from controllers.console.error import EmailSendIpLimitError, NotAllowedCreateWorkspace, NotAllowedRegister
 from controllers.console.setup import setup_required
+from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
-from libs.helper import email as email_validate
+from libs.helper import email, get_remote_ip
 from libs.password import hash_password, valid_password
 from models.account import Account
-from services.account_service import AccountService
-from services.errors.account import RateLimitExceededError
+from services.account_service import AccountService, TenantService
 
 
 class ForgotPasswordSendEmailApi(Resource):
     @setup_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
         args = parser.parse_args()
 
-        email = args["email"]
+        ip_address = get_remote_ip(request)
+        if AccountService.is_email_send_ip_limit(ip_address):
+            raise EmailSendIpLimitError()
 
-        if not email_validate(email):
-            raise InvalidEmailError()
-
-        account = Account.query.filter_by(email=email).first()
-
-        if account:
-            try:
-                AccountService.send_reset_password_email(account=account)
-            except RateLimitExceededError:
-                logging.warning(f"Rate limit exceeded for email: {account.email}")
-                raise PasswordResetRateLimitExceededError()
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
         else:
-            # Return success to avoid revealing email registration status
-            logging.warning(f"Attempt to reset password for unregistered email: {email}")
+            language = "en-US"
 
-        return {"result": "success"}
+        account = Account.query.filter_by(email=args["email"]).first()
+        token = None
+        if account is None:
+            if dify_config.ALLOW_REGISTER:
+                token = AccountService.send_reset_password_email(email=args["email"], language=language)
+            else:
+                raise NotAllowedRegister()
+        else:
+            token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)
+
+        return {"result": "success", "data": token}
 
 
 class ForgotPasswordCheckApi(Resource):
     @setup_required
     def post(self):
         parser = reqparse.RequestParser()
+        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("code", type=str, required=True, location="json")
         parser.add_argument("token", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
-        token = args["token"]
 
-        reset_data = AccountService.get_reset_password_data(token)
+        user_email = args["email"]
 
-        if reset_data is None:
-            return {"is_valid": False, "email": None}
-        return {"is_valid": True, "email": reset_data.get("email")}
+        token_data = AccountService.get_reset_password_data(args["token"])
+        if token_data is None:
+            raise InvalidTokenError()
+
+        if user_email != token_data.get("email"):
+            raise InvalidEmailError()
+
+        if args["code"] != token_data.get("code"):
+            raise EmailCodeError()
+
+        return {"is_valid": True, "email": token_data.get("email")}
 
 
 class ForgotPasswordResetApi(Resource):
@@ -92,11 +107,30 @@ class ForgotPasswordResetApi(Resource):
         base64_password_hashed = base64.b64encode(password_hashed).decode()
 
         account = Account.query.filter_by(email=reset_data.get("email")).first()
-        account.password = base64_password_hashed
-        account.password_salt = base64_salt
-        db.session.commit()
+        if account:
+            account.password = base64_password_hashed
+            account.password_salt = base64_salt
+            db.session.commit()
+            tenant = TenantService.get_join_tenants(account)
+            if not tenant:
+                if not dify_config.ALLOW_CREATE_WORKSPACE:
+                    raise NotAllowedCreateWorkspace()
+                else:
+                    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                    TenantService.create_tenant_member(tenant, account, role="owner")
+                    account.current_tenant = tenant
+                    tenant_was_created.send(tenant)
+        else:
+            account = AccountService.create_account_and_tenant(
+                email=reset_data.get("email"),
+                name=reset_data.get("email"),
+                password=password_confirm,
+                interface_language=languages[0],
+            )
 
-        return {"result": "success"}
+        token = AccountService.login(account, ip_address=get_remote_ip(request))
+
+        return {"result": "success", "data": token}
 
 
 api.add_resource(ForgotPasswordSendEmailApi, "/forgot-password")

api/controllers/console/auth/login.py

@@ -1,16 +1,28 @@
 from typing import cast
 
 import flask_login
-from flask import request
+from flask import redirect, 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 (
+    EmailCodeError,
+    EmailOrPasswordMismatchError,
+    EmailPasswordLoginLimitError,
+    InvalidEmailError,
+    InvalidTokenError,
+)
+from controllers.console.error import EmailSendIpLimitError, NotAllowedCreateWorkspace, NotAllowedRegister
 from controllers.console.setup import setup_required
+from events.tenant_event import tenant_was_created
 from libs.helper import email, get_remote_ip
 from libs.password import valid_password
 from models.account import Account
-from services.account_service import AccountService, TenantService
+from services.account_service import AccountService, RegisterService, TenantService
+from services.errors.workspace import WorkSpaceNotAllowedCreateError
 
 
 class LoginApi(Resource):
@@ -23,15 +35,37 @@ class LoginApi(Resource):
         parser.add_argument("email", type=email, required=True, location="json")
         parser.add_argument("password", type=valid_password, required=True, location="json")
         parser.add_argument("remember_me", type=bool, required=False, default=False, location="json")
+        parser.add_argument("invite_token", type=str, required=False, default=None, location="json")
         args = parser.parse_args()
 
-        # todo: Verify the recaptcha
+        is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args["email"])
+        if is_login_error_rate_limit:
+            raise EmailPasswordLoginLimitError()
+
+        invitation = args["invite_token"]
+        if invitation:
+            invitation = RegisterService.get_invitation_if_token_valid(None, args["email"], invitation)
 
         try:
-            account = AccountService.authenticate(args["email"], args["password"])
-        except services.errors.account.AccountLoginError as e:
-            return {"code": "unauthorized", "message": str(e)}, 401
+            if invitation:
+                data = invitation.get("data", {})
+                invitee_email = data.get("email") if data else None
+                if invitee_email != args["email"]:
+                    raise InvalidEmailError()
+                account = AccountService.authenticate(args["email"], args["password"], args["invite_token"])
+            else:
+                account = AccountService.authenticate(args["email"], args["password"])
+        except services.errors.account.AccountLoginError:
+            raise NotAllowedRegister()
+        except services.errors.account.AccountPasswordError:
+            AccountService.add_login_error_rate_limit(args["email"])
+            raise EmailOrPasswordMismatchError()
+        except services.errors.account.AccountNotFoundError:
+            if not dify_config.ALLOW_REGISTER:
+                raise NotAllowedRegister()
 
+            token = AccountService.send_reset_password_email(email=args["email"])
+            return {"result": "fail", "data": token, "message": "account_not_found"}
         # SELF_HOSTED only have one workspace
         tenants = TenantService.get_join_tenants(account)
         if len(tenants) == 0:
@@ -41,7 +75,7 @@ class LoginApi(Resource):
             }
 
         token = AccountService.login(account, ip_address=get_remote_ip(request))
-
+        AccountService.reset_login_error_rate_limit(args["email"])
         return {"result": "success", "data": token}
 
 
@@ -55,56 +89,111 @@ class LogoutApi(Resource):
         return {"result": "success"}
 
 
-class ResetPasswordApi(Resource):
+class ResetPasswordSendEmailApi(Resource):
     @setup_required
-    def get(self):
-        # parser = reqparse.RequestParser()
-        # parser.add_argument('email', type=email, required=True, location='json')
-        # args = parser.parse_args()
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
+        args = parser.parse_args()
 
-        # import mailchimp_transactional as MailchimpTransactional
-        # from mailchimp_transactional.api_client import ApiClientError
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
 
-        # account = {'email': args['email']}
-        # account = AccountService.get_by_email(args['email'])
-        # if account is None:
-        #     raise ValueError('Email not found')
-        # new_password = AccountService.generate_password()
-        # AccountService.update_password(account, new_password)
+        account = AccountService.get_user_through_email(args["email"])
+        if account is None:
+            if dify_config.ALLOW_REGISTER:
+                token = AccountService.send_reset_password_email(email=args["email"], language=language)
+            else:
+                raise NotAllowedRegister()
+        else:
+            token = AccountService.send_reset_password_email(account=account, language=language)
 
-        # todo: Send email
-        # MAILCHIMP_API_KEY = dify_config.MAILCHIMP_TRANSACTIONAL_API_KEY
-        # mailchimp = MailchimpTransactional(MAILCHIMP_API_KEY)
+        return {"result": "success", "data": token}
 
-        # message = {
-        #     'from_email': 'noreply@example.com',
-        #     'to': [{'email': account['email']}],
-        #     'subject': 'Reset your Dify password',
-        #     'html': """
-        #         <p>Dear User,</p>
-        #         <p>The Dify team has generated a new password for you, details as follows:</p>
-        #         <p><strong>{new_password}</strong></p>
-        #         <p>Please change your password to log in as soon as possible.</p>
-        #         <p>Regards,</p>
-        #         <p>The Dify Team</p>
-        #     """
-        # }
 
-        # response = mailchimp.messages.send({
-        #     'message': message,
-        #     # required for transactional email
-        #     ' settings': {
-        #         'sandbox_mode': dify_config.MAILCHIMP_SANDBOX_MODE,
-        #     },
-        # })
+class EmailCodeLoginSendEmailApi(Resource):
+    @setup_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
+        args = parser.parse_args()
 
-        # Check if MSG was sent
-        # if response.status_code != 200:
-        #     # handle error
-        #     pass
+        ip_address = get_remote_ip(request)
+        if AccountService.is_email_send_ip_limit(ip_address):
+            raise EmailSendIpLimitError()
 
-        return {"result": "success"}
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
+
+        account = AccountService.get_user_through_email(args["email"])
+        if account is None:
+            if dify_config.ALLOW_REGISTER:
+                token = AccountService.send_email_code_login_email(email=args["email"], language=language)
+            else:
+                raise NotAllowedRegister()
+        else:
+            token = AccountService.send_email_code_login_email(account=account, language=language)
+
+        return {"result": "success", "data": token}
+
+
+class EmailCodeLoginApi(Resource):
+    @setup_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("code", type=str, required=True, location="json")
+        parser.add_argument("token", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        user_email = args["email"]
+
+        token_data = AccountService.get_email_code_login_data(args["token"])
+        if token_data is None:
+            raise InvalidTokenError()
+
+        if token_data["email"] != args["email"]:
+            raise InvalidEmailError()
+
+        if token_data["code"] != args["code"]:
+            raise EmailCodeError()
+
+        AccountService.revoke_email_code_login_token(args["token"])
+        account = AccountService.get_user_through_email(user_email)
+        if account:
+            tenant = TenantService.get_join_tenants(account)
+            if not tenant:
+                if not dify_config.ALLOW_CREATE_WORKSPACE:
+                    raise NotAllowedCreateWorkspace()
+                else:
+                    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                    TenantService.create_tenant_member(tenant, account, role="owner")
+                    account.current_tenant = tenant
+                    tenant_was_created.send(tenant)
+
+        if account is None:
+            try:
+                account = AccountService.create_account_and_tenant(
+                    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."
+                )
+        token = AccountService.login(account, ip_address=get_remote_ip(request))
+        AccountService.reset_login_error_rate_limit(args["email"])
+        return {"result": "success", "data": token}
 
 
 api.add_resource(LoginApi, "/login")
 api.add_resource(LogoutApi, "/logout")
+api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
+api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")
+api.add_resource(ResetPasswordSendEmailApi, "/reset-password")

api/controllers/console/auth/oauth.py

@@ -5,14 +5,18 @@ from typing import Optional
 import requests
 from flask import current_app, redirect, request
 from flask_restful import Resource
+from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
 from constants.languages import languages
+from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import get_remote_ip
 from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
 from models.account import Account, AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
+from services.errors.account import AccountNotFoundError
+from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
 
 from .. import api
 
@@ -42,6 +46,7 @@ def get_oauth_providers():
 
 class OAuthLogin(Resource):
     def get(self, provider: str):
+        invite_token = request.args.get("invite_token") or None
         OAUTH_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_PROVIDERS.get(provider)
@@ -49,7 +54,7 @@ class OAuthLogin(Resource):
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
 
-        auth_url = oauth_provider.get_authorization_url()
+        auth_url = oauth_provider.get_authorization_url(invite_token=invite_token)
         return redirect(auth_url)
 
 
@@ -62,6 +67,11 @@ class OAuthCallback(Resource):
             return {"error": "Invalid provider"}, 400
 
         code = request.args.get("code")
+        state = request.args.get("state")
+        invite_token = None
+        if state:
+            invite_token = state
+
         try:
             token = oauth_provider.get_access_token(code)
             user_info = oauth_provider.get_user_info(token)
@@ -69,7 +79,27 @@ class OAuthCallback(Resource):
             logging.exception(f"An error occurred during the OAuth process with {provider}: {e.response.text}")
             return {"error": "OAuth process failed"}, 400
 
-        account = _generate_account(provider, user_info)
+        if invite_token and RegisterService.is_valid_invite_token(invite_token):
+            invitation = RegisterService._get_invitation_by_token(token=invite_token)
+            if invitation:
+                invitation_email = invitation.get("email", None)
+                if invitation_email != user_info.email:
+                    return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
+
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}")
+
+        try:
+            account = _generate_account(provider, user_info)
+        except AccountNotFoundError:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account not found.")
+        except WorkSpaceNotFoundError:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Workspace not found.")
+        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."
+            )
+
         # Check account status
         if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
             return {"error": "Account is banned or closed."}, 403
@@ -79,7 +109,15 @@ class OAuthCallback(Resource):
             account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
-        TenantService.create_owner_tenant_if_not_exist(account)
+        try:
+            TenantService.create_owner_tenant_if_not_exist(account)
+        except Unauthorized:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Workspace not found.")
+        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."
+            )
 
         token = AccountService.login(account, ip_address=get_remote_ip(request))
 
@@ -99,8 +137,20 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
     # Get account by openid or email.
     account = _get_account_by_openid_or_email(provider, user_info)
 
+    if account:
+        tenant = TenantService.get_join_tenants(account)
+        if not tenant:
+            if not dify_config.ALLOW_CREATE_WORKSPACE:
+                raise WorkSpaceNotAllowedCreateError()
+            else:
+                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                TenantService.create_tenant_member(tenant, account, role="owner")
+                account.current_tenant = tenant
+                tenant_was_created.send(tenant)
+
     if not account:
-        # Create account
+        if not dify_config.ALLOW_REGISTER:
+            raise AccountNotFoundError()
         account_name = user_info.name or "Dify"
         account = RegisterService.register(
             email=user_info.email, name=account_name, password=None, open_id=user_info.id, provider=provider

api/controllers/console/datasets/datasets.py

@@ -563,10 +563,10 @@ class DatasetRetrievalSettingApi(Resource):
             case (
                 VectorType.MILVUS
                 | VectorType.RELYT
-                | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT
+                | VectorType.PGVECTO_RS
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -577,6 +577,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
+                | VectorType.PGVECTOR
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/error.py

@@ -38,3 +38,21 @@ class AlreadyActivateError(BaseHTTPException):
     error_code = "already_activate"
     description = "Auth Token is invalid or account already activated, please check again."
     code = 403
+
+
+class NotAllowedCreateWorkspace(BaseHTTPException):
+    error_code = "unauthorized"
+    description = "Workspace not found, please contact system admin to invite you to join in a workspace."
+    code = 400
+
+
+class NotAllowedRegister(BaseHTTPException):
+    error_code = "unauthorized"
+    description = "Account not found."
+    code = 400
+
+
+class EmailSendIpLimitError(BaseHTTPException):
+    error_code = "email_send_ip_limit"
+    description = "Too many emails have been sent from this IP address recently. Please try again later."
+    code = 429

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -231,7 +231,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
             except Exception as e:
                 logger.error(e)
                 break
-        yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
+        if tts_publisher:
+            yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
 
     def _process_stream_response(
         self,

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -212,7 +212,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
             except Exception as e:
                 logger.error(e)
                 break
-        yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
+        if tts_publisher:
+            yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
 
     def _process_stream_response(
         self,

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -248,7 +248,8 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
             else:
                 start_listener_time = time.time()
                 yield MessageAudioStreamResponse(audio=audio.audio, task_id=task_id)
-        yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
+        if publisher:
+            yield MessageAudioEndStreamResponse(audio="", task_id=task_id)
 
     def _process_stream_response(
         self, publisher: AppGeneratorTTSPublisher, trace_manager: Optional[TraceQueueManager] = None

api/core/entities/provider_configuration.py

@@ -119,7 +119,7 @@ class ProviderConfiguration(BaseModel):
                         credentials = model_configuration.credentials
                         break
 
-            if self.custom_configuration.provider:
+            if not credentials and self.custom_configuration.provider:
                 credentials = self.custom_configuration.provider.credentials
 
             return credentials

api/core/model_runtime/callbacks/base_callback.py

@@ -1,3 +1,4 @@
+from abc import ABC, abstractmethod
 from typing import Optional
 
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
@@ -13,7 +14,7 @@ _TEXT_COLOR_MAPPING = {
 }
 
 
-class Callback:
+class Callback(ABC):
     """
     Base class for callbacks.
     Only for LLM.
@@ -21,6 +22,7 @@ class Callback:
 
     raise_error: bool = False
 
+    @abstractmethod
     def on_before_invoke(
         self,
         llm_instance: AIModel,
@@ -48,6 +50,7 @@ class Callback:
         """
         raise NotImplementedError()
 
+    @abstractmethod
     def on_new_chunk(
         self,
         llm_instance: AIModel,
@@ -77,6 +80,7 @@ class Callback:
         """
         raise NotImplementedError()
 
+    @abstractmethod
     def on_after_invoke(
         self,
         llm_instance: AIModel,
@@ -106,6 +110,7 @@ class Callback:
         """
         raise NotImplementedError()
 
+    @abstractmethod
     def on_invoke_error(
         self,
         llm_instance: AIModel,

api/core/model_runtime/docs/en_US/customizable_model_scale_out.md

@@ -0,0 +1,310 @@
+## Custom Integration of Pre-defined Models
+
+### Introduction
+
+After completing the vendors integration, the next step is to connect the vendor's models. To illustrate the entire connection process, we will use Xinference as an example to demonstrate a complete vendor integration.
+
+It is important to note that for custom models, each model connection requires a complete vendor credential.
+
+Unlike pre-defined models, a custom vendor integration always includes the following two parameters, which do not need to be defined in the vendor YAML file.
+
+![](images/index/image-3.png)
+
+As mentioned earlier, vendors do not need to implement validate_provider_credential. The runtime will automatically call the corresponding model layer's validate_credentials to validate the credentials based on the model type and name selected by the user.
+
+### Writing the Vendor YAML
+
+First, we need to identify the types of models supported by the vendor we are integrating.
+
+Currently supported model types are as follows:
+
+- `llm` Text Generation Models
+
+- `text_embedding` Text Embedding Models
+
+- `rerank` Rerank Models
+
+- `speech2text` Speech-to-Text
+
+- `tts` Text-to-Speech
+
+- `moderation` Moderation
+
+Xinference supports LLM, Text Embedding, and Rerank. So we will start by writing xinference.yaml.
+
+```yaml
+provider: xinference #Define the vendor identifier
+label: # Vendor display name, supports both en_US (English) and zh_Hans (Simplified Chinese). If zh_Hans is not set, it will use en_US by default.
+  en_US: Xorbits Inference
+icon_small: # Small icon, refer to other vendors' icons stored in the _assets directory within the vendor implementation directory; follows the same language policy as the label
+  en_US: icon_s_en.svg
+icon_large: # Large icon
+  en_US: icon_l_en.svg
+help: # Help information
+  title:
+    en_US: How to deploy Xinference
+    zh_Hans: 如何部署 Xinference
+  url:
+    en_US: https://github.com/xorbitsai/inference
+supported_model_types: # Supported model types. Xinference supports LLM, Text Embedding, and Rerank
+- llm
+- text-embedding
+- rerank
+configurate_methods: # Since Xinference is a locally deployed vendor with no predefined models, users need to deploy whatever models they need according to Xinference documentation. Thus, it only supports custom models.
+- customizable-model
+provider_credential_schema:
+  credential_form_schemas:
+```
+
+
+Then, we need to determine what credentials are required to define a model in Xinference.
+
+- Since it supports three different types of models, we need to specify the model_type to denote the model type. Here is how we can define it:
+
+```yaml
+provider_credential_schema:
+  credential_form_schemas:
+  - variable: model_type
+    type: select
+    label:
+      en_US: Model type
+      zh_Hans: 模型类型
+    required: true
+    options:
+    - value: text-generation
+      label:
+        en_US: Language Model
+        zh_Hans: 语言模型
+    - value: embeddings
+      label:
+        en_US: Text Embedding
+    - value: reranking
+      label:
+        en_US: Rerank
+```
+
+- Next, each model has its own model_name, so we need to define that here:
+
+```yaml
+  - variable: model_name
+    type: text-input
+    label:
+      en_US: Model name
+      zh_Hans: 模型名称
+    required: true
+    placeholder:
+      zh_Hans: 填写模型名称
+      en_US: Input model name
+```
+
+- Specify the Xinference local deployment address:
+
+```yaml
+  - variable: server_url
+    label:
+      zh_Hans: 服务器URL
+      en_US: Server url
+    type: text-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入Xinference的服务器地址，如 https://example.com/xxx
+      en_US: Enter the url of your Xinference, for example https://example.com/xxx
+```
+
+- Each model has a unique model_uid, so we also need to define that here:
+
+```yaml
+  - variable: model_uid
+    label:
+      zh_Hans: 模型UID
+      en_US: Model uid
+    type: text-input
+    required: true
+    placeholder:
+      zh_Hans: 在此输入您的Model UID
+      en_US: Enter the model uid
+```
+
+Now, we have completed the basic definition of the vendor.
+
+### Writing the Model Code
+
+Next, let's take the `llm` type as an example and write `xinference.llm.llm.py`.
+
+In `llm.py`, create a Xinference LLM class, we name it `XinferenceAILargeLanguageModel` (this can be arbitrary), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
+
+- LLM Invocation
+
+Implement the core method for LLM invocation, supporting both stream and synchronous responses.
+
+```python
+def _invoke(self, model: str, credentials: dict,
+            prompt_messages: list[PromptMessage], model_parameters: dict,
+            tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+            stream: bool = True, user: Optional[str] = None) \
+        -> Union[LLMResult, Generator]:
+    """
+    Invoke large language model
+    
+    :param model: model name
+	:param credentials: model credentials
+	:param prompt_messages: prompt messages
+	:param model_parameters: model parameters
+	:param tools: tools for tool usage
+	:param stop: stop words
+	:param stream: is the response a stream
+	:param user: unique user id
+	:return: full response or stream response chunk generator result
+	"""
+```
+
+When implementing, ensure to use two functions to return data separately for synchronous and stream responses. This is important because Python treats functions containing the `yield` keyword as generator functions, mandating them to return `Generator` types. Here’s an example (note that the example uses simplified parameters; in real implementation, use the parameter list as defined above):
+
+```python
+def _invoke(self, stream: bool, **kwargs) \
+        -> Union[LLMResult, Generator]:
+    if stream:
+          return self._handle_stream_response(**kwargs)
+    return self._handle_sync_response(**kwargs)
+
+def _handle_stream_response(self, **kwargs) -> Generator:
+    for chunk in response:
+          yield chunk
+def _handle_sync_response(self, **kwargs) -> LLMResult:
+    return LLMResult(**response)
+```
+
+- Pre-compute Input Tokens
+
+If the model does not provide an interface for pre-computing tokens, you can return 0 directly.
+
+```python
+def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],tools: Optional[list[PromptMessageTool]] = None) -> int:
+  """
+  Get number of tokens for given prompt messages
+
+  :param model: model name
+  :param credentials: model credentials
+  :param prompt_messages: prompt messages
+  :param tools: tools for tool usage
+  :return: token count
+  """
+```
+
+
+Sometimes, you might not want to return 0 directly. In such cases, you can use `self._get_num_tokens_by_gpt2(text: str)` to get pre-computed tokens. This method is provided by the `AIModel` base class, and it uses GPT2's Tokenizer for calculation. However, it should be noted that this is only a substitute and may not be fully accurate.
+
+- Model Credentials Validation
+
+Similar to vendor credentials validation, this method validates individual model credentials.
+
+```python
+def validate_credentials(self, model: str, credentials: dict) -> None:
+    """
+    Validate model credentials
+    
+    :param model: model name
+	:param credentials: model credentials
+	:return: None
+	"""
+```
+
+- Model Parameter Schema
+
+Unlike custom types, since the YAML file does not define which parameters a model supports, we need to dynamically generate the model parameter schema.
+
+For instance, Xinference supports `max_tokens`, `temperature`, and `top_p` parameters.
+
+However, some vendors may support different parameters for different models. For example, the `OpenLLM` vendor supports `top_k`, but not all models provided by this vendor support `top_k`. Let's say model A supports `top_k` but model B does not. In such cases, we need to dynamically generate the model parameter schema, as illustrated below:
+
+```python
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
+        """
+            used to define customizable model schema
+        """
+        rules = [
+            ParameterRule(
+                name='temperature', type=ParameterType.FLOAT,
+                use_template='temperature',
+                label=I18nObject(
+                    zh_Hans='温度', en_US='Temperature'
+                )
+            ),
+            ParameterRule(
+                name='top_p', type=ParameterType.FLOAT,
+                use_template='top_p',
+                label=I18nObject(
+                    zh_Hans='Top P', en_US='Top P'
+                )
+            ),
+            ParameterRule(
+                name='max_tokens', type=ParameterType.INT,
+                use_template='max_tokens',
+                min=1,
+                default=512,
+                label=I18nObject(
+                    zh_Hans='最大生成长度', en_US='Max Tokens'
+                )
+            )
+        ]
+
+        # if model is A, add top_k to rules
+        if model == 'A':
+            rules.append(
+                ParameterRule(
+                    name='top_k', type=ParameterType.INT,
+                    use_template='top_k',
+                    min=1,
+                    default=50,
+                    label=I18nObject(
+                        zh_Hans='Top K', en_US='Top K'
+                    )
+                )
+            )
+
+        """
+            some NOT IMPORTANT code here
+        """
+
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(
+                en_US=model
+            ),
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_type=model_type,
+            model_properties={ 
+                ModelPropertyKey.MODE:  ModelType.LLM,
+            },
+            parameter_rules=rules
+        )
+
+        return entity
+```
+
+- Exception Error Mapping
+
+When a model invocation error occurs, it should be mapped to the runtime's specified `InvokeError` type, enabling Dify to handle different errors appropriately.
+
+Runtime Errors:
+
+- `InvokeConnectionError` Connection error during invocation
+- `InvokeServerUnavailableError` Service provider unavailable
+- `InvokeRateLimitError` Rate limit reached
+- `InvokeAuthorizationError` Authorization failure
+- `InvokeBadRequestError` Invalid request parameters
+
+```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+```
+
+For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/predefined_model_scale_out.md

@@ -0,0 +1,173 @@
+## Predefined Model Integration
+
+After completing the vendor integration, the next step is to integrate the models from the vendor.
+
+First, we need to determine the type of model to be integrated and create the corresponding model type `module` under the respective vendor's directory.
+
+Currently supported model types are:
+
+- `llm` Text Generation Model
+- `text_embedding` Text Embedding Model
+- `rerank` Rerank Model
+- `speech2text` Speech-to-Text
+- `tts` Text-to-Speech
+- `moderation` Moderation
+
+Continuing with `Anthropic` as an example, `Anthropic` only supports LLM, so create a `module` named `llm` under `model_providers.anthropic`.
+
+For predefined models, we first need to create a YAML file named after the model under the `llm` `module`, such as `claude-2.1.yaml`.
+
+### Prepare Model YAML
+
+```yaml
+model: claude-2.1  # Model identifier
+# Display name of the model, which can be set to en_US English or zh_Hans Chinese. If zh_Hans is not set, it will default to en_US.
+# This can also be omitted, in which case the model identifier will be used as the label
+label:
+  en_US: claude-2.1
+model_type: llm  # Model type, claude-2.1 is an LLM
+features:  # Supported features, agent-thought supports Agent reasoning, vision supports image understanding
+- agent-thought
+model_properties:  # Model properties
+  mode: chat  # LLM mode, complete for text completion models, chat for conversation models
+  context_size: 200000  # Maximum context size
+parameter_rules:  # Parameter rules for the model call; only LLM requires this
+- name: temperature  # Parameter variable name
+  # Five default configuration templates are provided: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
+  # The template variable name can be set directly in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
+  # Additional configuration parameters will override the default configuration if set
+  use_template: temperature
+- name: top_p
+  use_template: top_p
+- name: top_k
+  label:  # Display name of the parameter
+    zh_Hans: 取样数量
+    en_US: Top k
+  type: int  # Parameter type, supports float/int/string/boolean
+  help:  # Help information, describing the parameter's function
+    zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+    en_US: Only sample from the top K options for each subsequent token.
+  required: false  # Whether the parameter is mandatory; can be omitted
+- name: max_tokens_to_sample
+  use_template: max_tokens
+  default: 4096  # Default value of the parameter
+  min: 1  # Minimum value of the parameter, applicable to float/int only
+  max: 4096  # Maximum value of the parameter, applicable to float/int only
+pricing:  # Pricing information
+  input: '8.00'  # Input unit price, i.e., prompt price
+  output: '24.00'  # Output unit price, i.e., response content price
+  unit: '0.000001'  # Price unit, meaning the above prices are per 100K
+  currency: USD  # Price currency
+```
+
+It is recommended to prepare all model configurations before starting the implementation of the model code.
+
+You can also refer to the YAML configuration information under the corresponding model type directories of other vendors in the `model_providers` directory. For the complete YAML rules, refer to: [Schema](schema.md#aimodelentity).
+
+### Implement the Model Call Code
+
+Next, create a Python file named `llm.py` under the `llm` `module` to write the implementation code.
+
+Create an Anthropic LLM class named `AnthropicLargeLanguageModel` (or any other name), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
+
+- LLM Call
+
+Implement the core method for calling the LLM, supporting both streaming and synchronous responses.
+
+```python
+  def _invoke(self, model: str, credentials: dict,
+              prompt_messages: list[PromptMessage], model_parameters: dict,
+              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
+              stream: bool = True, user: Optional[str] = None) \
+          -> Union[LLMResult, Generator]:
+      """
+      Invoke large language model
+  
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param model_parameters: model parameters
+      :param tools: tools for tool calling
+      :param stop: stop words
+      :param stream: is stream response
+      :param user: unique user id
+      :return: full response or stream response chunk generator result
+      """
+```
+
+Ensure to use two functions for returning data, one for synchronous returns and the other for streaming returns, because Python identifies functions containing the `yield` keyword as generator functions, fixing the return type to `Generator`. Thus, synchronous and streaming returns need to be implemented separately, as shown below (note that the example uses simplified parameters, for actual implementation follow the above parameter list):
+
+```python
+  def _invoke(self, stream: bool, **kwargs) \
+          -> Union[LLMResult, Generator]:
+      if stream:
+            return self._handle_stream_response(**kwargs)
+      return self._handle_sync_response(**kwargs)
+
+  def _handle_stream_response(self, **kwargs) -> Generator:
+      for chunk in response:
+            yield chunk
+  def _handle_sync_response(self, **kwargs) -> LLMResult:
+      return LLMResult(**response)
+```
+
+- Pre-compute Input Tokens
+
+If the model does not provide an interface to precompute tokens, return 0 directly.
+
+```python
+  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
+                     tools: Optional[list[PromptMessageTool]] = None) -> int:
+      """
+      Get number of tokens for given prompt messages
+
+      :param model: model name
+      :param credentials: model credentials
+      :param prompt_messages: prompt messages
+      :param tools: tools for tool calling
+      :return:
+      """
+```
+
+- Validate Model Credentials
+
+Similar to vendor credential validation, but specific to a single model.
+
+```python
+  def validate_credentials(self, model: str, credentials: dict) -> None:
+      """
+      Validate model credentials
+  
+      :param model: model name
+      :param credentials: model credentials
+      :return:
+      """
+```
+
+- Map Invoke Errors
+
+When a model call fails, map it to a specific `InvokeError` type as required by Runtime, allowing Dify to handle different errors accordingly.
+
+Runtime Errors:
+
+- `InvokeConnectionError` Connection error
+
+- `InvokeServerUnavailableError` Service provider unavailable
+- `InvokeRateLimitError` Rate limit reached
+- `InvokeAuthorizationError` Authorization failed
+- `InvokeBadRequestError` Parameter error
+
+```python
+  @property
+  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+      """
+      Map model invoke error to unified error
+      The key is the error type thrown to the caller
+      The value is the error type thrown by the model,
+      which needs to be converted into a unified error type for the caller.
+  
+      :return: Invoke error mapping
+      """
+```
+
+For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/provider_scale_out.md

@@ -58,7 +58,7 @@ provider_credential_schema:  # Provider credential rules, as Anthropic only supp
       en_US: Enter your API URL
 ```
 
-You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#Provider).
+You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#provider).
 
 ### Implementing Provider Code
 

api/core/model_runtime/docs/zh_Hans/provider_scale_out.md

@@ -117,7 +117,7 @@ model_credential_schema:
       en_US: Enter your API Base
 ```
 
-也可以参考  `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#Provider)。
+也可以参考  `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。
 
 #### 实现供应商代码
 

api/core/model_runtime/model_providers/_position.yaml

@@ -40,3 +40,4 @@
 - fireworks
 - mixedbread
 - nomic
+- voyage

api/core/model_runtime/model_providers/bedrock/llm/_position.yaml

@@ -6,6 +6,8 @@
 - anthropic.claude-v2:1
 - anthropic.claude-3-sonnet-v1:0
 - anthropic.claude-3-haiku-v1:0
+- ai21.jamba-1-5-large-v1:0
+- ai21.jamba-1-5-mini-v1:0
 - cohere.command-light-text-v14
 - cohere.command-text-v14
 - cohere.command-r-plus-v1.0
@@ -15,6 +17,10 @@
 - meta.llama3-1-405b-instruct-v1:0
 - meta.llama3-8b-instruct-v1:0
 - meta.llama3-70b-instruct-v1:0
+- us.meta.llama3-2-1b-instruct-v1:0
+- us.meta.llama3-2-3b-instruct-v1:0
+- us.meta.llama3-2-11b-instruct-v1:0
+- us.meta.llama3-2-90b-instruct-v1:0
 - meta.llama2-13b-chat-v1
 - meta.llama2-70b-chat-v1
 - mistral.mistral-large-2407-v1:0

api/core/model_runtime/model_providers/bedrock/llm/ai21.jamba-1-5-large-v1.0.yaml

@@ -0,0 +1,26 @@
+model: ai21.jamba-1-5-large-v1:0
+label:
+  en_US: Jamba 1.5 Large
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 256000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 1
+    min: 0.0
+    max: 2.0
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+pricing:
+  input: '0.002'
+  output: '0.008'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/ai21.jamba-1-5-mini-v1.0.yaml

@@ -0,0 +1,26 @@
+model: ai21.jamba-1-5-mini-v1:0
+label:
+  en_US: Jamba 1.5 Mini
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 256000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 1
+    min: 0.0
+    max: 2.0
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+pricing:
+  input: '0.0002'
+  output: '0.0004'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/llm.py

@@ -63,6 +63,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         {"prefix": "us.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "eu.anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "anthropic.claude-3", "support_system_prompts": True, "support_tool_use": True},
+        {"prefix": "us.meta.llama3-2", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "meta.llama", "support_system_prompts": True, "support_tool_use": False},
         {"prefix": "mistral.mistral-7b-instruct", "support_system_prompts": False, "support_tool_use": False},
         {"prefix": "mistral.mixtral-8x7b-instruct", "support_system_prompts": False, "support_tool_use": False},
@@ -70,6 +71,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         {"prefix": "mistral.mistral-small", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "cohere.command-r", "support_system_prompts": True, "support_tool_use": True},
         {"prefix": "amazon.titan", "support_system_prompts": False, "support_tool_use": False},
+        {"prefix": "ai21.jamba-1-5", "support_system_prompts": True, "support_tool_use": False},
     ]
 
     @staticmethod

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-11b-instruct-v1.0.yaml

@@ -0,0 +1,29 @@
+model: us.meta.llama3-2-11b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 11B Instruct
+model_type: llm
+features:
+  - vision
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00035'
+  output: '0.00035'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-1b-instruct-v1.0.yaml

@@ -0,0 +1,26 @@
+model: us.meta.llama3-2-1b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 1B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0001'
+  output: '0.0001'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-3b-instruct-v1.0.yaml

@@ -0,0 +1,26 @@
+model: us.meta.llama3-2-3b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 3B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00015'
+  output: '0.00015'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/llm/us.meta.llama3-2-90b-instruct-v1.0.yaml

@@ -0,0 +1,31 @@
+model: us.meta.llama3-2-90b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 90B Instruct
+model_type: llm
+features:
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+    min: 0
+    max: 1
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.002'
+  output: '0.002'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/perfxcloud/llm/_position.yaml

@@ -1,24 +1,23 @@
 - Qwen2.5-72B-Instruct
 - Qwen2.5-7B-Instruct
+- Qwen2-72B-Instruct
+- Qwen2-72B-Instruct-AWQ-int4
+- Qwen2-72B-Instruct-GPTQ-Int4
+- Qwen2-7B-Instruct
+- Qwen2-7B
+- Qwen1.5-110B-Chat-GPTQ-Int4
+- Qwen1.5-72B-Chat-GPTQ-Int4
+- Qwen1.5-7B
+- Qwen-14B-Chat-Int4
 - Yi-Coder-1.5B-Chat
 - Yi-Coder-9B-Chat
-- Qwen2-72B-Instruct-AWQ-int4
 - Yi-1_5-9B-Chat-16K
-- Qwen2-7B-Instruct
 - Reflection-Llama-3.1-70B
-- Qwen2-72B-Instruct
 - Meta-Llama-3.1-8B-Instruct
-
 - Meta-Llama-3.1-405B-Instruct-AWQ-INT4
 - Meta-Llama-3-70B-Instruct-GPTQ-Int4
-- chatglm3-6b
 - Meta-Llama-3-8B-Instruct
 - Llama3-Chinese_v2
 - deepseek-v2-lite-chat
-- Qwen2-72B-Instruct-GPTQ-Int4
-- Qwen2-7B
-- Qwen-14B-Chat-Int4
-- Qwen1.5-72B-Chat-GPTQ-Int4
-- Qwen1.5-7B
-- Qwen1.5-110B-Chat-GPTQ-Int4
 - deepseek-v2-chat
+- chatglm3-6b

api/core/model_runtime/model_providers/perfxcloud/text_embedding/_position.yaml

@@ -0,0 +1,4 @@
+- gte-Qwen2-7B-instruct
+- BAAI/bge-large-en-v1.5
+- BAAI/bge-large-zh-v1.5
+- BAAI/bge-m3

api/core/model_runtime/model_providers/perfxcloud/text_embedding/gte-Qwen2-7B-instruct.yaml

@@ -2,3 +2,4 @@ model: gte-Qwen2-7B-instruct
 model_type: text-embedding
 model_properties:
   context_size: 2048
+deprecated: true

api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml

@@ -1,18 +1,17 @@
 - Qwen/Qwen2.5-72B-Instruct
-- Qwen/Qwen2.5-Math-72B-Instruct
 - Qwen/Qwen2.5-32B-Instruct
 - Qwen/Qwen2.5-14B-Instruct
 - Qwen/Qwen2.5-7B-Instruct
 - Qwen/Qwen2.5-Coder-7B-Instruct
-- deepseek-ai/DeepSeek-V2.5
+- Qwen/Qwen2.5-Math-72B-Instruct
 - Qwen/Qwen2-72B-Instruct
 - Qwen/Qwen2-57B-A14B-Instruct
 - Qwen/Qwen2-7B-Instruct
 - Qwen/Qwen2-1.5B-Instruct
+- deepseek-ai/DeepSeek-V2.5
 - deepseek-ai/DeepSeek-V2-Chat
 - deepseek-ai/DeepSeek-Coder-V2-Instruct
 - THUDM/glm-4-9b-chat
-- THUDM/chatglm3-6b
 - 01-ai/Yi-1.5-34B-Chat-16K
 - 01-ai/Yi-1.5-9B-Chat-16K
 - 01-ai/Yi-1.5-6B-Chat
@@ -26,13 +25,4 @@
 - google/gemma-2-27b-it
 - google/gemma-2-9b-it
 - mistralai/Mistral-7B-Instruct-v0.2
-- Pro/Qwen/Qwen2-7B-Instruct
-- Pro/Qwen/Qwen2-1.5B-Instruct
-- Pro/THUDM/glm-4-9b-chat
-- Pro/THUDM/chatglm3-6b
-- Pro/01-ai/Yi-1.5-9B-Chat-16K
-- Pro/01-ai/Yi-1.5-6B-Chat
-- Pro/internlm/internlm2_5-7b-chat
-- Pro/meta-llama/Meta-Llama-3.1-8B-Instruct
-- Pro/meta-llama/Meta-Llama-3-8B-Instruct
-- Pro/google/gemma-2-9b-it
+- mistralai/Mixtral-8x7B-Instruct-v0.1

api/core/model_runtime/model_providers/siliconflow/llm/internlm2_5-20b-chat.yaml

@@ -0,0 +1,30 @@
+model: internlm/internlm2_5-20b-chat
+label:
+  en_US: internlm/internlm2_5-20b-chat
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32768
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '1'
+  output: '1'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-coder-7b-instruct.yaml

@@ -0,0 +1,74 @@
+model: Qwen/Qwen2.5-Coder-7B-Instruct
+label:
+  en_US: Qwen/Qwen2.5-Coder-7B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    type: float
+    default: 0.3
+    min: 0.0
+    max: 2.0
+    help:
+      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
+      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 8192
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
+      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
+  - name: top_p
+    use_template: top_p
+    type: float
+    default: 0.8
+    min: 0.1
+    max: 0.9
+    help:
+      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
+      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
+  - name: top_k
+    type: int
+    min: 0
+    max: 99
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    help:
+      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
+      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
+  - name: seed
+    required: false
+    type: int
+    default: 1234
+    label:
+      zh_Hans: 随机种子
+      en_US: Random seed
+    help:
+      zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
+      en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
+  - name: repetition_penalty
+    required: false
+    type: float
+    default: 1.1
+    label:
+      zh_Hans: 重复惩罚
+      en_US: Repetition penalty
+    help:
+      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
+      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0'
+  output: '0'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/siliconflow/llm/qwen2.5-math-72b-instruct.yaml

@@ -0,0 +1,74 @@
+model: Qwen/Qwen2.5-Math-72B-Instruct
+label:
+  en_US: Qwen/Qwen2.5-Math-72B-Instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    type: float
+    default: 0.3
+    min: 0.0
+    max: 2.0
+    help:
+      zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
+      en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 2000
+    min: 1
+    max: 2000
+    help:
+      zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
+      en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
+  - name: top_p
+    use_template: top_p
+    type: float
+    default: 0.8
+    min: 0.1
+    max: 0.9
+    help:
+      zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
+      en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
+  - name: top_k
+    type: int
+    min: 0
+    max: 99
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    help:
+      zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
+      en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
+  - name: seed
+    required: false
+    type: int
+    default: 1234
+    label:
+      zh_Hans: 随机种子
+      en_US: Random seed
+    help:
+      zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
+      en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
+  - name: repetition_penalty
+    required: false
+    type: float
+    default: 1.1
+    label:
+      zh_Hans: 重复惩罚
+      en_US: Repetition penalty
+    help:
+      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
+      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '4.13'
+  output: '4.13'
+  unit: '0.000001'
+  currency: RMB

api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-coder-7b-instruct.yaml

@@ -1,7 +1,7 @@
 # for more details, please refer to https://help.aliyun.com/zh/model-studio/getting-started/models
-model: qwen2.5-7b-instruct
+model: qwen2.5-coder-7b-instruct
 label:
-  en_US: qwen2.5-7b-instruct
+  en_US: qwen2.5-coder-7b-instruct
 model_type: llm
 features:
   - agent-thought

api/core/model_runtime/model_providers/voyage/_assets/icon_l_en.svg

@@ -0,0 +1,21 @@
+<svg version="1.0" xmlns="http://www.w3.org/2000/svg" width="100.000000pt" height="19.000000pt" viewBox="0 0 300.000000 57.000000" preserveAspectRatio="xMidYMid meet"><g transform="translate(0.000000,57.000000) scale(0.100000,-0.100000)" fill="#000000" stroke="none"><path d="M2505 368 c-38 -84 -86 -188 -106 -230 l-38 -78 27 0 c24 0 30 7 55
+    75 l28 75 100 0 100 0 25 -55 c13 -31 24 -64 24 -75 0 -17 7 -20 44 -20 l43 0
+    -37 73 c-20 39 -68 143 -106 229 -38 87 -74 158 -80 158 -5 0 -41 -69 -79
+    -152z m110 -30 c22 -51 41 -95 42 -98 2 -3 -36 -6 -83 -7 -76 -1 -85 0 -81 15
+    12 40 72 182 77 182 3 0 24 -41 45 -92z"/><path d="M63 493 c19 -61 197 -438 209 -440 10 -2 147 282 216 449 2 4 -10 8
+    -27 8 -23 0 -31 -5 -31 -17 0 -16 -142 -365 -146 -360 -8 11 -144 329 -149
+    350 -6 23 -12 27 -42 27 -29 0 -34 -3 -30 -17z"/><path d="M2855 285 l0 -225 30 0 30 0 0 225 0 225 -30 0 -30 0 0 -225z"/><path d="M588 380 c-55 -30 -82 -74 -86 -145 -3 -50 0 -66 20 -95 39 -58 82
+    -80 153 -80 68 0 110 21 149 73 32 43 30 150 -3 196 -47 66 -158 90 -233 51z
+    m133 -16 c59 -30 89 -156 54 -224 -45 -87 -162 -78 -201 16 -18 44 -18 128 1
+    164 28 55 90 73 146 44z"/><path d="M935 303 l76 -98 -7 -72 -6 -73 33 0 34 0 -3 78 -4 77 71 93 c65 85
+    68 92 46 92 -15 0 -29 -9 -36 -22 -18 -33 -90 -128 -98 -128 -6 1 -67 85 -88
+    122 -8 15 -24 23 -53 25 l-41 4 76 -98z"/><path d="M1257 230 c-82 -169 -83 -170 -57 -170 17 0 27 6 27 15 0 8 7 31 17
+    52 l17 38 79 0 78 1 16 -34 c9 -18 16 -42 16 -52 0 -17 7 -20 41 -20 22 0 39
+    3 37 8 -2 4 -39 80 -83 170 -43 89 -84 162 -92 162 -7 0 -50 -76 -96 -170z
+    m90 -38 c-33 -2 -61 -1 -63 1 -2 2 10 34 26 71 l31 68 33 -68 33 -69 -60 -3z"/><path d="M1665 386 c-37 -16 -84 -63 -97 -96 -13 -35 -12 -104 2 -132 49 -94
+    182 -134 280 -83 24 12 29 22 32 64 3 49 3 49 -30 53 l-33 4 3 -45 c4 -61 -5
+    -71 -60 -71 -93 0 -142 57 -142 164 0 44 5 60 25 85 47 55 136 65 184 20 30
+    -28 35 -20 11 19 -19 31 -22 32 -82 32 -35 -1 -76 -7 -93 -14z"/><path d="M1955 230 l0 -170 91 0 c76 0 93 3 98 16 4 9 5 18 4 20 -2 1 -31 -1
+    -66 -5 -34 -4 -64 -5 -67 -3 -3 3 -5 36 -5 73 l0 68 55 -6 c49 -5 55 -4 55 13
+    0 17 -6 19 -55 16 l-55 -4 0 61 0 61 64 0 c48 0 65 4 70 15 4 13 -10 15 -92
+    15 l-97 0 0 -170z"/></g></svg>

api/core/model_runtime/model_providers/voyage/_assets/icon_s_en.svg

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="64px" height="64px" viewBox="0 0 64 64" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+    <title>voyage</title>
+    <g id="voyage" stroke="none" stroke-width="1" fill="none" fill-rule="evenodd">
+        <rect id="矩形" fill="#333333" x="0" y="0" width="64" height="64" rx="12"></rect>
+        <path d="M12.1128004,51.4376727 C13.8950799,45.8316747 30.5922254,11.1847688 31.7178757,11.0009656 C32.6559176,10.8171624 45.5070913,36.9172188 51.9795803,52.2647871 C52.1671887,52.6323936 51.0415384,53 49.4468672,53 C47.2893709,53 46.5389374,52.540492 46.5389374,51.4376727 C46.5389374,49.967247 33.2187427,17.8935861 32.8435259,18.3530942 C32.0930924,19.3640118 19.3357228,48.5887229 18.8667019,50.5186566 C18.3038768,52.6323936 17.7410516,53 14.926926,53 C12.2066045,53 11.7375836,52.7242952 12.1128004,51.4376727 Z" id="路径" fill="#FFFFFF" transform="translate(32, 32) scale(1, -1) translate(-32, -32)"></path>
+    </g>
+</svg>

api/core/model_runtime/model_providers/voyage/rerank/rerank-1.yaml

@@ -0,0 +1,4 @@
+model: rerank-1
+model_type: rerank
+model_properties:
+  context_size: 8000

api/core/model_runtime/model_providers/voyage/rerank/rerank-lite-1.yaml

@@ -0,0 +1,4 @@
+model: rerank-lite-1
+model_type: rerank
+model_properties:
+  context_size: 4000

api/core/model_runtime/model_providers/voyage/rerank/rerank.py

@@ -0,0 +1,123 @@
+from typing import Optional
+
+import httpx
+
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType
+from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
+from core.model_runtime.errors.invoke import (
+    InvokeAuthorizationError,
+    InvokeBadRequestError,
+    InvokeConnectionError,
+    InvokeError,
+    InvokeRateLimitError,
+    InvokeServerUnavailableError,
+)
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.rerank_model import RerankModel
+
+
+class VoyageRerankModel(RerankModel):
+    """
+    Model class for Voyage rerank model.
+    """
+
+    def _invoke(
+        self,
+        model: str,
+        credentials: dict,
+        query: str,
+        docs: list[str],
+        score_threshold: Optional[float] = None,
+        top_n: Optional[int] = None,
+        user: Optional[str] = None,
+    ) -> RerankResult:
+        """
+        Invoke rerank model
+        :param model: model name
+        :param credentials: model credentials
+        :param query: search query
+        :param docs: docs for reranking
+        :param score_threshold: score threshold
+        :param top_n: top n documents to return
+        :param user: unique user id
+        :return: rerank result
+        """
+        if len(docs) == 0:
+            return RerankResult(model=model, docs=[])
+
+        base_url = credentials.get("base_url", "https://api.voyageai.com/v1")
+        base_url = base_url.removesuffix("/")
+
+        try:
+            response = httpx.post(
+                base_url + "/rerank",
+                json={"model": model, "query": query, "documents": docs, "top_k": top_n, "return_documents": True},
+                headers={"Authorization": f"Bearer {credentials.get('api_key')}", "Content-Type": "application/json"},
+            )
+            response.raise_for_status()
+            results = response.json()
+
+            rerank_documents = []
+            for result in results["data"]:
+                rerank_document = RerankDocument(
+                    index=result["index"],
+                    text=result["document"],
+                    score=result["relevance_score"],
+                )
+                if score_threshold is None or result["relevance_score"] >= score_threshold:
+                    rerank_documents.append(rerank_document)
+
+            return RerankResult(model=model, docs=rerank_documents)
+        except httpx.HTTPStatusError as e:
+            raise InvokeServerUnavailableError(str(e))
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        """
+        Validate model credentials
+        :param model: model name
+        :param credentials: model credentials
+        :return:
+        """
+        try:
+            self._invoke(
+                model=model,
+                credentials=credentials,
+                query="What is the capital of the United States?",
+                docs=[
+                    "Carson City is the capital city of the American state of Nevada. At the 2010 United States "
+                    "Census, Carson City had a population of 55,274.",
+                    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
+                    "are a political division controlled by the United States. Its capital is Saipan.",
+                ],
+                score_threshold=0.8,
+            )
+        except Exception as ex:
+            raise CredentialsValidateFailedError(str(ex))
+
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        """
+        Map model invoke error to unified error
+        """
+        return {
+            InvokeConnectionError: [httpx.ConnectError],
+            InvokeServerUnavailableError: [httpx.RemoteProtocolError],
+            InvokeRateLimitError: [],
+            InvokeAuthorizationError: [httpx.HTTPStatusError],
+            InvokeBadRequestError: [httpx.RequestError],
+        }
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
+        """
+        generate custom model entities from credentials
+        """
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model),
+            model_type=ModelType.RERANK,
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", "8000"))},
+        )
+
+        return entity

api/core/model_runtime/model_providers/voyage/text_embedding/text_embedding.py

@@ -0,0 +1,172 @@
+import time
+from json import JSONDecodeError, dumps
+from typing import Optional
+
+import requests
+
+from core.embedding.embedding_constant import EmbeddingInputType
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelPropertyKey, ModelType, PriceType
+from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
+from core.model_runtime.errors.invoke import (
+    InvokeAuthorizationError,
+    InvokeBadRequestError,
+    InvokeConnectionError,
+    InvokeError,
+    InvokeRateLimitError,
+    InvokeServerUnavailableError,
+)
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
+
+
+class VoyageTextEmbeddingModel(TextEmbeddingModel):
+    """
+    Model class for Voyage text embedding model.
+    """
+
+    api_base: str = "https://api.voyageai.com/v1"
+
+    def _invoke(
+        self,
+        model: str,
+        credentials: dict,
+        texts: list[str],
+        user: Optional[str] = None,
+        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+    ) -> TextEmbeddingResult:
+        """
+        Invoke text embedding model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param texts: texts to embed
+        :param user: unique user id
+        :param input_type: input type
+        :return: embeddings result
+        """
+        api_key = credentials["api_key"]
+        if not api_key:
+            raise CredentialsValidateFailedError("api_key is required")
+
+        base_url = credentials.get("base_url", self.api_base)
+        base_url = base_url.removesuffix("/")
+
+        url = base_url + "/embeddings"
+        headers = {"Authorization": "Bearer " + api_key, "Content-Type": "application/json"}
+        voyage_input_type = "null"
+        if input_type is not None:
+            voyage_input_type = input_type.value
+        data = {"model": model, "input": texts, "input_type": voyage_input_type}
+
+        try:
+            response = requests.post(url, headers=headers, data=dumps(data))
+        except Exception as e:
+            raise InvokeConnectionError(str(e))
+
+        if response.status_code != 200:
+            try:
+                resp = response.json()
+                msg = resp["detail"]
+                if response.status_code == 401:
+                    raise InvokeAuthorizationError(msg)
+                elif response.status_code == 429:
+                    raise InvokeRateLimitError(msg)
+                elif response.status_code == 500:
+                    raise InvokeServerUnavailableError(msg)
+                else:
+                    raise InvokeBadRequestError(msg)
+            except JSONDecodeError as e:
+                raise InvokeServerUnavailableError(
+                    f"Failed to convert response to json: {e} with text: {response.text}"
+                )
+
+        try:
+            resp = response.json()
+            embeddings = resp["data"]
+            usage = resp["usage"]
+        except Exception as e:
+            raise InvokeServerUnavailableError(f"Failed to convert response to json: {e} with text: {response.text}")
+
+        usage = self._calc_response_usage(model=model, credentials=credentials, tokens=usage["total_tokens"])
+
+        result = TextEmbeddingResult(
+            model=model, embeddings=[[float(data) for data in x["embedding"]] for x in embeddings], usage=usage
+        )
+
+        return result
+
+    def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
+        """
+        Get number of tokens for given prompt messages
+
+        :param model: model name
+        :param credentials: model credentials
+        :param texts: texts to embed
+        :return:
+        """
+        return sum(self._get_num_tokens_by_gpt2(text) for text in texts)
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        """
+        Validate model credentials
+
+        :param model: model name
+        :param credentials: model credentials
+        :return:
+        """
+        try:
+            self._invoke(model=model, credentials=credentials, texts=["ping"])
+        except Exception as e:
+            raise CredentialsValidateFailedError(f"Credentials validation failed: {e}")
+
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        return {
+            InvokeConnectionError: [InvokeConnectionError],
+            InvokeServerUnavailableError: [InvokeServerUnavailableError],
+            InvokeRateLimitError: [InvokeRateLimitError],
+            InvokeAuthorizationError: [InvokeAuthorizationError],
+            InvokeBadRequestError: [KeyError, InvokeBadRequestError],
+        }
+
+    def _calc_response_usage(self, model: str, credentials: dict, tokens: int) -> EmbeddingUsage:
+        """
+        Calculate response usage
+
+        :param model: model name
+        :param credentials: model credentials
+        :param tokens: input tokens
+        :return: usage
+        """
+        # get input price info
+        input_price_info = self.get_price(
+            model=model, credentials=credentials, price_type=PriceType.INPUT, tokens=tokens
+        )
+
+        # transform usage
+        usage = EmbeddingUsage(
+            tokens=tokens,
+            total_tokens=tokens,
+            unit_price=input_price_info.unit_price,
+            price_unit=input_price_info.unit,
+            total_price=input_price_info.total_amount,
+            currency=input_price_info.currency,
+            latency=time.perf_counter() - self.started_at,
+        )
+
+        return usage
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
+        """
+        generate custom model entities from credentials
+        """
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model),
+            model_type=ModelType.TEXT_EMBEDDING,
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
+        )
+
+        return entity

api/core/model_runtime/model_providers/voyage/text_embedding/voyage-3-lite.yaml

@@ -0,0 +1,8 @@
+model: voyage-3-lite
+model_type: text-embedding
+model_properties:
+  context_size: 32000
+pricing:
+  input: '0.00002'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/voyage/text_embedding/voyage-3.yaml

@@ -0,0 +1,8 @@
+model: voyage-3
+model_type: text-embedding
+model_properties:
+  context_size: 32000
+pricing:
+  input: '0.00006'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/voyage/voyage.py

@@ -0,0 +1,28 @@
+import logging
+
+from core.model_runtime.entities.model_entities import ModelType
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.model_provider import ModelProvider
+
+logger = logging.getLogger(__name__)
+
+
+class VoyageProvider(ModelProvider):
+    def validate_provider_credentials(self, credentials: dict) -> None:
+        """
+        Validate provider credentials
+        if validate failed, raise exception
+
+        :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
+        """
+        try:
+            model_instance = self.get_model_instance(ModelType.TEXT_EMBEDDING)
+
+            # Use `voyage-3` model for validate,
+            # no matter what model you pass in, text completion model or chat model
+            model_instance.validate_credentials(model="voyage-3", credentials=credentials)
+        except CredentialsValidateFailedError as ex:
+            raise ex
+        except Exception as ex:
+            logger.exception(f"{self.get_provider_schema().provider} credentials validate failed")
+            raise ex

api/core/model_runtime/model_providers/voyage/voyage.yaml

@@ -0,0 +1,31 @@
+provider: voyage
+label:
+  en_US: Voyage
+description:
+  en_US: Embedding and Rerank Model Supported
+icon_small:
+  en_US: icon_s_en.svg
+icon_large:
+  en_US: icon_l_en.svg
+background: "#EFFDFD"
+help:
+  title:
+    en_US: Get your API key from Voyage AI
+    zh_Hans: 从 Voyage 获取 API Key
+  url:
+    en_US: https://dash.voyageai.com/
+supported_model_types:
+  - text-embedding
+  - rerank
+configurate_methods:
+  - predefined-model
+provider_credential_schema:
+  credential_form_schemas:
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key

api/core/model_runtime/model_providers/zhipuai/zhipuai_sdk/core/_base_models.py

@@ -48,7 +48,7 @@ from ._utils import (
 )
 
 if TYPE_CHECKING:
-    from pydantic_core.core_schema import LiteralSchema, ModelField, ModelFieldsSchema
+    from pydantic_core.core_schema import ModelField
 
 __all__ = ["BaseModel", "GenericModel"]
 _BaseModelT = TypeVar("_BaseModelT", bound="BaseModel")

api/core/model_runtime/model_providers/zhipuai/zhipuai_sdk/core/_utils/_utils.py

@@ -248,7 +248,7 @@ def required_args(*variants: Sequence[str]) -> Callable[[CallableT], CallableT]:
         @functools.wraps(func)
         def wrapper(*args: object, **kwargs: object) -> object:
             given_params: set[str] = set()
-            for i, _ in enumerate(args):
+            for i in range(len(args)):
                 try:
                     given_params.add(positional[i])
                 except IndexError:

api/core/rag/datasource/keyword/jieba/jieba.py

@@ -45,7 +45,7 @@ class Jieba(BaseKeyword):
             keyword_table_handler = JiebaKeywordTableHandler()
 
             keyword_table = self._get_dataset_keyword_table()
-            keywords_list = kwargs.get("keywords_list", None)
+            keywords_list = kwargs.get("keywords_list")
             for i in range(len(texts)):
                 text = texts[i]
                 if keywords_list:

api/core/rag/datasource/vdb/tencent/tencent_vector.py

@@ -56,7 +56,7 @@ class TencentVector(BaseVector):
             return self._client.create_database(database_name=self._client_config.database)
 
     def get_type(self) -> str:
-        return "tencent"
+        return VectorType.TENCENT
 
     def to_index_struct(self) -> dict:
         return {"type": self.get_type(), "vector_store": {"class_prefix": self._collection_name}}

api/events/event_handlers/create_document_index.py

@@ -14,7 +14,7 @@ from models.dataset import Document
 @document_index_created.connect
 def handle(sender, **kwargs):
     dataset_id = sender
-    document_ids = kwargs.get("document_ids", None)
+    document_ids = kwargs.get("document_ids")
     documents = []
     start_at = time.perf_counter()
     for document_id in document_ids:

api/libs/helper.py

@@ -189,23 +189,39 @@ def compact_generate_response(response: Union[dict, RateLimitGenerator]) -> Resp
 
 class TokenManager:
     @classmethod
-    def generate_token(cls, account: Account, token_type: str, additional_data: dict = None) -> str:
-        old_token = cls._get_current_token_for_account(account.id, token_type)
-        if old_token:
-            if isinstance(old_token, bytes):
-                old_token = old_token.decode("utf-8")
-            cls.revoke_token(old_token, token_type)
+    def generate_token(
+        cls,
+        token_type: str,
+        account: Optional[Account] = None,
+        email: Optional[str] = None,
+        additional_data: dict = None,
+    ) -> str:
+        if account is None and email is None:
+            raise ValueError("Account or email must be provided")
+
+        account_id = account.id if account else None
+        account_email = account.email if account else email
+
+        if account_id:
+            old_token = cls._get_current_token_for_account(account_id, token_type)
+            if old_token:
+                if isinstance(old_token, bytes):
+                    old_token = old_token.decode("utf-8")
+                cls.revoke_token(old_token, token_type)
 
         token = str(uuid.uuid4())
-        token_data = {"account_id": account.id, "email": account.email, "token_type": token_type}
+        token_data = {"account_id": account_id, "email": account_email, "token_type": token_type}
         if additional_data:
             token_data.update(additional_data)
 
         expiry_hours = current_app.config[f"{token_type.upper()}_TOKEN_EXPIRY_HOURS"]
         token_key = cls._get_token_key(token, token_type)
-        redis_client.setex(token_key, expiry_hours * 60 * 60, json.dumps(token_data))
+        expiry_time = int(expiry_hours * 60 * 60)
+        redis_client.setex(token_key, expiry_time, json.dumps(token_data))
+
+        if account_id:
+            cls._set_current_token_for_account(account.id, token, token_type, expiry_hours)
 
-        cls._set_current_token_for_account(account.id, token, token_type, expiry_hours)
         return token
 
     @classmethod
@@ -234,9 +250,12 @@ class TokenManager:
         return current_token
 
     @classmethod
-    def _set_current_token_for_account(cls, account_id: str, token: str, token_type: str, expiry_hours: int):
+    def _set_current_token_for_account(
+        cls, account_id: str, token: str, token_type: str, expiry_hours: Union[int, float]
+    ):
         key = cls._get_account_token_key(account_id, token_type)
-        redis_client.setex(key, expiry_hours * 60 * 60, token)
+        expiry_time = int(expiry_hours * 60 * 60)
+        redis_client.setex(key, expiry_time, token)
 
     @classmethod
     def _get_account_token_key(cls, account_id: str, token_type: str) -> str:

api/libs/oauth.py

@@ -1,5 +1,6 @@
 import urllib.parse
 from dataclasses import dataclass
+from typing import Optional
 
 import requests
 
@@ -40,12 +41,14 @@ class GitHubOAuth(OAuth):
     _USER_INFO_URL = "https://api.github.com/user"
     _EMAIL_INFO_URL = "https://api.github.com/user/emails"
 
-    def get_authorization_url(self):
+    def get_authorization_url(self, invite_token: Optional[str] = None):
         params = {
             "client_id": self.client_id,
             "redirect_uri": self.redirect_uri,
             "scope": "user:email",  # Request only basic user information
         }
+        if invite_token:
+            params["state"] = invite_token
         return f"{self._AUTH_URL}?{urllib.parse.urlencode(params)}"
 
     def get_access_token(self, code: str):
@@ -90,13 +93,15 @@ class GoogleOAuth(OAuth):
     _TOKEN_URL = "https://oauth2.googleapis.com/token"
     _USER_INFO_URL = "https://www.googleapis.com/oauth2/v3/userinfo"
 
-    def get_authorization_url(self):
+    def get_authorization_url(self, invite_token: Optional[str] = None):
         params = {
             "client_id": self.client_id,
             "response_type": "code",
             "redirect_uri": self.redirect_uri,
             "scope": "openid email",
         }
+        if invite_token:
+            params["state"] = invite_token
         return f"{self._AUTH_URL}?{urllib.parse.urlencode(params)}"
 
     def get_access_token(self, code: str):

api/libs/password.py

@@ -13,7 +13,7 @@ def valid_password(password):
     if re.match(pattern, password) is not None:
         return password
 
-    raise ValueError("Not a valid password.")
+    raise ValueError("Password must contain letters and numbers, and the length must be greater than 8.")
 
 
 def hash_password(password_str, salt_byte):

api/poetry.lock

@@ -8074,29 +8074,29 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "ruff"
-version = "0.6.5"
+version = "0.6.8"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.6.5-py3-none-linux_armv6l.whl", hash = "sha256:7e4e308f16e07c95fc7753fc1aaac690a323b2bb9f4ec5e844a97bb7fbebd748"},
-    {file = "ruff-0.6.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:932cd69eefe4daf8c7d92bd6689f7e8182571cb934ea720af218929da7bd7d69"},
-    {file = "ruff-0.6.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:3a8d42d11fff8d3143ff4da41742a98f8f233bf8890e9fe23077826818f8d680"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a50af6e828ee692fb10ff2dfe53f05caecf077f4210fae9677e06a808275754f"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:794ada3400a0d0b89e3015f1a7e01f4c97320ac665b7bc3ade24b50b54cb2972"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:381413ec47f71ce1d1c614f7779d88886f406f1fd53d289c77e4e533dc6ea200"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:52e75a82bbc9b42e63c08d22ad0ac525117e72aee9729a069d7c4f235fc4d276"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:09c72a833fd3551135ceddcba5ebdb68ff89225d30758027280968c9acdc7810"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:800c50371bdcb99b3c1551d5691e14d16d6f07063a518770254227f7f6e8c178"},
-    {file = "ruff-0.6.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e25ddd9cd63ba1f3bd51c1f09903904a6adf8429df34f17d728a8fa11174253"},
-    {file = "ruff-0.6.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:7291e64d7129f24d1b0c947ec3ec4c0076e958d1475c61202497c6aced35dd19"},
-    {file = "ruff-0.6.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:9ad7dfbd138d09d9a7e6931e6a7e797651ce29becd688be8a0d4d5f8177b4b0c"},
-    {file = "ruff-0.6.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:005256d977021790cc52aa23d78f06bb5090dc0bfbd42de46d49c201533982ae"},
-    {file = "ruff-0.6.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:482c1e6bfeb615eafc5899127b805d28e387bd87db38b2c0c41d271f5e58d8cc"},
-    {file = "ruff-0.6.5-py3-none-win32.whl", hash = "sha256:cf4d3fa53644137f6a4a27a2b397381d16454a1566ae5335855c187fbf67e4f5"},
-    {file = "ruff-0.6.5-py3-none-win_amd64.whl", hash = "sha256:3e42a57b58e3612051a636bc1ac4e6b838679530235520e8f095f7c44f706ff9"},
-    {file = "ruff-0.6.5-py3-none-win_arm64.whl", hash = "sha256:51935067740773afdf97493ba9b8231279e9beef0f2a8079188c4776c25688e0"},
-    {file = "ruff-0.6.5.tar.gz", hash = "sha256:4d32d87fab433c0cf285c3683dd4dae63be05fd7a1d65b3f5bf7cdd05a6b96fb"},
+    {file = "ruff-0.6.8-py3-none-linux_armv6l.whl", hash = "sha256:77944bca110ff0a43b768f05a529fecd0706aac7bcce36d7f1eeb4cbfca5f0f2"},
+    {file = "ruff-0.6.8-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:27b87e1801e786cd6ede4ada3faa5e254ce774de835e6723fd94551464c56b8c"},
+    {file = "ruff-0.6.8-py3-none-macosx_11_0_arm64.whl", hash = "sha256:cd48f945da2a6334f1793d7f701725a76ba93bf3d73c36f6b21fb04d5338dcf5"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:677e03c00f37c66cea033274295a983c7c546edea5043d0c798833adf4cf4c6f"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9f1476236b3eacfacfc0f66aa9e6cd39f2a624cb73ea99189556015f27c0bdeb"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6f5a2f17c7d32991169195d52a04c95b256378bbf0de8cb98478351eb70d526f"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:5fd0d4b7b1457c49e435ee1e437900ced9b35cb8dc5178921dfb7d98d65a08d0"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f8034b19b993e9601f2ddf2c517451e17a6ab5cdb1c13fdff50c1442a7171d87"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6cfb227b932ba8ef6e56c9f875d987973cd5e35bc5d05f5abf045af78ad8e098"},
+    {file = "ruff-0.6.8-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ef0411eccfc3909269fed47c61ffebdcb84a04504bafa6b6df9b85c27e813b0"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:007dee844738c3d2e6c24ab5bc7d43c99ba3e1943bd2d95d598582e9c1b27750"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:ce60058d3cdd8490e5e5471ef086b3f1e90ab872b548814e35930e21d848c9ce"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_i686.whl", hash = "sha256:1085c455d1b3fdb8021ad534379c60353b81ba079712bce7a900e834859182fa"},
+    {file = "ruff-0.6.8-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:70edf6a93b19481affd287d696d9e311388d808671bc209fb8907b46a8c3af44"},
+    {file = "ruff-0.6.8-py3-none-win32.whl", hash = "sha256:792213f7be25316f9b46b854df80a77e0da87ec66691e8f012f887b4a671ab5a"},
+    {file = "ruff-0.6.8-py3-none-win_amd64.whl", hash = "sha256:ec0517dc0f37cad14a5319ba7bba6e7e339d03fbf967a6d69b0907d61be7a263"},
+    {file = "ruff-0.6.8-py3-none-win_arm64.whl", hash = "sha256:8d3bb2e3fbb9875172119021a13eed38849e762499e3cfde9588e4b4d70968dc"},
+    {file = "ruff-0.6.8.tar.gz", hash = "sha256:a5bf44b1aa0adaf6d9d20f86162b34f7c593bfedabc51239953e446aefc8ce18"},
 ]
 
 [[package]]
@@ -10501,4 +10501,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "69b42bb1ff033f14e199fee8335356275099421d72bbd7037b7a991ea65cae08"
+content-hash = "c4580c22e2b220c8c80dbc3f765060a09e14874ed29b690c13a533bf0365e789"

api/pyproject.toml

@@ -123,6 +123,7 @@ FIRECRAWL_API_KEY = "fc-"
 TEI_EMBEDDING_SERVER_URL = "http://a.abc.com:11451"
 TEI_RERANK_SERVER_URL = "http://a.abc.com:11451"
 MIXEDBREAD_API_KEY = "mk-aaaaaaaaaaaaaaaaaaaa"
+VOYAGE_API_KEY = "va-aaaaaaaaaaaaaaaaaaaa"
 
 [tool.poetry]
 name = "dify-api"
@@ -286,4 +287,4 @@ optional = true
 
 [tool.poetry.group.lint.dependencies]
 dotenv-linter = "~0.5.0"
-ruff = "~0.6.5"
+ruff = "~0.6.8"

api/services/account_service.py

@@ -1,5 +1,6 @@
 import base64
 import logging
+import random
 import secrets
 import uuid
 from datetime import datetime, timedelta, timezone
@@ -22,7 +23,9 @@ from models.model import DifySetup
 from services.errors.account import (
     AccountAlreadyInTenantError,
     AccountLoginError,
+    AccountNotFoundError,
     AccountNotLinkTenantError,
+    AccountPasswordError,
     AccountRegisterError,
     CannotOperateSelfError,
     CurrentPasswordIncorrectError,
@@ -30,16 +33,21 @@ from services.errors.account import (
     LinkAccountIntegrateError,
     MemberNotInTenantError,
     NoPermissionError,
-    RateLimitExceededError,
     RoleAlreadyAssignedError,
     TenantNotFoundError,
 )
+from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from tasks.mail_email_code_login import send_email_code_login_mail_task
 from tasks.mail_invite_member_task import send_invite_member_mail_task
 from tasks.mail_reset_password_task import send_reset_password_mail_task
 
 
 class AccountService:
-    reset_password_rate_limiter = RateLimiter(prefix="reset_password_rate_limit", max_attempts=5, time_window=60 * 60)
+    reset_password_rate_limiter = RateLimiter(prefix="reset_password_rate_limit", max_attempts=1, time_window=60 * 1)
+    email_code_login_rate_limiter = RateLimiter(
+        prefix="email_code_login_rate_limit", max_attempts=1, time_window=60 * 1
+    )
+    LOGIN_MAX_ERROR_LIMITS = 5
 
     @staticmethod
     def load_user(user_id: str) -> None | Account:
@@ -85,23 +93,34 @@ class AccountService:
         return token
 
     @staticmethod
-    def authenticate(email: str, password: str) -> Account:
+    def authenticate(email: str, password: str, invite_token: str = None) -> Account:
         """authenticate account with email and password"""
 
         account = Account.query.filter_by(email=email).first()
         if not account:
-            raise AccountLoginError("Invalid email or password.")
+            raise AccountNotFoundError()
 
         if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
             raise AccountLoginError("Account is banned or closed.")
 
+        if password and invite_token and account.password is None:
+            # if invite_token is valid, set password and password_salt
+            salt = secrets.token_bytes(16)
+            base64_salt = base64.b64encode(salt).decode()
+            password_hashed = hash_password(password, salt)
+            base64_password_hashed = base64.b64encode(password_hashed).decode()
+            account.password = base64_password_hashed
+            account.password_salt = base64_salt
+
+        if account.password is None or not compare_password(password, account.password, account.password_salt):
+            raise AccountPasswordError("Invalid email or password.")
+
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
             account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
-            db.session.commit()
 
-        if account.password is None or not compare_password(password, account.password, account.password_salt):
-            raise AccountLoginError("Invalid email or password.")
+        db.session.commit()
+
         return account
 
     @staticmethod
@@ -127,9 +146,18 @@ class AccountService:
 
     @staticmethod
     def create_account(
-        email: str, name: str, interface_language: str, password: Optional[str] = None, interface_theme: str = "light"
+        email: str,
+        name: str,
+        interface_language: str,
+        password: Optional[str] = None,
+        interface_theme: str = "light",
+        is_setup: Optional[bool] = False,
     ) -> Account:
         """create account"""
+        if not dify_config.ALLOW_REGISTER and not is_setup:
+            from controllers.console.error import NotAllowedRegister
+
+            raise NotAllowedRegister()
         account = Account()
         account.email = email
         account.name = name
@@ -156,6 +184,19 @@ class AccountService:
         db.session.commit()
         return account
 
+    @staticmethod
+    def create_account_and_tenant(
+        email: str, name: str, interface_language: str, password: Optional[str] = None
+    ) -> Account:
+        """create account"""
+        account = AccountService.create_account(
+            email=email, name=name, interface_language=interface_language, password=password
+        )
+
+        TenantService.create_owner_tenant_if_not_exist(account=account)
+
+        return account
+
     @staticmethod
     def link_account_integrate(provider: str, open_id: str, account: Account) -> None:
         """Link account integrate"""
@@ -214,6 +255,9 @@ class AccountService:
         if ip_address:
             AccountService.update_last_login(account, ip_address=ip_address)
         exp = timedelta(days=30)
+        if account.status == AccountStatus.PENDING.value:
+            account.status = AccountStatus.ACTIVE.value
+            db.session.commit()
         token = AccountService.get_account_jwt_token(account, exp=exp)
         redis_client.set(_get_login_cache_key(account_id=account.id, token=token), "1", ex=int(exp.total_seconds()))
         return token
@@ -229,13 +273,26 @@ class AccountService:
         return AccountService.load_user(account_id)
 
     @classmethod
-    def send_reset_password_email(cls, account):
-        if cls.reset_password_rate_limiter.is_rate_limited(account.email):
-            raise RateLimitExceededError(f"Rate limit exceeded for email: {account.email}. Please try again later.")
+    def send_reset_password_email(
+        cls, account: Optional[Account] = None, email: Optional[str] = None, language: Optional[str] = "en-US"
+    ):
+        account_email = account.email if account else email
 
-        token = TokenManager.generate_token(account, "reset_password")
-        send_reset_password_mail_task.delay(language=account.interface_language, to=account.email, token=token)
-        cls.reset_password_rate_limiter.increment_rate_limit(account.email)
+        if cls.reset_password_rate_limiter.is_rate_limited(account_email):
+            from controllers.console.auth.error import PasswordResetRateLimitExceededError
+
+            raise PasswordResetRateLimitExceededError()
+
+        code = "".join([str(random.randint(0, 9)) for _ in range(6)])
+        token = TokenManager.generate_token(
+            account=account, email=email, token_type="reset_password", additional_data={"code": code}
+        )
+        send_reset_password_mail_task.delay(
+            language=language,
+            to=account_email,
+            code=code,
+        )
+        cls.reset_password_rate_limiter.increment_rate_limit(account_email)
         return token
 
     @classmethod
@@ -246,6 +303,112 @@ class AccountService:
     def get_reset_password_data(cls, token: str) -> Optional[dict[str, Any]]:
         return TokenManager.get_token_data(token, "reset_password")
 
+    @classmethod
+    def send_email_code_login_email(
+        cls, account: Optional[Account] = None, email: Optional[str] = None, language: Optional[str] = "en-US"
+    ):
+        if cls.email_code_login_rate_limiter.is_rate_limited(email):
+            from controllers.console.auth.error import EmailCodeLoginRateLimitExceededError
+
+            raise EmailCodeLoginRateLimitExceededError()
+
+        code = "".join([str(random.randint(0, 9)) for _ in range(6)])
+        token = TokenManager.generate_token(
+            account=account, email=email, token_type="email_code_login", additional_data={"code": code}
+        )
+        send_email_code_login_mail_task.delay(
+            language=language,
+            to=account.email if account else email,
+            code=code,
+        )
+        cls.email_code_login_rate_limiter.increment_rate_limit(email)
+        return token
+
+    @classmethod
+    def get_email_code_login_data(cls, token: str) -> Optional[dict[str, Any]]:
+        return TokenManager.get_token_data(token, "email_code_login")
+
+    @classmethod
+    def revoke_email_code_login_token(cls, token: str):
+        TokenManager.revoke_token(token, "email_code_login")
+
+    @classmethod
+    def get_user_through_email(cls, email: str):
+        account = db.session.query(Account).filter(Account.email == email).first()
+        if not account:
+            return None
+
+        if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
+            raise Unauthorized("Account is banned or closed.")
+
+        return account
+
+    @staticmethod
+    def add_login_error_rate_limit(email: str) -> None:
+        key = f"login_error_rate_limit:{email}"
+        count = redis_client.get(key)
+        if count is None:
+            count = 0
+        count = int(count) + 1
+        redis_client.setex(key, 60 * 60 * 24, count)
+
+    @staticmethod
+    def is_login_error_rate_limit(email: str) -> bool:
+        key = f"login_error_rate_limit:{email}"
+        count = redis_client.get(key)
+        if count is None:
+            return False
+
+        count = int(count)
+        if count > AccountService.LOGIN_MAX_ERROR_LIMITS:
+            return True
+        return False
+
+    @staticmethod
+    def reset_login_error_rate_limit(email: str):
+        key = f"login_error_rate_limit:{email}"
+        redis_client.delete(key)
+
+    @staticmethod
+    def is_email_send_ip_limit(ip_address: str):
+        minute_key = f"email_send_ip_limit_minute:{ip_address}"
+        freeze_key = f"email_send_ip_limit_freeze:{ip_address}"
+        hour_limit_key = f"email_send_ip_limit_hour:{ip_address}"
+
+        # check ip is frozen
+        if redis_client.get(freeze_key):
+            return True
+
+        # check current minute count
+        current_minute_count = redis_client.get(minute_key)
+        if current_minute_count is None:
+            current_minute_count = 0
+        current_minute_count = int(current_minute_count)
+
+        # check current hour count
+        if current_minute_count > dify_config.EMAIL_SEND_IP_LIMIT_PER_MINUTE:
+            hour_limit_count = redis_client.get(hour_limit_key)
+            if hour_limit_count is None:
+                hour_limit_count = 0
+            hour_limit_count = int(hour_limit_count)
+
+            if hour_limit_count >= 1:
+                redis_client.setex(freeze_key, 60 * 60, 1)
+                return True
+            else:
+                redis_client.setex(hour_limit_key, 60 * 10, hour_limit_count + 1)  # first time limit 10 minutes
+
+            # add hour limit count
+            redis_client.incr(hour_limit_key)
+            redis_client.expire(hour_limit_key, 60 * 60)
+
+            return True
+
+        redis_client.setex(minute_key, 60, current_minute_count + 1)
+        redis_client.expire(minute_key, 60)
+
+        return False
+
 
 def _get_login_cache_key(*, account_id: str, token: str):
     return f"account_login:{account_id}:{token}"
@@ -253,8 +416,12 @@ def _get_login_cache_key(*, account_id: str, token: str):
 
 class TenantService:
     @staticmethod
-    def create_tenant(name: str) -> Tenant:
+    def create_tenant(name: str, is_setup: Optional[bool] = False) -> Tenant:
         """Create tenant"""
+        if not dify_config.ALLOW_CREATE_WORKSPACE and not is_setup:
+            from controllers.console.error import NotAllowedCreateWorkspace
+
+            raise NotAllowedCreateWorkspace()
         tenant = Tenant(name=name)
 
         db.session.add(tenant)
@@ -265,8 +432,12 @@ class TenantService:
         return tenant
 
     @staticmethod
-    def create_owner_tenant_if_not_exist(account: Account, name: Optional[str] = None):
+    def create_owner_tenant_if_not_exist(
+        account: Account, name: Optional[str] = None, is_setup: Optional[bool] = False
+    ):
         """Create owner tenant if not exist"""
+        if not dify_config.ALLOW_CREATE_WORKSPACE and not is_setup:
+            raise WorkSpaceNotAllowedCreateError()
         available_ta = (
             TenantAccountJoin.query.filter_by(account_id=account.id).order_by(TenantAccountJoin.id.asc()).first()
         )
@@ -275,9 +446,9 @@ class TenantService:
             return
 
         if name:
-            tenant = TenantService.create_tenant(name)
+            tenant = TenantService.create_tenant(name=name, is_setup=is_setup)
         else:
-            tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+            tenant = TenantService.create_tenant(name=f"{account.name}'s Workspace", is_setup=is_setup)
         TenantService.create_tenant_member(tenant, account, role="owner")
         account.current_tenant = tenant
         db.session.commit()
@@ -291,8 +462,13 @@ class TenantService:
                 logging.error(f"Tenant {tenant.id} has already an owner.")
                 raise Exception("Tenant already has an owner.")
 
-        ta = TenantAccountJoin(tenant_id=tenant.id, account_id=account.id, role=role)
-        db.session.add(ta)
+        ta = db.session.query(TenantAccountJoin).filter_by(tenant_id=tenant.id, account_id=account.id).first()
+        if ta:
+            ta.role = role
+        else:
+            ta = TenantAccountJoin(tenant_id=tenant.id, account_id=account.id, role=role)
+            db.session.add(ta)
+
         db.session.commit()
         return ta
 
@@ -509,12 +685,13 @@ class RegisterService:
                 name=name,
                 interface_language=languages[0],
                 password=password,
+                is_setup=True,
             )
 
             account.last_login_ip = ip_address
             account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
 
-            TenantService.create_owner_tenant_if_not_exist(account)
+            TenantService.create_owner_tenant_if_not_exist(account=account, is_setup=True)
 
             dify_setup = DifySetup(version=dify_config.CURRENT_VERSION)
             db.session.add(dify_setup)
@@ -551,15 +728,16 @@ class RegisterService:
 
             if open_id is not None or provider is not None:
                 AccountService.link_account_integrate(provider, open_id, account)
-            if dify_config.EDITION != "SELF_HOSTED":
-                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
 
+            if dify_config.ALLOW_CREATE_WORKSPACE:
+                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
                 TenantService.create_tenant_member(tenant, account, role="owner")
                 account.current_tenant = tenant
-
                 tenant_was_created.send(tenant)
 
             db.session.commit()
+        except WorkSpaceNotAllowedCreateError:
+            db.session.rollback()
         except Exception as e:
             db.session.rollback()
             logging.error(f"Register failed: {e}")
@@ -618,6 +796,11 @@ class RegisterService:
         redis_client.setex(cls._get_invitation_token_key(token), expiry_hours * 60 * 60, json.dumps(invitation_data))
         return token
 
+    @classmethod
+    def is_valid_invite_token(cls, token: str) -> bool:
+        data = redis_client.get(cls._get_invitation_token_key(token))
+        return data is not None
+
     @classmethod
     def revoke_token(cls, workspace_id: str, email: str, token: str):
         if workspace_id and email:
@@ -666,7 +849,9 @@ class RegisterService:
         }
 
     @classmethod
-    def _get_invitation_by_token(cls, token: str, workspace_id: str, email: str) -> Optional[dict[str, str]]:
+    def _get_invitation_by_token(
+        cls, token: str, workspace_id: Optional[str] = None, email: Optional[str] = None
+    ) -> Optional[dict[str, str]]:
         if workspace_id is not None and email is not None:
             email_hash = sha256(email.encode()).hexdigest()
             cache_key = f"member_invite_token:{workspace_id}, {email_hash}:{token}"

api/services/errors/account.py

@@ -13,6 +13,10 @@ class AccountLoginError(BaseServiceError):
     pass
 
 
+class AccountPasswordError(BaseServiceError):
+    pass
+
+
 class AccountNotLinkTenantError(BaseServiceError):
     pass
 

api/services/errors/workspace.py

@@ -0,0 +1,9 @@
+from services.errors.base import BaseServiceError
+
+
+class WorkSpaceNotAllowedCreateError(BaseServiceError):
+    pass
+
+
+class WorkSpaceNotFoundError(BaseServiceError):
+    pass

api/services/feature_service.py

@@ -42,6 +42,11 @@ class SystemFeatureModel(BaseModel):
     sso_enforced_for_web: bool = False
     sso_enforced_for_web_protocol: str = ""
     enable_web_sso_switch_component: bool = False
+    enable_email_code_login: bool = False
+    enable_email_password_login: bool = True
+    enable_social_oauth_login: bool = False
+    is_allow_register: bool = True
+    is_allow_create_workspace: bool = True
 
 
 class FeatureService:
@@ -60,12 +65,22 @@ class FeatureService:
     def get_system_features(cls) -> SystemFeatureModel:
         system_features = SystemFeatureModel()
 
+        cls.__fulfill_login_params_from_env(system_features)
+
         if dify_config.ENTERPRISE_ENABLED:
             system_features.enable_web_sso_switch_component = True
             cls._fulfill_params_from_enterprise(system_features)
 
         return system_features
 
+    @classmethod
+    def __fulfill_login_params_from_env(cls, features: FeatureModel):
+        features.enable_email_code_login = dify_config.ENABLE_EMAIL_CODE_LOGIN
+        features.enable_email_password_login = dify_config.ENABLE_EMAIL_PASSWORD_LOGIN
+        features.enable_social_oauth_login = dify_config.ENABLE_SOCIAL_OAUTH_LOGIN
+        features.is_allow_register = dify_config.ALLOW_REGISTER
+        features.is_allow_create_workspace = dify_config.ALLOW_CREATE_WORKSPACE
+
     @classmethod
     def _fulfill_params_from_env(cls, features: FeatureModel):
         features.can_replace_logo = dify_config.CAN_REPLACE_LOGO
@@ -117,3 +132,5 @@ class FeatureService:
         features.sso_enforced_for_signin_protocol = enterprise_info["sso_enforced_for_signin_protocol"]
         features.sso_enforced_for_web = enterprise_info["sso_enforced_for_web"]
         features.sso_enforced_for_web_protocol = enterprise_info["sso_enforced_for_web_protocol"]
+        features.enable_email_code_login = enterprise_info["enable_email_code_login"]
+        features.enable_email_password_login = enterprise_info["enable_email_password_login"]

api/tasks/mail_email_code_login.py

@@ -0,0 +1,41 @@
+import logging
+import time
+
+import click
+from celery import shared_task
+from flask import render_template
+
+from extensions.ext_mail import mail
+
+
+@shared_task(queue="mail")
+def send_email_code_login_mail_task(language: str, to: str, code: str):
+    """
+    Async Send email code login mail
+    :param language: Language in which the email should be sent (e.g., 'en', 'zh')
+    :param to: Recipient email address
+    :param code: Email code to be included in the email
+    """
+    if not mail.is_inited():
+        return
+
+    logging.info(click.style("Start email code login mail to {}".format(to), fg="green"))
+    start_at = time.perf_counter()
+
+    # send email code login mail using different languages
+    try:
+        if language == "zh-Hans":
+            html_content = render_template("email_code_login_mail_template_zh-CN.html", to=to, code=code)
+            mail.send(to=to, subject="邮箱验证码", html=html_content)
+        else:
+            html_content = render_template("email_code_login_mail_template_en-US.html", to=to, code=code)
+            mail.send(to=to, subject="Email Code", html=html_content)
+
+        end_at = time.perf_counter()
+        logging.info(
+            click.style(
+                "Send email code login mail to {} succeeded: latency: {}".format(to, end_at - start_at), fg="green"
+            )
+        )
+    except Exception:
+        logging.exception("Send email code login mail to {} failed".format(to))

api/tasks/mail_reset_password_task.py

@@ -5,17 +5,16 @@ import click
 from celery import shared_task
 from flask import render_template
 
-from configs import dify_config
 from extensions.ext_mail import mail
 
 
 @shared_task(queue="mail")
-def send_reset_password_mail_task(language: str, to: str, token: str):
+def send_reset_password_mail_task(language: str, to: str, code: str):
     """
     Async Send reset password mail
     :param language: Language in which the email should be sent (e.g., 'en', 'zh')
     :param to: Recipient email address
-    :param token: Reset password token to be included in the email
+    :param code: Reset password code
     """
     if not mail.is_inited():
         return
@@ -25,12 +24,11 @@ def send_reset_password_mail_task(language: str, to: str, token: str):
 
     # send reset password mail using different languages
     try:
-        url = f"{dify_config.CONSOLE_WEB_URL}/forgot-password?token={token}"
         if language == "zh-Hans":
-            html_content = render_template("reset_password_mail_template_zh-CN.html", to=to, url=url)
+            html_content = render_template("reset_password_mail_template_zh-CN.html", to=to, code=code)
             mail.send(to=to, subject="重置您的 Dify 密码", html=html_content)
         else:
-            html_content = render_template("reset_password_mail_template_en-US.html", to=to, url=url)
+            html_content = render_template("reset_password_mail_template_en-US.html", to=to, code=code)
             mail.send(to=to, subject="Reset Your Dify Password", html=html_content)
 
         end_at = time.perf_counter()

api/templates/email_code_login_mail_template_en-US.html

@@ -0,0 +1,74 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <style>
+      body {
+        font-family: 'Arial', sans-serif;
+        line-height: 16pt;
+        color: #101828;
+        background-color: #e9ebf0;
+        margin: 0;
+        padding: 0;
+      }
+      .container {
+        width: 600px;
+        height: 360px;
+        margin: 40px auto;
+        padding: 36px 48px;
+        background-color: #fcfcfd;
+        border-radius: 16px;
+        border: 1px solid #ffffff;
+        box-shadow: 0 2px 4px -2px rgba(9, 9, 11, 0.08);
+      }
+      .header {
+        margin-bottom: 24px;
+      }
+      .header img {
+        max-width: 100px;
+        height: auto;
+      }
+      .title {
+        font-weight: 600;
+        font-size: 24px;
+        line-height: 28.8px;
+      }
+      .description {
+        font-size: 13px;
+        line-height: 16px;
+        color: #676f83;
+        margin-top: 12px;
+      }
+      .code-content {
+        padding: 16px 32px;
+        text-align: center;
+        border-radius: 16px;
+        background-color: #f2f4f7;
+        margin: 16px auto;
+      }
+      .code {
+        line-height: 36px;
+        font-weight: 700;
+        font-size: 30px;
+      }
+      .tips {
+        line-height: 16px;
+        color: #676f83;
+        font-size: 13px;
+      }
+    </style>
+  </head>
+  <body>
+    <div class="container">
+      <div class="header">
+        <!-- Optional: Add a logo or a header image here -->
+        <img src="https://cloud.dify.ai/logo/logo-site.png" alt="Dify Logo" />
+      </div>
+      <p class="title">Your login code for Dify</p>
+      <p class="description">Copy and paste this code, this code will only be valid for the next 5 minutes.</p>
+      <div class="code-content">
+        <span class="code">{{code}}</span>
+      </div>
+      <p class="tips">If you didn't request a login, don't worry. You can safely ignore this email.</p>
+    </div>
+  </body>
+</html>

api/templates/email_code_login_mail_template_zh-CN.html

@@ -0,0 +1,74 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <style>
+      body {
+        font-family: 'Arial', sans-serif;
+        line-height: 16pt;
+        color: #101828;
+        background-color: #e9ebf0;
+        margin: 0;
+        padding: 0;
+      }
+      .container {
+        width: 600px;
+        height: 360px;
+        margin: 40px auto;
+        padding: 36px 48px;
+        background-color: #fcfcfd;
+        border-radius: 16px;
+        border: 1px solid #ffffff;
+        box-shadow: 0 2px 4px -2px rgba(9, 9, 11, 0.08);
+      }
+      .header {
+        margin-bottom: 24px;
+      }
+      .header img {
+        max-width: 100px;
+        height: auto;
+      }
+      .title {
+        font-weight: 600;
+        font-size: 24px;
+        line-height: 28.8px;
+      }
+      .description {
+        font-size: 13px;
+        line-height: 16px;
+        color: #676f83;
+        margin-top: 12px;
+      }
+      .code-content {
+        padding: 16px 32px;
+        text-align: center;
+        border-radius: 16px;
+        background-color: #f2f4f7;
+        margin: 16px auto;
+      }
+      .code {
+        line-height: 36px;
+        font-weight: 700;
+        font-size: 30px;
+      }
+      .tips {
+        line-height: 16px;
+        color: #676f83;
+        font-size: 13px;
+      }
+    </style>
+  </head>
+  <body>
+    <div class="container">
+      <div class="header">
+        <!-- Optional: Add a logo or a header image here -->
+        <img src="https://cloud.dify.ai/logo/logo-site.png" alt="Dify Logo" />
+      </div>
+      <p class="title">Dify 的登录验证码</p>
+      <p class="description">复制并粘贴此验证码，注意验证码仅在接下来的 5 分钟内有效。</p>
+      <div class="code-content">
+        <span class="code">{{code}}</span>
+      </div>
+      <p class="tips">如果您没有请求登陆，请不要担心。您可以安全地忽略此电子邮件。</p>
+    </div>
+  </body>
+</html>

api/templates/invite_member_mail_template_en-US.html

@@ -59,7 +59,7 @@
         <div class="content">
             <p>Dear {{ to }},</p>
             <p>{{ inviter_name }} is pleased to invite you to join our workspace on Dify, a platform specifically designed for LLM application development. On Dify, you can explore, create, and collaborate to build and operate AI applications.</p>
-            <p>You can now log in to Dify using the GitHub or Google account associated with this email.</p>
+            <p>Click the button below to log in to Dify and join the workspace.</p>
             <p style="text-align: center;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">Login Here</a></p>
         </div>
         <div class="footer">

api/templates/invite_member_mail_template_zh-CN.html

@@ -59,7 +59,7 @@
         <div class="content">
             <p>尊敬的 {{ to }}，</p>
             <p>{{ inviter_name }} 现邀请您加入我们在 Dify 的工作区，这是一个专为 LLM 应用开发而设计的平台。在 Dify 上，您可以探索、创造和合作，构建和运营 AI 应用。</p>
-            <p>您现在可以使用与此邮件相对应的 GitHub 或 Google 账号登录 Dify。</p>
+            <p>点击下方按钮即可登录 Dify 并且加入空间。</p>
             <p style="text-align: center;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">在此登录</a></p>
         </div>
         <div class="footer">

api/templates/reset_password_mail_template_en-US.html

@@ -1,72 +1,74 @@
 <!DOCTYPE html>
 <html>
-<head>
+  <head>
     <style>
-        body {
-            font-family: 'Arial', sans-serif;
-            line-height: 16pt;
-            color: #374151;
-            background-color: #E5E7EB;
-            margin: 0;
-            padding: 0;
-        }
-        .container {
-            width: 100%;
-            max-width: 560px;
-            margin: 40px auto;
-            padding: 20px;
-            background-color: #F3F4F6;
-            border-radius: 8px;
-            box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
-        }
-        .header {
-            text-align: center;
-            margin-bottom: 20px;
-        }
-        .header img {
-            max-width: 100px;
-            height: auto;
-        }
-        .button {
-            display: inline-block;
-            padding: 12px 24px;
-            background-color: #2970FF;
-            color: white;
-            text-decoration: none;
-            border-radius: 4px;
-            text-align: center;
-            transition: background-color 0.3s ease;
-        }
-        .button:hover {
-            background-color: #265DD4;
-        }
-        .footer {
-            font-size: 0.9em;
-            color: #777777;
-            margin-top: 30px;
-        }
-        .content {
-            margin-top: 20px;
-        }
+      body {
+        font-family: 'Arial', sans-serif;
+        line-height: 16pt;
+        color: #101828;
+        background-color: #e9ebf0;
+        margin: 0;
+        padding: 0;
+      }
+      .container {
+        width: 600px;
+        height: 360px;
+        margin: 40px auto;
+        padding: 36px 48px;
+        background-color: #fcfcfd;
+        border-radius: 16px;
+        border: 1px solid #ffffff;
+        box-shadow: 0 2px 4px -2px rgba(9, 9, 11, 0.08);
+      }
+      .header {
+        margin-bottom: 24px;
+      }
+      .header img {
+        max-width: 100px;
+        height: auto;
+      }
+      .title {
+        font-weight: 600;
+        font-size: 24px;
+        line-height: 28.8px;
+      }
+      .description {
+        font-size: 13px;
+        line-height: 16px;
+        color: #676f83;
+        margin-top: 12px;
+      }
+      .code-content {
+        padding: 16px 32px;
+        text-align: center;
+        border-radius: 16px;
+        background-color: #f2f4f7;
+        margin: 16px auto;
+      }
+      .code {
+        line-height: 36px;
+        font-weight: 700;
+        font-size: 30px;
+      }
+      .tips {
+        line-height: 16px;
+        color: #676f83;
+        font-size: 13px;
+      }
     </style>
-</head>
-
-<body>
+  </head>
+  <body>
     <div class="container">
-        <div class="header">
-            <img src="https://cloud.dify.ai/logo/logo-site.png" alt="Dify Logo">
-        </div>
-        <div class="content">
-            <p>Dear {{ to }},</p>
-            <p>We have received a request to reset your password. If you initiated this request, please click the button below to reset your password:</p>
-            <p style="text-align: center;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">Reset Password</a></p>
-            <p>If you did not request a password reset, please ignore this email and your account will remain secure.</p>
-        </div>
-        <div class="footer">
-            <p>Best regards,</p>
-            <p>Dify Team</p>
-            <p>Please do not reply directly to this email; it is automatically sent by the system.</p>
-        </div>
+      <div class="header">
+        <!-- Optional: Add a logo or a header image here -->
+        <img src="https://cloud.dify.ai/logo/logo-site.png" alt="Dify Logo" />
+      </div>
+        <p class="title">Reset your Dify password</p>
+      <p class="description">Copy and paste this code, this code will only be valid for the next 5 minutes.</p>
+      <div class="code-content">
+        <span class="code">{{code}}</span>
+      </div>
+        <p class="tips">If you didn't request a reset, don't worry. You can safely ignore this email.</p>
     </div>
-</body>
+  </body>
 </html>

api/templates/reset_password_mail_template_zh-CN.html

@@ -1,72 +1,74 @@
 <!DOCTYPE html>
 <html>
-<head>
+  <head>
     <style>
-        body {
-            font-family: 'Arial', sans-serif;
-            line-height: 16pt;
-            color: #374151;
-            background-color: #E5E7EB;
-            margin: 0;
-            padding: 0;
-        }
-        .container {
-            width: 100%;
-            max-width: 560px;
-            margin: 40px auto;
-            padding: 20px;
-            background-color: #F3F4F6;
-            border-radius: 8px;
-            box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
-        }
-        .header {
-            text-align: center;
-            margin-bottom: 20px;
-        }
-        .header img {
-            max-width: 100px;
-            height: auto;
-        }
-        .button {
-            display: inline-block;
-            padding: 12px 24px;
-            background-color: #2970FF;
-            color: white;
-            text-decoration: none;
-            border-radius: 4px;
-            text-align: center;
-            transition: background-color 0.3s ease;
-        }
-        .button:hover {
-            background-color: #265DD4;
-        }
-        .footer {
-            font-size: 0.9em;
-            color: #777777;
-            margin-top: 30px;
-        }
-        .content {
-            margin-top: 20px;
-        }
+      body {
+        font-family: 'Arial', sans-serif;
+        line-height: 16pt;
+        color: #101828;
+        background-color: #e9ebf0;
+        margin: 0;
+        padding: 0;
+      }
+      .container {
+        width: 600px;
+        height: 360px;
+        margin: 40px auto;
+        padding: 36px 48px;
+        background-color: #fcfcfd;
+        border-radius: 16px;
+        border: 1px solid #ffffff;
+        box-shadow: 0 2px 4px -2px rgba(9, 9, 11, 0.08);
+      }
+      .header {
+        margin-bottom: 24px;
+      }
+      .header img {
+        max-width: 100px;
+        height: auto;
+      }
+      .title {
+        font-weight: 600;
+        font-size: 24px;
+        line-height: 28.8px;
+      }
+      .description {
+        font-size: 13px;
+        line-height: 16px;
+        color: #676f83;
+        margin-top: 12px;
+      }
+      .code-content {
+        padding: 16px 32px;
+        text-align: center;
+        border-radius: 16px;
+        background-color: #f2f4f7;
+        margin: 16px auto;
+      }
+      .code {
+        line-height: 36px;
+        font-weight: 700;
+        font-size: 30px;
+      }
+      .tips {
+        line-height: 16px;
+        color: #676f83;
+        font-size: 13px;
+      }
     </style>
-</head>
-
-<body>
+  </head>
+  <body>
     <div class="container">
-        <div class="header">
-            <img src="https://cloud.dify.ai/logo/logo-site.png" alt="Dify Logo">
-        </div>
-        <div class="content">
-            <p>尊敬的 {{ to }}，</p>
-            <p>我们收到了您关于重置密码的请求。如果是您本人操作，请点击以下按钮重置您的密码：</p>
-            <p style="text-align: center;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">重置密码</a></p>
-            <p>如果您没有请求重置密码，请忽略此邮件，您的账户信息将保持安全。</p>
-        </div>
-        <div class="footer">
-            <p>此致，</p>
-            <p>Dify 团队</p>
-            <p>请不要直接回复此电子邮件；由系统自动发送。</p>
-        </div>
+      <div class="header">
+        <!-- Optional: Add a logo or a header image here -->
+        <img src="https://cloud.dify.ai/logo/logo-site.png" alt="Dify Logo" />
+      </div>
+        <p class="title">重置您的 Dify 账户密码</p>
+      <p class="description">复制并粘贴此验证码，注意验证码仅在接下来的 5 分钟内有效。</p>
+      <div class="code-content">
+        <span class="code">{{code}}</span>
+      </div>
+        <p class="tips">如果您没有请求重置，请不要担心。您可以安全地忽略此电子邮件。</p>
     </div>
-</body>
+  </body>
 </html>

api/tests/integration_tests/model_runtime/voyage/test_provider.py

@@ -0,0 +1,25 @@
+import os
+from unittest.mock import Mock, patch
+
+import pytest
+
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.voyage.voyage import VoyageProvider
+
+
+def test_validate_provider_credentials():
+    provider = VoyageProvider()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        provider.validate_provider_credentials(credentials={"api_key": "hahahaha"})
+    with patch("requests.post") as mock_post:
+        mock_response = Mock()
+        mock_response.json.return_value = {
+            "object": "list",
+            "data": [{"object": "embedding", "embedding": [0.23333 for _ in range(1024)], "index": 0}],
+            "model": "voyage-3",
+            "usage": {"total_tokens": 1},
+        }
+        mock_response.status_code = 200
+        mock_post.return_value = mock_response
+        provider.validate_provider_credentials(credentials={"api_key": os.environ.get("VOYAGE_API_KEY")})

api/tests/integration_tests/model_runtime/voyage/test_rerank.py

@@ -0,0 +1,92 @@
+import os
+from unittest.mock import Mock, patch
+
+import pytest
+
+from core.model_runtime.entities.rerank_entities import RerankResult
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.voyage.rerank.rerank import VoyageRerankModel
+
+
+def test_validate_credentials():
+    model = VoyageRerankModel()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        model.validate_credentials(
+            model="rerank-lite-1",
+            credentials={"api_key": "invalid_key"},
+        )
+    with patch("httpx.post") as mock_post:
+        mock_response = Mock()
+        mock_response.json.return_value = {
+            "object": "list",
+            "data": [
+                {
+                    "relevance_score": 0.546875,
+                    "index": 0,
+                    "document": "Carson City is the capital city of the American state of Nevada. At the 2010 United "
+                    "States Census, Carson City had a population of 55,274.",
+                },
+                {
+                    "relevance_score": 0.4765625,
+                    "index": 1,
+                    "document": "The Commonwealth of the Northern Mariana Islands is a group of islands in the "
+                    "Pacific Ocean that are a political division controlled by the United States. Its "
+                    "capital is Saipan.",
+                },
+            ],
+            "model": "rerank-lite-1",
+            "usage": {"total_tokens": 96},
+        }
+        mock_response.status_code = 200
+        mock_post.return_value = mock_response
+        model.validate_credentials(
+            model="rerank-lite-1",
+            credentials={
+                "api_key": os.environ.get("VOYAGE_API_KEY"),
+            },
+        )
+
+
+def test_invoke_model():
+    model = VoyageRerankModel()
+    with patch("httpx.post") as mock_post:
+        mock_response = Mock()
+        mock_response.json.return_value = {
+            "object": "list",
+            "data": [
+                {
+                    "relevance_score": 0.84375,
+                    "index": 0,
+                    "document": "Kasumi is a girl name of Japanese origin meaning mist.",
+                },
+                {
+                    "relevance_score": 0.4765625,
+                    "index": 1,
+                    "document": "Her music is a kawaii bass, a mix of future bass, pop, and kawaii music and she "
+                    "leads a team named PopiParty.",
+                },
+            ],
+            "model": "rerank-lite-1",
+            "usage": {"total_tokens": 59},
+        }
+        mock_response.status_code = 200
+        mock_post.return_value = mock_response
+        result = model.invoke(
+            model="rerank-lite-1",
+            credentials={
+                "api_key": os.environ.get("VOYAGE_API_KEY"),
+            },
+            query="Who is Kasumi?",
+            docs=[
+                "Kasumi is a girl name of Japanese origin meaning mist.",
+                "Her music is a kawaii bass, a mix of future bass, pop, and kawaii music and she leads a team named "
+                "PopiParty.",
+            ],
+            score_threshold=0.5,
+        )
+
+        assert isinstance(result, RerankResult)
+        assert len(result.docs) == 1
+        assert result.docs[0].index == 0
+        assert result.docs[0].score >= 0.5

api/tests/integration_tests/model_runtime/voyage/test_text_embedding.py

@@ -0,0 +1,70 @@
+import os
+from unittest.mock import Mock, patch
+
+import pytest
+
+from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.voyage.text_embedding.text_embedding import VoyageTextEmbeddingModel
+
+
+def test_validate_credentials():
+    model = VoyageTextEmbeddingModel()
+
+    with pytest.raises(CredentialsValidateFailedError):
+        model.validate_credentials(model="voyage-3", credentials={"api_key": "invalid_key"})
+    with patch("requests.post") as mock_post:
+        mock_response = Mock()
+        mock_response.json.return_value = {
+            "object": "list",
+            "data": [{"object": "embedding", "embedding": [0.23333 for _ in range(1024)], "index": 0}],
+            "model": "voyage-3",
+            "usage": {"total_tokens": 1},
+        }
+        mock_response.status_code = 200
+        mock_post.return_value = mock_response
+        model.validate_credentials(model="voyage-3", credentials={"api_key": os.environ.get("VOYAGE_API_KEY")})
+
+
+def test_invoke_model():
+    model = VoyageTextEmbeddingModel()
+
+    with patch("requests.post") as mock_post:
+        mock_response = Mock()
+        mock_response.json.return_value = {
+            "object": "list",
+            "data": [
+                {"object": "embedding", "embedding": [0.23333 for _ in range(1024)], "index": 0},
+                {"object": "embedding", "embedding": [0.23333 for _ in range(1024)], "index": 1},
+            ],
+            "model": "voyage-3",
+            "usage": {"total_tokens": 2},
+        }
+        mock_response.status_code = 200
+        mock_post.return_value = mock_response
+        result = model.invoke(
+            model="voyage-3",
+            credentials={
+                "api_key": os.environ.get("VOYAGE_API_KEY"),
+            },
+            texts=["hello", "world"],
+            user="abc-123",
+        )
+
+        assert isinstance(result, TextEmbeddingResult)
+        assert len(result.embeddings) == 2
+        assert result.usage.total_tokens == 2
+
+
+def test_get_num_tokens():
+    model = VoyageTextEmbeddingModel()
+
+    num_tokens = model.get_num_tokens(
+        model="voyage-3",
+        credentials={
+            "api_key": os.environ.get("VOYAGE_API_KEY"),
+        },
+        texts=["ping"],
+    )
+
+    assert num_tokens == 1

api/tests/integration_tests/tools/__mock/http.py

@@ -17,7 +17,7 @@ class MockedHttp:
         request = httpx.Request(
             method, url, params=kwargs.get("params"), headers=kwargs.get("headers"), cookies=kwargs.get("cookies")
         )
-        data = kwargs.get("data", None)
+        data = kwargs.get("data")
         resp = json.dumps(data).encode("utf-8") if data else b"OK"
         response = httpx.Response(
             status_code=200,

api/tests/integration_tests/workflow/nodes/__mock/http.py

@@ -22,8 +22,8 @@ class MockedHttp:
             return response
 
         # get data, files
-        data = kwargs.get("data", None)
-        files = kwargs.get("files", None)
+        data = kwargs.get("data")
+        files = kwargs.get("files")
         if data is not None:
             resp = dumps(data).encode("utf-8")
         elif files is not None:

dev/pytest/pytest_model_runtime.sh

@@ -9,4 +9,5 @@ pytest api/tests/integration_tests/model_runtime/anthropic \
   api/tests/integration_tests/model_runtime/upstage \
   api/tests/integration_tests/model_runtime/fireworks \
   api/tests/integration_tests/model_runtime/nomic \
-  api/tests/integration_tests/model_runtime/mixedbread
+  api/tests/integration_tests/model_runtime/mixedbread \
+  api/tests/integration_tests/model_runtime/voyage

docker/.env.example

@@ -567,8 +567,7 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
 INVITE_EXPIRY_HOURS=72
 
 # Reset password token valid time (hours),
-# Default: 24.
-RESET_PASSWORD_TOKEN_EXPIRY_HOURS=24
+RESET_PASSWORD_TOKEN_EXPIRY_HOURS=1/12
 
 # The sandbox service endpoint.
 CODE_EXECUTION_ENDPOINT=http://sandbox:8194
@@ -797,4 +796,4 @@ POSITION_TOOL_EXCLUDES=
 # Example: POSITION_PROVIDER_PINS=openai,openllm
 POSITION_PROVIDER_PINS=
 POSITION_PROVIDER_INCLUDES=
-POSITION_PROVIDER_EXCLUDES=
+POSITION_PROVIDER_EXCLUDES=

web/app/components/workflow/nodes/knowledge-retrieval/use-config.ts

@@ -136,6 +136,8 @@ const useConfig = (id: string, payload: KnowledgeRetrievalNodeType) => {
         top_k: multipleRetrievalConfig?.top_k || DATASET_DEFAULT.top_k,
         score_threshold: multipleRetrievalConfig?.score_threshold,
         reranking_model: multipleRetrievalConfig?.reranking_model,
+        reranking_mode: multipleRetrievalConfig?.reranking_mode,
+        weights: multipleRetrievalConfig?.weights,
       }
     })
     setInputs(newInput)