uncompleted and disabled documents can't create segment with api

Co-authored-by: crazywoola <427733928@qq.com>

.github/workflows/translate-i18n-base-on-english.yml

@@ -0,0 +1,52 @@
+name: Check i18n Files and Create PR
+
+on:
+  pull_request:
+    types: [closed]
+    branches: [main]
+
+jobs:
+  check-and-update:
+    if: github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: web
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check for file changes in i18n/en-US
+        id: check_files
+        run: |
+          changed_files=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }} -- 'i18n/en-US/*.ts')
+          echo "Changed files: $changed_files"
+          if [ -n "$changed_files" ]; then
+            echo "FILES_CHANGED=true" >> $GITHUB_ENV
+          else
+            echo "FILES_CHANGED=false" >> $GITHUB_ENV
+          fi
+
+      - name: Set up Node.js
+        if: env.FILES_CHANGED == 'true'
+        uses: actions/setup-node@v2
+        with:
+          node-version: 'lts/*'
+
+      - name: Install dependencies
+        if: env.FILES_CHANGED == 'true'
+        run: yarn install --frozen-lockfile
+
+      - name: Run npm script
+        if: env.FILES_CHANGED == 'true'
+        run: npm run auto-gen-i18n
+
+      - name: Create Pull Request
+        if: env.FILES_CHANGED == 'true'
+        uses: peter-evans/create-pull-request@v6
+        with:
+          commit-message: Update i18n files based on en-US changes
+          title: 'chore: translate i18n files'
+          body: This PR was automatically created to update i18n files based on changes in en-US locale.
+          branch: chore/automated-i18n-updates

CONTRIBUTING.md

@@ -8,7 +8,7 @@ In terms of licensing, please take a minute to read our short [License and Contr
 
 ## Before you jump in
 
-[Find](https://github.com/langgenius/dify/issues?q=is:issue+is:closed) an existing issue, or [open](https://github.com/langgenius/dify/issues/new/choose) a new one. We categorize issues into 2 types:
+[Find](https://github.com/langgenius/dify/issues?q=is:issue+is:open) an existing issue, or [open](https://github.com/langgenius/dify/issues/new/choose) a new one. We categorize issues into 2 types:
 
 ### Feature requests:
 

CONTRIBUTING_CN.md

@@ -8,7 +8,7 @@
 
 ## 在开始之前
 
-[查找](https://github.com/langgenius/dify/issues?q=is:issue+is:closed)现有问题，或 [创建](https://github.com/langgenius/dify/issues/new/choose) 一个新问题。我们将问题分为两类：
+[查找](https://github.com/langgenius/dify/issues?q=is:issue+is:open)现有问题，或 [创建](https://github.com/langgenius/dify/issues/new/choose) 一个新问题。我们将问题分为两类：
 
 ### 功能请求：
 

CONTRIBUTING_JA.md

@@ -10,7 +10,7 @@ Dify にコントリビュートしたいとお考えなのですね。それは
 
 ## 飛び込む前に
 
-[既存の Issue](https://github.com/langgenius/dify/issues?q=is:issue+is:closed) を探すか、[新しい Issue](https://github.com/langgenius/dify/issues/new/choose) を作成してください。私たちは Issue を 2 つのタイプに分類しています。
+[既存の Issue](https://github.com/langgenius/dify/issues?q=is:issue+is:open) を探すか、[新しい Issue](https://github.com/langgenius/dify/issues/new/choose) を作成してください。私たちは Issue を 2 つのタイプに分類しています。
 
 ### 機能リクエスト
 

CONTRIBUTING_VI.md

@@ -8,7 +8,7 @@ Về vấn đề cấp phép, xin vui lòng dành chút thời gian đọc qua [
 
 ## Trước khi bắt đầu
 
-[Tìm kiếm](https://github.com/langgenius/dify/issues?q=is:issue+is:closed) một vấn đề hiện có, hoặc [tạo mới](https://github.com/langgenius/dify/issues/new/choose) một vấn đề. Chúng tôi phân loại các vấn đề thành 2 loại:
+[Tìm kiếm](https://github.com/langgenius/dify/issues?q=is:issue+is:open) một vấn đề hiện có, hoặc [tạo mới](https://github.com/langgenius/dify/issues/new/choose) một vấn đề. Chúng tôi phân loại các vấn đề thành 2 loại:
 
 ### Yêu cầu tính năng:
 

api/.env.example

@@ -60,7 +60,8 @@ ALIYUN_OSS_SECRET_KEY=your-secret-key
 ALIYUN_OSS_ENDPOINT=your-endpoint
 ALIYUN_OSS_AUTH_VERSION=v1
 ALIYUN_OSS_REGION=your-region
-
+# Don't start with '/'. OSS doesn't support leading slash in object names.
+ALIYUN_OSS_PATH=your-path
 # Google Storage configuration
 GOOGLE_STORAGE_BUCKET_NAME=yout-bucket-name
 GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64=your-google-service-account-json-base64-string

api/Dockerfile

@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.2-1 libldap-2.5-0=2.5.18+dfsg-2 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
+    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.2-2 libldap-2.5-0=2.5.18+dfsg-3 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 

api/commands.py

@@ -559,8 +559,9 @@ def add_qdrant_doc_id_index(field: str):
 
 @click.command("create-tenant", help="Create account and tenant.")
 @click.option("--email", prompt=True, help="The email address of the tenant account.")
+@click.option("--name", prompt=True, help="The workspace name of the tenant account.")
 @click.option("--language", prompt=True, help="Account language, default: en-US.")
-def create_tenant(email: str, language: Optional[str] = None):
+def create_tenant(email: str, language: Optional[str] = None, name: Optional[str] = None):
     """
     Create tenant account
     """
@@ -580,13 +581,15 @@ def create_tenant(email: str, language: Optional[str] = None):
     if language not in languages:
         language = "en-US"
 
+    name = name.strip()
+
     # generate random password
     new_password = secrets.token_urlsafe(16)
 
     # register account
     account = RegisterService.register(email=email, name=account_name, password=new_password, language=language)
 
-    TenantService.create_owner_tenant_if_not_exist(account)
+    TenantService.create_owner_tenant_if_not_exist(account, name)
 
     click.echo(
         click.style(

api/configs/feature/__init__.py

@@ -1,6 +1,6 @@
-from typing import Optional
+from typing import Annotated, Optional
 
-from pydantic import AliasChoices, Field, NegativeInt, NonNegativeInt, PositiveInt, computed_field
+from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
 
 from configs.feature.hosted_service import HostedServiceConfig
@@ -45,7 +45,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
     Code Execution Sandbox configs
     """
 
-    CODE_EXECUTION_ENDPOINT: str = Field(
+    CODE_EXECUTION_ENDPOINT: HttpUrl = Field(
         description="endpoint URL of code execution servcie",
         default="http://sandbox:8194",
     )
@@ -55,6 +55,21 @@ class CodeExecutionSandboxConfig(BaseSettings):
         default="dify-sandbox",
     )
 
+    CODE_EXECUTION_CONNECT_TIMEOUT: Optional[float] = Field(
+        description="connect timeout in seconds for code execution request",
+        default=10.0,
+    )
+
+    CODE_EXECUTION_READ_TIMEOUT: Optional[float] = Field(
+        description="read timeout in seconds for code execution request",
+        default=60.0,
+    )
+
+    CODE_EXECUTION_WRITE_TIMEOUT: Optional[float] = Field(
+        description="write timeout in seconds for code execution request",
+        default=10.0,
+    )
+
     CODE_MAX_NUMBER: PositiveInt = Field(
         description="max depth for code execution",
         default=9223372036854775807,
@@ -202,20 +217,17 @@ class HttpConfig(BaseSettings):
     def WEB_API_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
-    HTTP_REQUEST_MAX_CONNECT_TIMEOUT: NonNegativeInt = Field(
-        description="",
-        default=300,
-    )
+    HTTP_REQUEST_MAX_CONNECT_TIMEOUT: Annotated[
+        PositiveInt, Field(ge=10, description="connect timeout in seconds for HTTP request")
+    ] = 10
 
-    HTTP_REQUEST_MAX_READ_TIMEOUT: NonNegativeInt = Field(
-        description="",
-        default=600,
-    )
+    HTTP_REQUEST_MAX_READ_TIMEOUT: Annotated[
+        PositiveInt, Field(ge=60, description="read timeout in seconds for HTTP request")
+    ] = 60
 
-    HTTP_REQUEST_MAX_WRITE_TIMEOUT: NonNegativeInt = Field(
-        description="",
-        default=600,
-    )
+    HTTP_REQUEST_MAX_WRITE_TIMEOUT: Annotated[
+        PositiveInt, Field(ge=10, description="read timeout in seconds for HTTP request")
+    ] = 20
 
     HTTP_REQUEST_NODE_MAX_BINARY_SIZE: PositiveInt = Field(
         description="",

api/configs/middleware/__init__.py

@@ -13,6 +13,7 @@ from configs.middleware.storage.oci_storage_config import OCIStorageConfig
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
 from configs.middleware.vdb.chroma_config import ChromaConfig
+from configs.middleware.vdb.elasticsearch_config import ElasticsearchConfig
 from configs.middleware.vdb.milvus_config import MilvusConfig
 from configs.middleware.vdb.myscale_config import MyScaleConfig
 from configs.middleware.vdb.opensearch_config import OpenSearchConfig
@@ -200,5 +201,6 @@ class MiddlewareConfig(
     TencentVectorDBConfig,
     TiDBVectorConfig,
     WeaviateConfig,
+    ElasticsearchConfig,
 ):
     pass

api/configs/middleware/storage/aliyun_oss_storage_config.py

@@ -38,3 +38,8 @@ class AliyunOSSStorageConfig(BaseSettings):
         description="Aliyun OSS authentication version",
         default=None,
     )
+
+    ALIYUN_OSS_PATH: Optional[str] = Field(
+        description="Aliyun OSS path",
+        default=None,
+    )

api/configs/middleware/vdb/elasticsearch_config.py

@@ -0,0 +1,30 @@
+from typing import Optional
+
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class ElasticsearchConfig(BaseSettings):
+    """
+    Elasticsearch configs
+    """
+
+    ELASTICSEARCH_HOST: Optional[str] = Field(
+        description="Elasticsearch host",
+        default="127.0.0.1",
+    )
+
+    ELASTICSEARCH_PORT: PositiveInt = Field(
+        description="Elasticsearch port",
+        default=9200,
+    )
+
+    ELASTICSEARCH_USERNAME: Optional[str] = Field(
+        description="Elasticsearch username",
+        default="elastic",
+    )
+
+    ELASTICSEARCH_PASSWORD: Optional[str] = Field(
+        description="Elasticsearch password",
+        default="elastic",
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.7.2",
+        default="0.7.3",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/app/app.py

@@ -174,6 +174,7 @@ class AppApi(Resource):
         parser.add_argument("icon", type=str, location="json")
         parser.add_argument("icon_background", type=str, location="json")
         parser.add_argument("max_active_requests", type=int, location="json")
+        parser.add_argument("use_icon_as_answer_icon", type=bool, location="json")
         args = parser.parse_args()
 
         app_service = AppService()

api/controllers/console/app/conversation.py

@@ -173,21 +173,18 @@ class ChatConversationApi(Resource):
 
         if args["keyword"]:
             keyword_filter = "%{}%".format(args["keyword"])
-            query = (
-                query.join(
-                    Message,
-                    Message.conversation_id == Conversation.id,
-                )
-                .join(subquery, subquery.c.conversation_id == Conversation.id)
-                .filter(
-                    or_(
-                        Message.query.ilike(keyword_filter),
-                        Message.answer.ilike(keyword_filter),
-                        Conversation.name.ilike(keyword_filter),
-                        Conversation.introduction.ilike(keyword_filter),
-                        subquery.c.from_end_user_session_id.ilike(keyword_filter),
-                    ),
-                )
+            message_subquery = (
+                db.session.query(Message.conversation_id)
+                .filter(or_(Message.query.ilike(keyword_filter), Message.answer.ilike(keyword_filter)))
+                .subquery()
+            )
+            query = query.join(subquery, subquery.c.conversation_id == Conversation.id).filter(
+                or_(
+                    Conversation.id.in_(message_subquery),
+                    Conversation.name.ilike(keyword_filter),
+                    Conversation.introduction.ilike(keyword_filter),
+                    subquery.c.from_end_user_session_id.ilike(keyword_filter),
+                ),
             )
 
         account = current_user

api/controllers/console/app/model_config.py

@@ -32,6 +32,8 @@ class ModelConfigResource(Resource):
 
         new_app_model_config = AppModelConfig(
             app_id=app_model.id,
+            created_by=current_user.id,
+            updated_by=current_user.id,
         )
         new_app_model_config = new_app_model_config.from_model_config_dict(model_configuration)
 

api/controllers/console/app/site.py

@@ -1,3 +1,5 @@
+from datetime import datetime, timezone
+
 from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden, NotFound
@@ -32,6 +34,7 @@ def parse_app_site_args():
     )
     parser.add_argument("prompt_public", type=bool, required=False, location="json")
     parser.add_argument("show_workflow_steps", type=bool, required=False, location="json")
+    parser.add_argument("use_icon_as_answer_icon", type=bool, required=False, location="json")
     return parser.parse_args()
 
 
@@ -66,11 +69,14 @@ class AppSite(Resource):
             "customize_token_strategy",
             "prompt_public",
             "show_workflow_steps",
+            "use_icon_as_answer_icon",
         ]:
             value = args.get(attr_name)
             if value is not None:
                 setattr(site, attr_name, value)
 
+        site.updated_by = current_user.id
+        site.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         return site
@@ -93,6 +99,8 @@ class AppSiteAccessTokenReset(Resource):
             raise NotFound
 
         site.code = Site.generate_code(16)
+        site.updated_by = current_user.id
+        site.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         return site

api/controllers/console/app/statistic.py

@@ -16,6 +16,60 @@ from libs.login import login_required
 from models.model import AppMode
 
 
+class DailyMessageStatistic(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model
+    def get(self, app_model):
+        account = current_user
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("start", type=datetime_string("%Y-%m-%d %H:%M"), location="args")
+        parser.add_argument("end", type=datetime_string("%Y-%m-%d %H:%M"), location="args")
+        args = parser.parse_args()
+
+        sql_query = """
+        SELECT date(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date, count(*) AS message_count
+            FROM messages where app_id = :app_id 
+        """
+        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
+
+        timezone = pytz.timezone(account.timezone)
+        utc_timezone = pytz.utc
+
+        if args["start"]:
+            start_datetime = datetime.strptime(args["start"], "%Y-%m-%d %H:%M")
+            start_datetime = start_datetime.replace(second=0)
+
+            start_datetime_timezone = timezone.localize(start_datetime)
+            start_datetime_utc = start_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += " and created_at >= :start"
+            arg_dict["start"] = start_datetime_utc
+
+        if args["end"]:
+            end_datetime = datetime.strptime(args["end"], "%Y-%m-%d %H:%M")
+            end_datetime = end_datetime.replace(second=0)
+
+            end_datetime_timezone = timezone.localize(end_datetime)
+            end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += " and created_at < :end"
+            arg_dict["end"] = end_datetime_utc
+
+        sql_query += " GROUP BY date order by date"
+
+        response_data = []
+
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+            for i in rs:
+                response_data.append({"date": str(i.date), "message_count": i.message_count})
+
+        return jsonify({"data": response_data})
+
+
 class DailyConversationStatistic(Resource):
     @setup_required
     @login_required
@@ -419,6 +473,7 @@ WHERE app_id = :app_id"""
         return jsonify({"data": response_data})
 
 
+api.add_resource(DailyMessageStatistic, "/apps/<uuid:app_id>/statistics/daily-messages")
 api.add_resource(DailyConversationStatistic, "/apps/<uuid:app_id>/statistics/daily-conversations")
 api.add_resource(DailyTerminalsStatistic, "/apps/<uuid:app_id>/statistics/daily-end-users")
 api.add_resource(DailyTokenCostStatistic, "/apps/<uuid:app_id>/statistics/token-costs")

api/controllers/console/datasets/datasets.py

@@ -122,6 +122,7 @@ class DatasetListApi(Resource):
                 name=args["name"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
+                permission=DatasetPermissionEnum.ONLY_ME,
             )
         except services.errors.dataset.DatasetNameDuplicateError:
             raise DatasetNameDuplicateError()

api/controllers/console/datasets/datasets_document.py

@@ -599,6 +599,7 @@ class DocumentDetailApi(DocumentResource):
                 "hit_count": document.hit_count,
                 "display_status": document.display_status,
                 "doc_form": document.doc_form,
+                "doc_language": document.doc_language,
             }
         else:
             process_rules = DatasetService.get_process_rules(dataset_id)
@@ -631,6 +632,7 @@ class DocumentDetailApi(DocumentResource):
                 "hit_count": document.hit_count,
                 "display_status": document.display_status,
                 "doc_form": document.doc_form,
+                "doc_language": document.doc_language,
             }
 
         return response, 200

api/controllers/console/datasets/file.py

@@ -39,7 +39,7 @@ class FileApi(Resource):
     @login_required
     @account_initialization_required
     @marshal_with(file_fields)
-    @cloud_edition_billing_resource_check(resource="documents")
+    @cloud_edition_billing_resource_check("documents")
     def post(self):
         # get file from request
         file = request.files["file"]

api/controllers/console/explore/installed_app.py

@@ -35,6 +35,7 @@ class InstalledAppsListApi(Resource):
                 "uninstallable": current_tenant_id == installed_app.app_owner_tenant_id,
             }
             for installed_app in installed_apps
+            if installed_app.app is not None
         ]
         installed_apps.sort(
             key=lambda app: (

api/controllers/console/wraps.py

@@ -46,9 +46,7 @@ def only_edition_self_hosted(view):
     return decorated
 
 
-def cloud_edition_billing_resource_check(
-    resource: str, error_msg: str = "You have reached the limit of your subscription."
-):
+def cloud_edition_billing_resource_check(resource: str):
     def interceptor(view):
         @wraps(view)
         def decorated(*args, **kwargs):
@@ -60,22 +58,22 @@ def cloud_edition_billing_resource_check(
                 documents_upload_quota = features.documents_upload_quota
                 annotation_quota_limit = features.annotation_quota_limit
                 if resource == "members" and 0 < members.limit <= members.size:
-                    abort(403, error_msg)
+                    abort(403, "The number of members has reached the limit of your subscription.")
                 elif resource == "apps" and 0 < apps.limit <= apps.size:
-                    abort(403, error_msg)
+                    abort(403, "The number of apps has reached the limit of your subscription.")
                 elif resource == "vector_space" and 0 < vector_space.limit <= vector_space.size:
-                    abort(403, error_msg)
+                    abort(403, "The capacity of the vector space has reached the limit of your subscription.")
                 elif resource == "documents" and 0 < documents_upload_quota.limit <= documents_upload_quota.size:
                     # The api of file upload is used in the multiple places, so we need to check the source of the request from datasets
                     source = request.args.get("source")
                     if source == "datasets":
-                        abort(403, error_msg)
+                        abort(403, "The number of documents has reached the limit of your subscription.")
                     else:
                         return view(*args, **kwargs)
                 elif resource == "workspace_custom" and not features.can_replace_logo:
-                    abort(403, error_msg)
+                    abort(403, "The workspace custom feature has reached the limit of your subscription.")
                 elif resource == "annotation" and 0 < annotation_quota_limit.limit < annotation_quota_limit.size:
-                    abort(403, error_msg)
+                    abort(403, "The annotation quota has reached the limit of your subscription.")
                 else:
                     return view(*args, **kwargs)
 
@@ -86,10 +84,7 @@ def cloud_edition_billing_resource_check(
     return interceptor
 
 
-def cloud_edition_billing_knowledge_limit_check(
-    resource: str,
-    error_msg: str = "To unlock this feature and elevate your Dify experience, please upgrade to a paid plan.",
-):
+def cloud_edition_billing_knowledge_limit_check(resource: str):
     def interceptor(view):
         @wraps(view)
         def decorated(*args, **kwargs):
@@ -97,7 +92,10 @@ def cloud_edition_billing_knowledge_limit_check(
             if features.billing.enabled:
                 if resource == "add_segment":
                     if features.billing.subscription.plan == "sandbox":
-                        abort(403, error_msg)
+                        abort(
+                            403,
+                            "To unlock this feature and elevate your Dify experience, please upgrade to a paid plan.",
+                        )
                 else:
                     return view(*args, **kwargs)
 

api/controllers/service_api/dataset/segment.py

@@ -36,6 +36,10 @@ class SegmentApi(DatasetApiResource):
         document = DocumentService.get_document(dataset.id, document_id)
         if not document:
             raise NotFound("Document not found.")
+        if document.indexing_status != "completed":
+            raise NotFound("Document is already completed.")
+        if not document.enabled:
+            raise NotFound("Document is disabled.")
         # check embedding model setting
         if dataset.indexing_technique == "high_quality":
             try:

api/controllers/service_api/wraps.py

@@ -83,9 +83,7 @@ def validate_app_token(view: Optional[Callable] = None, *, fetch_user_arg: Optio
         return decorator(view)
 
 
-def cloud_edition_billing_resource_check(
-    resource: str, api_token_type: str, error_msg: str = "You have reached the limit of your subscription."
-):
+def cloud_edition_billing_resource_check(resource: str, api_token_type: str):
     def interceptor(view):
         def decorated(*args, **kwargs):
             api_token = validate_and_get_api_token(api_token_type)
@@ -98,13 +96,13 @@ def cloud_edition_billing_resource_check(
                 documents_upload_quota = features.documents_upload_quota
 
                 if resource == "members" and 0 < members.limit <= members.size:
-                    raise Forbidden(error_msg)
+                    raise Forbidden("The number of members has reached the limit of your subscription.")
                 elif resource == "apps" and 0 < apps.limit <= apps.size:
-                    raise Forbidden(error_msg)
+                    raise Forbidden("The number of apps has reached the limit of your subscription.")
                 elif resource == "vector_space" and 0 < vector_space.limit <= vector_space.size:
-                    raise Forbidden(error_msg)
+                    raise Forbidden("The capacity of the vector space has reached the limit of your subscription.")
                 elif resource == "documents" and 0 < documents_upload_quota.limit <= documents_upload_quota.size:
-                    raise Forbidden(error_msg)
+                    raise Forbidden("The number of documents has reached the limit of your subscription.")
                 else:
                     return view(*args, **kwargs)
 
@@ -115,11 +113,7 @@ def cloud_edition_billing_resource_check(
     return interceptor
 
 
-def cloud_edition_billing_knowledge_limit_check(
-    resource: str,
-    api_token_type: str,
-    error_msg: str = "To unlock this feature and elevate your Dify experience, please upgrade to a paid plan.",
-):
+def cloud_edition_billing_knowledge_limit_check(resource: str, api_token_type: str):
     def interceptor(view):
         @wraps(view)
         def decorated(*args, **kwargs):
@@ -128,7 +122,9 @@ def cloud_edition_billing_knowledge_limit_check(
             if features.billing.enabled:
                 if resource == "add_segment":
                     if features.billing.subscription.plan == "sandbox":
-                        raise Forbidden(error_msg)
+                        raise Forbidden(
+                            "To unlock this feature and elevate your Dify experience, please upgrade to a paid plan."
+                        )
                 else:
                     return view(*args, **kwargs)
 

api/controllers/web/site.py

@@ -39,6 +39,7 @@ class AppSiteApi(WebApiResource):
         "default_language": fields.String,
         "prompt_public": fields.Boolean,
         "show_workflow_steps": fields.Boolean,
+        "use_icon_as_answer_icon": fields.Boolean,
     }
 
     app_fields = {

api/core/app/app_config/easy_ui_based_app/dataset/manager.py

@@ -93,7 +93,7 @@ class DatasetConfigManager:
                     reranking_model=dataset_configs.get('reranking_model'),
                     weights=dataset_configs.get('weights'),
                     reranking_enabled=dataset_configs.get('reranking_enabled', True),
-                    rerank_mode=dataset_configs.get('rerank_mode', 'reranking_model'),
+                    rerank_mode=dataset_configs.get('reranking_mode', 'reranking_model'),
                 )
             )
 

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

@@ -4,7 +4,7 @@ import os
 import threading
 import uuid
 from collections.abc import Generator
-from typing import Union
+from typing import Literal, Union, overload
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -39,6 +39,26 @@ logger = logging.getLogger(__name__)
 
 
 class AdvancedChatAppGenerator(MessageBasedAppGenerator):
+    @overload
+    def generate(
+        self, app_model: App,
+        workflow: Workflow,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[True] = True,
+    ) -> Generator[str, None, None]: ...
+
+    @overload
+    def generate(
+        self, app_model: App,
+        workflow: Workflow,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[False] = False,
+    ) -> dict: ...
+
     def generate(
         self, app_model: App,
         workflow: Workflow,

api/core/app/apps/agent_chat/app_generator.py

@@ -3,7 +3,7 @@ import os
 import threading
 import uuid
 from collections.abc import Generator
-from typing import Any, Union
+from typing import Any, Literal, Union, overload
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -28,6 +28,24 @@ logger = logging.getLogger(__name__)
 
 
 class AgentChatAppGenerator(MessageBasedAppGenerator):
+    @overload
+    def generate(
+        self, app_model: App,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[True] = True,
+    ) -> Generator[dict, None, None]: ...
+
+    @overload
+    def generate(
+        self, app_model: App,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[False] = False,
+    ) -> dict: ...
+
     def generate(self, app_model: App,
                  user: Union[Account, EndUser],
                  args: Any,

api/core/app/apps/chat/app_generator.py

@@ -3,7 +3,7 @@ import os
 import threading
 import uuid
 from collections.abc import Generator
-from typing import Any, Union
+from typing import Any, Literal, Union, overload
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -28,13 +28,31 @@ logger = logging.getLogger(__name__)
 
 
 class ChatAppGenerator(MessageBasedAppGenerator):
+    @overload
+    def generate(
+        self, app_model: App,
+        user: Union[Account, EndUser],
+        args: Any,
+        invoke_from: InvokeFrom,
+        stream: Literal[True] = True,
+    ) -> Generator[str, None, None]: ...
+
+    @overload
+    def generate(
+        self, app_model: App,
+        user: Union[Account, EndUser],
+        args: Any,
+        invoke_from: InvokeFrom,
+        stream: Literal[False] = False,
+    ) -> dict: ...
+
     def generate(
         self, app_model: App,
         user: Union[Account, EndUser],
         args: Any,
         invoke_from: InvokeFrom,
         stream: bool = True,
-    ) -> Union[dict, Generator[dict, None, None]]:
+    ) -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
 

api/core/app/apps/completion/app_generator.py

@@ -3,7 +3,7 @@ import os
 import threading
 import uuid
 from collections.abc import Generator
-from typing import Any, Union
+from typing import Any, Literal, Union, overload
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -30,12 +30,30 @@ logger = logging.getLogger(__name__)
 
 
 class CompletionAppGenerator(MessageBasedAppGenerator):
+    @overload
+    def generate(
+        self, app_model: App,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[True] = True,
+    ) -> Generator[str, None, None]: ...
+
+    @overload
+    def generate(
+        self, app_model: App,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[False] = False,
+    ) -> dict: ...
+
     def generate(self, app_model: App,
                  user: Union[Account, EndUser],
                  args: Any,
                  invoke_from: InvokeFrom,
                  stream: bool = True) \
-            -> Union[dict, Generator[dict, None, None]]:
+            -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
 
@@ -203,7 +221,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
                                 user: Union[Account, EndUser],
                                 invoke_from: InvokeFrom,
                                 stream: bool = True) \
-            -> Union[dict, Generator[dict, None, None]]:
+            -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
 

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

@@ -4,7 +4,7 @@ import os
 import threading
 import uuid
 from collections.abc import Generator
-from typing import Union
+from typing import Literal, Union, overload
 
 from flask import Flask, current_app
 from pydantic import ValidationError
@@ -32,6 +32,26 @@ logger = logging.getLogger(__name__)
 
 
 class WorkflowAppGenerator(BaseAppGenerator):
+    @overload
+    def generate(
+        self, app_model: App,
+        workflow: Workflow,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[True] = True,
+    ) -> Generator[str, None, None]: ...
+
+    @overload
+    def generate(
+        self, app_model: App,
+        workflow: Workflow,
+        user: Union[Account, EndUser],
+        args: dict,
+        invoke_from: InvokeFrom,
+        stream: Literal[False] = False,
+    ) -> dict: ...
+
     def generate(
         self, app_model: App,
         workflow: Workflow,
@@ -107,7 +127,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
         application_generate_entity: WorkflowAppGenerateEntity,
         invoke_from: InvokeFrom,
         stream: bool = True,
-    ) -> Union[dict, Generator[dict, None, None]]:
+    ) -> Union[dict, Generator[str, None, None]]:
         """
         Generate App response.
 

api/core/helper/code_executor/code_executor.py

@@ -15,12 +15,6 @@ from core.helper.code_executor.template_transformer import TemplateTransformer
 
 logger = logging.getLogger(__name__)
 
-# Code Executor
-CODE_EXECUTION_ENDPOINT = dify_config.CODE_EXECUTION_ENDPOINT
-CODE_EXECUTION_API_KEY = dify_config.CODE_EXECUTION_API_KEY
-
-CODE_EXECUTION_TIMEOUT = Timeout(connect=10, write=10, read=60, pool=None)
-
 class CodeExecutionException(Exception):
     pass
 
@@ -71,10 +65,10 @@ class CodeExecutor:
         :param code: code
         :return:
         """
-        url = URL(CODE_EXECUTION_ENDPOINT) / 'v1' / 'sandbox' / 'run'
+        url = URL(str(dify_config.CODE_EXECUTION_ENDPOINT)) / 'v1' / 'sandbox' / 'run'
 
         headers = {
-            'X-Api-Key': CODE_EXECUTION_API_KEY
+            'X-Api-Key': dify_config.CODE_EXECUTION_API_KEY
         }
 
         data = {
@@ -85,7 +79,12 @@ class CodeExecutor:
         }
 
         try:
-            response = post(str(url), json=data, headers=headers, timeout=CODE_EXECUTION_TIMEOUT)
+            response = post(str(url), json=data, headers=headers,
+                            timeout=Timeout(
+                                connect=dify_config.CODE_EXECUTION_CONNECT_TIMEOUT,
+                                read=dify_config.CODE_EXECUTION_READ_TIMEOUT,
+                                write=dify_config.CODE_EXECUTION_WRITE_TIMEOUT,
+                                pool=None))
             if response.status_code == 503:
                 raise CodeExecutionException('Code execution service is unavailable')
             elif response.status_code != 200:
@@ -96,7 +95,7 @@ class CodeExecutor:
             raise CodeExecutionException('Failed to execute code, which is likely a network issue,'
                                          ' please check if the sandbox service is running.'
                                          f' ( Error: {str(e)} )')
-        
+
         try:
             response = response.json()
         except:
@@ -104,12 +103,12 @@ class CodeExecutor:
 
         if (code := response.get('code')) != 0:
             raise CodeExecutionException(f"Got error code: {code}. Got error msg: {response.get('message')}")
-        
+
         response = CodeExecutionResponse(**response)
-        
+
         if response.data.error:
             raise CodeExecutionException(response.data.error)
-        
+
         return response.data.stdout or ''
 
     @classmethod
@@ -133,4 +132,3 @@ class CodeExecutor:
             raise e
 
         return template_transformer.transform_response(response)
-    

api/core/indexing_runner.py

@@ -720,6 +720,7 @@ class IndexingRunner:
                 document_ids = [document.metadata['doc_id'] for document in documents]
                 db.session.query(DocumentSegment).filter(
                     DocumentSegment.document_id == document_id,
+                    DocumentSegment.dataset_id == dataset_id,
                     DocumentSegment.index_node_id.in_(document_ids),
                     DocumentSegment.status == "indexing"
                 ).update({
@@ -751,6 +752,7 @@ class IndexingRunner:
             document_ids = [document.metadata['doc_id'] for document in chunk_documents]
             db.session.query(DocumentSegment).filter(
                 DocumentSegment.document_id == dataset_document.id,
+                DocumentSegment.dataset_id == dataset.id,
                 DocumentSegment.index_node_id.in_(document_ids),
                 DocumentSegment.status == "indexing"
             ).update({

api/core/model_runtime/model_providers/azure_ai_studio/azure_ai_studio.py

@@ -0,0 +1,17 @@
+import logging
+
+from core.model_runtime.model_providers.__base.model_provider import ModelProvider
+
+logger = logging.getLogger(__name__)
+
+
+class AzureAIStudioProvider(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`.
+        """
+        pass

api/core/model_runtime/model_providers/azure_ai_studio/azure_ai_studio.yaml

@@ -0,0 +1,65 @@
+provider: azure_ai_studio
+label:
+  zh_Hans: Azure AI Studio
+  en_US: Azure AI Studio
+icon_small:
+  en_US: icon_s_en.png
+icon_large:
+  en_US: icon_l_en.png
+description:
+  en_US: Azure AI Studio
+  zh_Hans: Azure AI Studio
+background: "#93c5fd"
+help:
+  title:
+    en_US: How to deploy customized model on Azure AI Studio
+    zh_Hans: 如何在Azure AI Studio上的私有化部署的模型
+  url:
+    en_US: https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models
+    zh_Hans: https://learn.microsoft.com/zh-cn/azure/ai-studio/how-to/deploy-models
+supported_model_types:
+  - llm
+  - rerank
+configurate_methods:
+  - customizable-model
+model_credential_schema:
+  model:
+    label:
+      en_US: Model Name
+      zh_Hans: 模型名称
+    placeholder:
+      en_US: Enter your model name
+      zh_Hans: 输入模型名称
+  credential_form_schemas:
+    - variable: endpoint
+      label:
+        en_US: Azure AI Studio Endpoint
+      type: text-input
+      required: true
+      placeholder:
+        zh_Hans: 请输入你的Azure AI Studio推理端点
+        en_US: 'Enter your API Endpoint, eg: https://example.com'
+    - variable: api_key
+      required: true
+      label:
+        en_US: API Key
+        zh_Hans: API Key
+      type: secret-input
+      placeholder:
+        en_US: Enter your Azure AI Studio API Key
+        zh_Hans: 在此输入您的 Azure AI Studio API Key
+      show_on:
+        - variable: __model_type
+          value: llm
+    - variable: jwt_token
+      required: true
+      label:
+        en_US: JWT Token
+        zh_Hans: JWT令牌
+      type: secret-input
+      placeholder:
+        en_US: Enter your Azure AI Studio JWT Token
+        zh_Hans: 在此输入您的 Azure AI Studio 推理 API Key
+      show_on:
+        - variable: __model_type
+          value: rerank

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

@@ -0,0 +1,334 @@
+import logging
+from collections.abc import Generator
+from typing import Any, Optional, Union
+
+from azure.ai.inference import ChatCompletionsClient
+from azure.ai.inference.models import StreamingChatCompletionsUpdate
+from azure.core.credentials import AzureKeyCredential
+from azure.core.exceptions import (
+    ClientAuthenticationError,
+    DecodeError,
+    DeserializationError,
+    HttpResponseError,
+    ResourceExistsError,
+    ResourceModifiedError,
+    ResourceNotFoundError,
+    ResourceNotModifiedError,
+    SerializationError,
+    ServiceRequestError,
+    ServiceResponseError,
+)
+
+from core.model_runtime.callbacks.base_callback import Callback
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    PromptMessage,
+    PromptMessageTool,
+)
+from core.model_runtime.entities.model_entities import (
+    AIModelEntity,
+    FetchFrom,
+    I18nObject,
+    ModelType,
+    ParameterRule,
+    ParameterType,
+)
+from core.model_runtime.errors.invoke import (
+    InvokeAuthorizationError,
+    InvokeBadRequestError,
+    InvokeConnectionError,
+    InvokeError,
+    InvokeServerUnavailableError,
+)
+from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+
+logger = logging.getLogger(__name__)
+
+
+class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
+    """
+    Model class for Azure AI Studio large language model.
+    """
+
+    client: Any = None
+
+    from azure.ai.inference.models import StreamingChatCompletionsUpdate
+
+    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
+        """
+
+        if not self.client:
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("api_key")
+            self.client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))
+
+        messages = [{"role": msg.role.value, "content": msg.content} for msg in prompt_messages]
+
+        payload = {
+            "messages": messages,
+            "max_tokens": model_parameters.get("max_tokens", 4096),
+            "temperature": model_parameters.get("temperature", 0),
+            "top_p": model_parameters.get("top_p", 1),
+            "stream": stream,
+        }
+
+        if stop:
+            payload["stop"] = stop
+
+        if tools:
+            payload["tools"] = [tool.model_dump() for tool in tools]
+
+        try:
+            response = self.client.complete(**payload)
+
+            if stream:
+                return self._handle_stream_response(response, model, prompt_messages)
+            else:
+                return self._handle_non_stream_response(response, model, prompt_messages, credentials)
+        except Exception as e:
+            raise self._transform_invoke_error(e)
+
+    def _handle_stream_response(self, response, model: str, prompt_messages: list[PromptMessage]) -> Generator:
+        for chunk in response:
+            if isinstance(chunk, StreamingChatCompletionsUpdate):
+                if chunk.choices:
+                    delta = chunk.choices[0].delta
+                    if delta.content:
+                        yield LLMResultChunk(
+                            model=model,
+                            prompt_messages=prompt_messages,
+                            delta=LLMResultChunkDelta(
+                                index=0,
+                                message=AssistantPromptMessage(content=delta.content, tool_calls=[]),
+                            ),
+                        )
+
+    def _handle_non_stream_response(
+        self, response, model: str, prompt_messages: list[PromptMessage], credentials: dict
+    ) -> LLMResult:
+        assistant_text = response.choices[0].message.content
+        assistant_prompt_message = AssistantPromptMessage(content=assistant_text)
+        usage = self._calc_response_usage(
+            model, credentials, response.usage.prompt_tokens, response.usage.completion_tokens
+        )
+        result = LLMResult(model=model, prompt_messages=prompt_messages, message=assistant_prompt_message, usage=usage)
+
+        if hasattr(response, "system_fingerprint"):
+            result.system_fingerprint = response.system_fingerprint
+
+        return result
+
+    def _invoke_result_generator(
+        self,
+        model: str,
+        result: Generator,
+        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,
+        callbacks: Optional[list[Callback]] = None,
+    ) -> Generator:
+        """
+        Invoke result generator
+
+        :param result: result generator
+        :return: result generator
+        """
+        callbacks = callbacks or []
+        prompt_message = AssistantPromptMessage(content="")
+        usage = None
+        system_fingerprint = None
+        real_model = model
+
+        try:
+            for chunk in result:
+                if isinstance(chunk, dict):
+                    content = chunk["choices"][0]["message"]["content"]
+                    usage = chunk["usage"]
+                    chunk = LLMResultChunk(
+                        model=model,
+                        prompt_messages=prompt_messages,
+                        delta=LLMResultChunkDelta(
+                            index=0,
+                            message=AssistantPromptMessage(content=content, tool_calls=[]),
+                        ),
+                        system_fingerprint=chunk.get("system_fingerprint"),
+                    )
+
+                yield chunk
+
+                self._trigger_new_chunk_callbacks(
+                    chunk=chunk,
+                    model=model,
+                    credentials=credentials,
+                    prompt_messages=prompt_messages,
+                    model_parameters=model_parameters,
+                    tools=tools,
+                    stop=stop,
+                    stream=stream,
+                    user=user,
+                    callbacks=callbacks,
+                )
+
+                prompt_message.content += chunk.delta.message.content
+                real_model = chunk.model
+                if hasattr(chunk.delta, "usage"):
+                    usage = chunk.delta.usage
+
+                if chunk.system_fingerprint:
+                    system_fingerprint = chunk.system_fingerprint
+        except Exception as e:
+            raise self._transform_invoke_error(e)
+
+        self._trigger_after_invoke_callbacks(
+            model=model,
+            result=LLMResult(
+                model=real_model,
+                prompt_messages=prompt_messages,
+                message=prompt_message,
+                usage=usage if usage else LLMUsage.empty_usage(),
+                system_fingerprint=system_fingerprint,
+            ),
+            credentials=credentials,
+            prompt_messages=prompt_messages,
+            model_parameters=model_parameters,
+            tools=tools,
+            stop=stop,
+            stream=stream,
+            user=user,
+            callbacks=callbacks,
+        )
+
+    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:
+        """
+        # Implement token counting logic here
+        # Might need to use a tokenizer specific to the Azure AI Studio model
+        return 0
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        """
+        Validate model credentials
+
+        :param model: model name
+        :param credentials: model credentials
+        :return:
+        """
+        try:
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("api_key")
+            client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))
+            client.get_model_info()
+        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
+        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
+        """
+        return {
+            InvokeConnectionError: [
+                ServiceRequestError,
+            ],
+            InvokeServerUnavailableError: [
+                ServiceResponseError,
+            ],
+            InvokeAuthorizationError: [
+                ClientAuthenticationError,
+            ],
+            InvokeBadRequestError: [
+                HttpResponseError,
+                DecodeError,
+                ResourceExistsError,
+                ResourceNotFoundError,
+                ResourceModifiedError,
+                ResourceNotModifiedError,
+                SerializationError,
+                DeserializationError,
+            ],
+        }
+
+    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"),
+            ),
+        ]
+
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model),
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_type=ModelType.LLM,
+            features=[],
+            model_properties={},
+            parameter_rules=rules,
+        )
+
+        return entity

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

@@ -0,0 +1,164 @@
+import json
+import logging
+import os
+import ssl
+import urllib.request
+from typing import Optional
+
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, 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
+
+logger = logging.getLogger(__name__)
+
+
+class AzureRerankModel(RerankModel):
+    """
+    Model class for Azure AI Studio rerank model.
+    """
+
+    def _allow_self_signed_https(self, allowed):
+        # bypass the server certificate verification on client side
+        if allowed and not os.environ.get("PYTHONHTTPSVERIFY", "") and getattr(ssl, "_create_unverified_context", None):
+            ssl._create_default_https_context = ssl._create_unverified_context
+
+    def _azure_rerank(self, query_input: str, docs: list[str], endpoint: str, api_key: str):
+        #   self._allow_self_signed_https(True)  # Enable if using self-signed certificate
+
+        data = {"inputs": query_input, "docs": docs}
+
+        body = json.dumps(data).encode("utf-8")
+        headers = {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}
+
+        req = urllib.request.Request(endpoint, body, headers)
+
+        try:
+            with urllib.request.urlopen(req) as response:
+                result = response.read()
+                return json.loads(result)
+        except urllib.error.HTTPError as error:
+            logger.error(f"The request failed with status code: {error.code}")
+            logger.error(error.info())
+            logger.error(error.read().decode("utf8", "ignore"))
+            raise
+
+    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
+        :param user: unique user id
+        :return: rerank result
+        """
+        try:
+            if len(docs) == 0:
+                return RerankResult(model=model, docs=[])
+
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("jwt_token")
+
+            if not endpoint or not api_key:
+                raise ValueError("Azure endpoint and API key must be provided in credentials")
+
+            result = self._azure_rerank(query, docs, endpoint, api_key)
+            logger.info(f"Azure rerank result: {result}")
+
+            rerank_documents = []
+            for idx, (doc, score_dict) in enumerate(zip(docs, result)):
+                score = score_dict["score"]
+                rerank_document = RerankDocument(index=idx, text=doc, score=score)
+
+                if score_threshold is None or score >= score_threshold:
+                    rerank_documents.append(rerank_document)
+
+            rerank_documents.sort(key=lambda x: x.score, reverse=True)
+
+            if top_n:
+                rerank_documents = rerank_documents[:top_n]
+
+            return RerankResult(model=model, docs=rerank_documents)
+
+        except Exception as e:
+            logger.exception(f"Exception in Azure rerank: {e}")
+            raise
+
+    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
+        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
+        """
+        return {
+            InvokeConnectionError: [urllib.error.URLError],
+            InvokeServerUnavailableError: [urllib.error.HTTPError],
+            InvokeRateLimitError: [InvokeRateLimitError],
+            InvokeAuthorizationError: [InvokeAuthorizationError],
+            InvokeBadRequestError: [InvokeBadRequestError, KeyError, ValueError, json.JSONDecodeError],
+        }
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
+        """
+        used to define customizable model schema
+        """
+        entity = AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model),
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_type=ModelType.RERANK,
+            model_properties={},
+            parameter_rules=[],
+        )
+
+        return entity

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

@@ -150,9 +150,9 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
             except json.JSONDecodeError as e:
                 raise CredentialsValidateFailedError('Credentials validation failed: JSON decode error')
 
-            if (completion_type is LLMMode.CHAT and json_result['object'] == ''):
+            if (completion_type is LLMMode.CHAT and json_result.get('object','') == ''):
                 json_result['object'] = 'chat.completion'
-            elif (completion_type is LLMMode.COMPLETION and json_result['object'] == ''):
+            elif (completion_type is LLMMode.COMPLETION and json_result.get('object','') == ''):
                 json_result['object'] = 'text_completion'
 
             if (completion_type is LLMMode.CHAT

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

@@ -137,9 +137,19 @@ class TongyiTextEmbeddingModel(_CommonTongyi, TextEmbeddingModel):
                 input=text,
                 text_type="document",
             )
-            data = response.output["embeddings"][0]
-            embeddings.append(data["embedding"])
-            embedding_used_tokens += response.usage["total_tokens"]
+            if response.output and "embeddings" in response.output and response.output["embeddings"]:
+                data = response.output["embeddings"][0]
+                if "embedding" in data:
+                    embeddings.append(data["embedding"])
+                else:
+                    raise ValueError("Embedding data is missing in the response.")
+            else:
+                raise ValueError("Response output is missing or does not contain embeddings.")
+            
+            if response.usage and "total_tokens" in response.usage:
+                embedding_used_tokens += response.usage["total_tokens"]
+            else:
+                raise ValueError("Response usage is missing or does not contain total tokens.")
 
         return [list(map(float, e)) for e in embeddings], embedding_used_tokens
 

api/core/model_runtime/model_providers/volcengine_maas/client.py

@@ -32,6 +32,9 @@ from core.model_runtime.entities.message_entities import (
     UserPromptMessage,
 )
 
+DEFAULT_V2_ENDPOINT = "maas-api.ml-platform-cn-beijing.volces.com"
+DEFAULT_V3_ENDPOINT = "https://ark.cn-beijing.volces.com/api/v3"
+
 
 class ArkClientV3:
     endpoint_id: Optional[str] = None
@@ -43,16 +46,24 @@ class ArkClientV3:
 
     @staticmethod
     def is_legacy(credentials: dict) -> bool:
+        # match default v2 endpoint
         if ArkClientV3.is_compatible_with_legacy(credentials):
             return False
-        sdk_version = credentials.get("sdk_version", "v2")
-        return sdk_version != "v3"
+        # match default v3 endpoint
+        if credentials.get("api_endpoint_host") == DEFAULT_V3_ENDPOINT:
+            return False
+        # only v3 support api_key
+        if credentials.get("auth_method") == "api_key":
+            return False
+        # these cases are considered as sdk v2
+        # - modified default v2 endpoint
+        # - modified default v3 endpoint and auth without api_key
+        return True
 
     @staticmethod
     def is_compatible_with_legacy(credentials: dict) -> bool:
-        sdk_version = credentials.get("sdk_version")
         endpoint = credentials.get("api_endpoint_host")
-        return sdk_version is None and endpoint == "maas-api.ml-platform-cn-beijing.volces.com"
+        return endpoint == DEFAULT_V2_ENDPOINT
 
     @classmethod
     def from_credentials(cls, credentials):
@@ -60,11 +71,24 @@ class ArkClientV3:
         args = {
             "base_url": credentials['api_endpoint_host'],
             "region": credentials['volc_region'],
-            "ak": credentials['volc_access_key_id'],
-            "sk": credentials['volc_secret_access_key'],
         }
+        if credentials.get("auth_method") == "api_key":
+            args = {
+                **args,
+                "api_key": credentials['volc_api_key'],
+            }
+        else:
+            args = {
+                **args,
+                "ak": credentials['volc_access_key_id'],
+                "sk": credentials['volc_secret_access_key'],
+            }
+
         if cls.is_compatible_with_legacy(credentials):
-            args["base_url"] = "https://ark.cn-beijing.volces.com/api/v3"
+            args = {
+                **args,
+                "base_url": DEFAULT_V3_ENDPOINT
+            }
 
         client = ArkClientV3(
             **args

api/core/model_runtime/model_providers/volcengine_maas/llm/models.py

@@ -38,7 +38,7 @@ configs: dict[str, ModelConfig] = {
     ),
     'Doubao-lite-128k': ModelConfig(
         properties=ModelProperties(context_size=131072, max_tokens=4096, mode=LLMMode.CHAT),
-        features=[ModelFeature.TOOL_CALL]
+        features=[]
     ),
     'Skylark2-pro-4k': ModelConfig(
         properties=ModelProperties(context_size=4096, max_tokens=4096, mode=LLMMode.CHAT),
@@ -54,23 +54,23 @@ configs: dict[str, ModelConfig] = {
     ),
     'Moonshot-v1-8k': ModelConfig(
         properties=ModelProperties(context_size=8192, max_tokens=4096, mode=LLMMode.CHAT),
-        features=[]
+        features=[ModelFeature.TOOL_CALL]
     ),
     'Moonshot-v1-32k': ModelConfig(
         properties=ModelProperties(context_size=32768, max_tokens=16384, mode=LLMMode.CHAT),
-        features=[]
+        features=[ModelFeature.TOOL_CALL]
     ),
     'Moonshot-v1-128k': ModelConfig(
         properties=ModelProperties(context_size=131072, max_tokens=65536, mode=LLMMode.CHAT),
-        features=[]
+        features=[ModelFeature.TOOL_CALL]
     ),
     'GLM3-130B': ModelConfig(
         properties=ModelProperties(context_size=8192, max_tokens=4096, mode=LLMMode.CHAT),
-        features=[]
+        features=[ModelFeature.TOOL_CALL]
     ),
     'GLM3-130B-Fin': ModelConfig(
         properties=ModelProperties(context_size=8192, max_tokens=4096, mode=LLMMode.CHAT),
-        features=[]
+        features=[ModelFeature.TOOL_CALL]
     ),
     'Mistral-7B': ModelConfig(
         properties=ModelProperties(context_size=8192, max_tokens=2048, mode=LLMMode.CHAT),

api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml

@@ -30,8 +30,28 @@ model_credential_schema:
       en_US: Enter your Model Name
       zh_Hans: 输入模型名称
   credential_form_schemas:
+    - variable: auth_method
+      required: true
+      label:
+        en_US: Authentication Method
+        zh_Hans: 鉴权方式
+      type: select
+      default: aksk
+      options:
+        - label:
+            en_US: API Key
+          value: api_key
+        - label:
+            en_US: Access Key / Secret Access Key
+          value: aksk
+      placeholder:
+        en_US: Enter your Authentication Method
+        zh_Hans: 选择鉴权方式
     - variable: volc_access_key_id
       required: true
+      show_on:
+        - variable: auth_method
+          value: aksk
       label:
         en_US: Access Key
         zh_Hans: Access Key
@@ -41,6 +61,9 @@ model_credential_schema:
         zh_Hans: 输入您的 Access Key
     - variable: volc_secret_access_key
       required: true
+      show_on:
+        - variable: auth_method
+          value: aksk
       label:
         en_US: Secret Access Key
         zh_Hans: Secret Access Key
@@ -48,6 +71,17 @@ model_credential_schema:
       placeholder:
         en_US: Enter your Secret Access Key
         zh_Hans: 输入您的 Secret Access Key
+    - variable: volc_api_key
+      required: true
+      show_on:
+        - variable: auth_method
+          value: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      placeholder:
+        en_US: Enter your API Key
+        zh_Hans: 输入您的 API Key
     - variable: volc_region
       required: true
       label:
@@ -64,7 +98,7 @@ model_credential_schema:
         en_US: API Endpoint Host
         zh_Hans: API Endpoint Host
       type: text-input
-      default: maas-api.ml-platform-cn-beijing.volces.com
+      default: https://ark.cn-beijing.volces.com/api/v3
       placeholder:
         en_US: Enter your API Endpoint Host
         zh_Hans: 输入 API Endpoint Host

api/core/model_runtime/model_providers/zhipuai/llm/glm-4-flash.yaml

@@ -38,7 +38,7 @@ parameter_rules:
     min: 1
     max: 8192
 pricing:
-  input: '0.0001'
-  output: '0.0001'
+  input: '0'
+  output: '0'
   unit: '0.001'
   currency: RMB

api/core/model_runtime/model_providers/zhipuai/llm/glm_3_turbo.yaml

@@ -37,3 +37,8 @@ parameter_rules:
     default: 1024
     min: 1
     max: 8192
+pricing:
+  input: '0.001'
+  output: '0.001'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/zhipuai/llm/glm_4.yaml

@@ -37,3 +37,8 @@ parameter_rules:
     default: 1024
     min: 1
     max: 8192
+pricing:
+  input: '0.1'
+  output: '0.1'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/zhipuai/llm/glm_4_long.yaml

@@ -30,4 +30,9 @@ parameter_rules:
     use_template: max_tokens
     default: 1024
     min: 1
-    max: 4096
+    max: 8192
+pricing:
+  input: '0.001'
+  output: '0.001'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/zhipuai/llm/glm_4_plus.yaml

@@ -0,0 +1,44 @@
+model: glm-4-plus
+label:
+  en_US: glm-4-plus
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.95
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
+      en_US: Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
+  - name: top_p
+    use_template: top_p
+    default: 0.7
+    help:
+      zh_Hans: 用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
+      en_US: Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
+  - name: incremental
+    label:
+      zh_Hans: 增量返回
+      en_US: Incremental
+    type: boolean
+    help:
+      zh_Hans: SSE接口调用时，用于控制每次返回内容方式是增量还是全量，不提供此参数时默认为增量返回，true 为增量返回，false 为全量返回。
+      en_US: When the SSE interface is called, it is used to control whether the content is returned incrementally or in full. If this parameter is not provided, the default is incremental return. true means incremental return, false means full return.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 8192
+pricing:
+  input: '0.05'
+  output: '0.05'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/zhipuai/llm/glm_4v.yaml

@@ -34,4 +34,9 @@ parameter_rules:
     use_template: max_tokens
     default: 1024
     min: 1
-    max: 8192
+    max: 1024
+pricing:
+  input: '0.05'
+  output: '0.05'
+  unit: '0.001'
+  currency: RMB

api/core/model_runtime/model_providers/zhipuai/llm/glm_4v_plus.yaml

@@ -0,0 +1,42 @@
+model: glm-4v-plus
+label:
+  en_US: glm-4v-plus
+model_type: llm
+model_properties:
+  mode: chat
+features:
+  - vision
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.95
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
+      en_US: Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
+  - name: top_p
+    use_template: top_p
+    default: 0.7
+    help:
+      zh_Hans: 用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
+      en_US: Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
+  - name: incremental
+    label:
+      zh_Hans: 增量返回
+      en_US: Incremental
+    type: boolean
+    help:
+      zh_Hans: SSE接口调用时，用于控制每次返回内容方式是增量还是全量，不提供此参数时默认为增量返回，true 为增量返回，false 为全量返回。
+      en_US: When the SSE interface is called, it is used to control whether the content is returned incrementally or in full. If this parameter is not provided, the default is incremental return. true means incremental return, false means full return.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 1024
+pricing:
+  input: '0.01'
+  output: '0.01'
+  unit: '0.001'
+  currency: RMB

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

@@ -153,7 +153,8 @@ class ZhipuAILargeLanguageModel(_CommonZhipuaiAI, LargeLanguageModel):
         :return: full response or stream response chunk generator result
         """
         extra_model_kwargs = {}
-        if stop:
+        # request to glm-4v-plus with stop words will always response "finish_reason":"network_error"
+        if stop and model!= 'glm-4v-plus':
             extra_model_kwargs['stop'] = stop
 
         client = ZhipuAI(
@@ -174,7 +175,7 @@ class ZhipuAILargeLanguageModel(_CommonZhipuaiAI, LargeLanguageModel):
             if copy_prompt_message.role in [PromptMessageRole.USER, PromptMessageRole.SYSTEM, PromptMessageRole.TOOL]:
                 if isinstance(copy_prompt_message.content, list):
                     # check if model is 'glm-4v'
-                    if model != 'glm-4v':
+                    if model not in ('glm-4v', 'glm-4v-plus'):
                         # not support list message
                         continue
                     # get image and 
@@ -207,7 +208,7 @@ class ZhipuAILargeLanguageModel(_CommonZhipuaiAI, LargeLanguageModel):
                 else:
                     new_prompt_messages.append(copy_prompt_message)
 
-        if model == 'glm-4v':
+        if model == 'glm-4v' or model == 'glm-4v-plus':
             params = self._construct_glm_4v_parameter(model, new_prompt_messages, model_parameters)
         else:
             params = {
@@ -304,7 +305,7 @@ class ZhipuAILargeLanguageModel(_CommonZhipuaiAI, LargeLanguageModel):
 
         return params
 
-    def _construct_glm_4v_messages(self, prompt_message: Union[str | list[PromptMessageContent]]) -> list[dict]:
+    def _construct_glm_4v_messages(self, prompt_message: Union[str, list[PromptMessageContent]]) -> list[dict]:
         if isinstance(prompt_message, str):
             return [{'type': 'text', 'text': prompt_message}]
 

api/core/ops/entities/config_entity.py

@@ -21,7 +21,6 @@ class LangfuseConfig(BaseTracingConfig):
     """
     public_key: str
     secret_key: str
-    project_key: str
     host: str = 'https://api.langfuse.com'
 
     @field_validator("host")

api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py

@@ -1,5 +1,7 @@
 import json
-from typing import Any
+import logging
+from typing import Any, Optional
+from urllib.parse import urlparse
 
 import requests
 from elasticsearch import Elasticsearch
@@ -7,16 +9,20 @@ from flask import current_app
 from pydantic import BaseModel, model_validator
 
 from core.rag.datasource.entity.embedding import Embeddings
+from core.rag.datasource.vdb.field import Field
 from core.rag.datasource.vdb.vector_base import BaseVector
 from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.models.document import Document
+from extensions.ext_redis import redis_client
 from models.dataset import Dataset
 
+logger = logging.getLogger(__name__)
+
 
 class ElasticSearchConfig(BaseModel):
     host: str
-    port: str
+    port: int
     username: str
     password: str
 
@@ -37,12 +43,19 @@ class ElasticSearchVector(BaseVector):
     def __init__(self, index_name: str, config: ElasticSearchConfig, attributes: list):
         super().__init__(index_name.lower())
         self._client = self._init_client(config)
+        self._version = self._get_version()
+        self._check_version()
         self._attributes = attributes
 
     def _init_client(self, config: ElasticSearchConfig) -> Elasticsearch:
         try:
+            parsed_url = urlparse(config.host)
+            if parsed_url.scheme in ['http', 'https']:
+                hosts = f'{config.host}:{config.port}'
+            else:
+                hosts = f'http://{config.host}:{config.port}'
             client = Elasticsearch(
-                hosts=f'{config.host}:{config.port}',
+                hosts=hosts,
                 basic_auth=(config.username, config.password),
                 request_timeout=100000,
                 retry_on_timeout=True,
@@ -53,42 +66,27 @@ class ElasticSearchVector(BaseVector):
 
         return client
 
+    def _get_version(self) -> str:
+        info = self._client.info()
+        return info['version']['number']
+
+    def _check_version(self):
+        if self._version < '8.0.0':
+            raise ValueError("Elasticsearch vector database version must be greater than 8.0.0")
+
     def get_type(self) -> str:
         return 'elasticsearch'
 
     def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
         uuids = self._get_uuids(documents)
-        texts = [d.page_content for d in documents]
-        metadatas = [d.metadata for d in documents]
-
-        if not self._client.indices.exists(index=self._collection_name):
-            dim = len(embeddings[0])
-            mapping = {
-                "properties": {
-                    "text": {
-                        "type": "text"
-                    },
-                    "vector": {
-                        "type": "dense_vector",
-                        "index": True,
-                        "dims": dim,
-                        "similarity": "l2_norm"
-                    },
-                }
-            }
-            self._client.indices.create(index=self._collection_name, mappings=mapping)
-
-        added_ids = []
-        for i, text in enumerate(texts):
+        for i in range(len(documents)):
             self._client.index(index=self._collection_name,
                                id=uuids[i],
                                document={
-                                   "text": text,
-                                   "vector": embeddings[i] if embeddings[i] else None,
-                                   "metadata": metadatas[i] if metadatas[i] else {},
+                                   Field.CONTENT_KEY.value: documents[i].page_content,
+                                   Field.VECTOR.value: embeddings[i] if embeddings[i] else None,
+                                   Field.METADATA_KEY.value: documents[i].metadata if documents[i].metadata else {}
                                })
-            added_ids.append(uuids[i])
-
         self._client.indices.refresh(index=self._collection_name)
         return uuids
 
@@ -116,28 +114,21 @@ class ElasticSearchVector(BaseVector):
         self._client.indices.delete(index=self._collection_name)
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
-        query_str = {
-            "query": {
-                "script_score": {
-                    "query": {
-                        "match_all": {}
-                    },
-                    "script": {
-                        "source": "cosineSimilarity(params.query_vector, 'vector') + 1.0",
-                        "params": {
-                            "query_vector": query_vector
-                        }
-                    }
-                }
-            }
+        top_k = kwargs.get("top_k", 10)
+        knn = {
+            "field": Field.VECTOR.value,
+            "query_vector": query_vector,
+            "k": top_k
         }
 
-        results = self._client.search(index=self._collection_name, body=query_str)
+        results = self._client.search(index=self._collection_name, knn=knn, size=top_k)
 
         docs_and_scores = []
         for hit in results['hits']['hits']:
             docs_and_scores.append(
-                (Document(page_content=hit['_source']['text'], metadata=hit['_source']['metadata']), hit['_score']))
+                (Document(page_content=hit['_source'][Field.CONTENT_KEY.value],
+                          vector=hit['_source'][Field.VECTOR.value],
+                          metadata=hit['_source'][Field.METADATA_KEY.value]), hit['_score']))
 
         docs = []
         for doc, score in docs_and_scores:
@@ -146,25 +137,61 @@ class ElasticSearchVector(BaseVector):
                 doc.metadata['score'] = score
             docs.append(doc)
 
-        # Sort the documents by score in descending order
-        docs = sorted(docs, key=lambda x: x.metadata['score'], reverse=True)
-
         return docs
+
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         query_str = {
             "match": {
-                "text": query
+                Field.CONTENT_KEY.value: query
             }
         }
         results = self._client.search(index=self._collection_name, query=query_str)
         docs = []
         for hit in results['hits']['hits']:
-            docs.append(Document(page_content=hit['_source']['text'], metadata=hit['_source']['metadata']))
+            docs.append(Document(
+                page_content=hit['_source'][Field.CONTENT_KEY.value],
+                vector=hit['_source'][Field.VECTOR.value],
+                metadata=hit['_source'][Field.METADATA_KEY.value],
+            ))
 
         return docs
 
     def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs):
-        return self.add_texts(texts, embeddings, **kwargs)
+        metadatas = [d.metadata for d in texts]
+        self.create_collection(embeddings, metadatas)
+        self.add_texts(texts, embeddings, **kwargs)
+
+    def create_collection(
+            self, embeddings: list, metadatas: Optional[list[dict]] = None, index_params: Optional[dict] = None
+    ):
+        lock_name = f'vector_indexing_lock_{self._collection_name}'
+        with redis_client.lock(lock_name, timeout=20):
+            collection_exist_cache_key = f'vector_indexing_{self._collection_name}'
+            if redis_client.get(collection_exist_cache_key):
+                logger.info(f"Collection {self._collection_name} already exists.")
+                return
+
+            if not self._client.indices.exists(index=self._collection_name):
+                dim = len(embeddings[0])
+                mappings = {
+                    "properties": {
+                        Field.CONTENT_KEY.value: {"type": "text"},
+                        Field.VECTOR.value: {  # Make sure the dimension is correct here
+                            "type": "dense_vector",
+                            "dims": dim,
+                            "similarity": "cosine"
+                        },
+                        Field.METADATA_KEY.value: {
+                            "type": "object",
+                            "properties": {
+                                "doc_id": {"type": "keyword"}  # Map doc_id to keyword type
+                            }
+                        }
+                    }
+                }
+                self._client.indices.create(index=self._collection_name, mappings=mappings)
+
+            redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
 
 class ElasticSearchVectorFactory(AbstractVectorFactory):

api/core/rag/datasource/vdb/myscale/myscale_vector.py

@@ -122,7 +122,7 @@ class MyScaleVector(BaseVector):
 
     def _search(self, dist: str, order: SortOrder, **kwargs: Any) -> list[Document]:
         top_k = kwargs.get("top_k", 5)
-        score_threshold = kwargs.get("score_threshold", 0.0)
+        score_threshold = kwargs.get('score_threshold') or 0.0
         where_str = f"WHERE dist < {1 - score_threshold}" if \
             self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0 else ""
         sql = f"""

api/core/rag/extractor/notion_extractor.py

@@ -281,20 +281,25 @@ class NotionExtractor(BaseExtractor):
                     for table_header_cell_text in tabel_header_cell:
                         text = table_header_cell_text["text"]["content"]
                         table_header_cell_texts.append(text)
-            # get table columns text and format
+                else:
+                    table_header_cell_texts.append('')
+            # Initialize Markdown table with headers
+            markdown_table = "| " + " | ".join(table_header_cell_texts) + " |\n"
+            markdown_table += "| " + " | ".join(['---'] * len(table_header_cell_texts)) + " |\n"
+
+            # Process data to format each row in Markdown table format
             results = data["results"]
             for i in range(len(results) - 1):
                 column_texts = []
-                tabel_column_cells = data["results"][i + 1]['table_row']['cells']
-                for j in range(len(tabel_column_cells)):
-                    if tabel_column_cells[j]:
-                        for table_column_cell_text in tabel_column_cells[j]:
+                table_column_cells = data["results"][i + 1]['table_row']['cells']
+                for j in range(len(table_column_cells)):
+                    if table_column_cells[j]:
+                        for table_column_cell_text in table_column_cells[j]:
                             column_text = table_column_cell_text["text"]["content"]
-                            column_texts.append(f'{table_header_cell_texts[j]}:{column_text}')
-
-                cur_result_text = "\n".join(column_texts)
-                result_lines_arr.append(cur_result_text)
-
+                            column_texts.append(column_text)
+                # Add row to Markdown table
+                markdown_table += "| " + " | ".join(column_texts) + " |\n"
+            result_lines_arr.append(markdown_table)
             if data["next_cursor"] is None:
                 done = True
                 break

api/core/rag/extractor/word_extractor.py

@@ -170,6 +170,8 @@ class WordExtractor(BaseExtractor):
             if run.element.xpath('.//a:blip'):
                 for blip in run.element.xpath('.//a:blip'):
                     image_id = blip.get("{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed")
+                    if not image_id:
+                        continue
                     image_part = paragraph.part.rels[image_id].target_part
 
                     if image_part in image_map:
@@ -256,6 +258,6 @@ class WordExtractor(BaseExtractor):
                         content.append(parsed_paragraph)
                 elif isinstance(element.tag, str) and element.tag.endswith('tbl'):  # table
                     table = tables.pop(0)
-                    content.append(self._table_to_markdown(table,image_map))
+                    content.append(self._table_to_markdown(table, image_map))
         return '\n'.join(content)
 

api/core/rag/index_processor/index_processor_base.py

@@ -57,7 +57,7 @@ class BaseIndexProcessor(ABC):
 
             character_splitter = FixedRecursiveCharacterTextSplitter.from_encoder(
                 chunk_size=segmentation["max_tokens"],
-                chunk_overlap=segmentation.get('chunk_overlap', 0),
+                chunk_overlap=segmentation.get('chunk_overlap', 0) or 0,
                 fixed_separator=separator,
                 separators=["\n\n", "。", ". ", " ", ""],
                 embedding_model_instance=embedding_model_instance

api/core/tools/provider/_position.yaml

@@ -1,5 +1,6 @@
 - google
 - bing
+- perplexity
 - duckduckgo
 - searchapi
 - serper
@@ -10,6 +11,7 @@
 - wikipedia
 - nominatim
 - yahoo
+- alphavantage
 - arxiv
 - pubmed
 - stablediffusion
@@ -30,5 +32,7 @@
 - dingtalk
 - feishu
 - feishu_base
+- feishu_document
+- feishu_message
 - slack
 - tianditu

api/core/tools/provider/builtin/alphavantage/_assets/icon.svg

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="56px" height="56px" viewBox="0 0 56 56" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+    <title>形状结合</title>
+    <g id="设计规范" stroke="none" stroke-width="1" fill="none" fill-rule="evenodd">
+        <path d="M56,0 L56,56 L0,56 L0,0 L56,0 Z M31.6063018,12 L24.3936982,12 L24.1061064,12.7425499 L12.6071308,42.4324141 L12,44 L19.7849972,44 L20.0648488,43.2391815 L22.5196173,36.5567427 L33.4780427,36.5567427 L35.9351512,43.2391815 L36.2150028,44 L44,44 L43.3928692,42.4324141 L31.8938936,12.7425499 L31.6063018,12 Z M28.0163803,21.5755126 L31.1613993,30.2523823 L24.8432808,30.2523823 L28.0163803,21.5755126 Z" id="形状结合" fill="#2F4F4F"></path>
+    </g>
+</svg>

api/core/tools/provider/builtin/alphavantage/alphavantage.py

@@ -0,0 +1,22 @@
+from typing import Any
+
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin.alphavantage.tools.query_stock import QueryStockTool
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class AlphaVantageProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict[str, Any]) -> None:
+        try:
+            QueryStockTool().fork_tool_runtime(
+                runtime={
+                    "credentials": credentials,
+                }
+            ).invoke(
+                user_id='',
+                tool_parameters={
+                    "code": "AAPL",  # Apple Inc.
+                },
+            )
+        except Exception as e:
+            raise ToolProviderCredentialValidationError(str(e))

api/core/tools/provider/builtin/alphavantage/alphavantage.yaml

@@ -0,0 +1,31 @@
+identity:
+  author: zhuhao
+  name: alphavantage
+  label:
+    en_US: AlphaVantage
+    zh_Hans: AlphaVantage
+    pt_BR: AlphaVantage
+  description:
+    en_US: AlphaVantage is an online platform that provides financial market data and APIs, making it convenient for individual investors and developers to access stock quotes, technical indicators, and stock analysis.
+    zh_Hans: AlphaVantage是一个在线平台，它提供金融市场数据和API，便于个人投资者和开发者获取股票报价、技术指标和股票分析。
+    pt_BR: AlphaVantage is an online platform that provides financial market data and APIs, making it convenient for individual investors and developers to access stock quotes, technical indicators, and stock analysis.
+  icon: icon.svg
+  tags:
+    - finance
+credentials_for_provider:
+  api_key:
+    type: secret-input
+    required: true
+    label:
+      en_US: AlphaVantage API key
+      zh_Hans: AlphaVantage API key
+      pt_BR: AlphaVantage API key
+    placeholder:
+      en_US: Please input your AlphaVantage API key
+      zh_Hans: 请输入你的 AlphaVantage API key
+      pt_BR: Please input your AlphaVantage API key
+    help:
+      en_US: Get your AlphaVantage API key from AlphaVantage
+      zh_Hans: 从 AlphaVantage 获取您的 AlphaVantage API key
+      pt_BR: Get your AlphaVantage API key from AlphaVantage
+    url: https://www.alphavantage.co/support/#api-key

api/core/tools/provider/builtin/alphavantage/tools/query_stock.py

@@ -0,0 +1,49 @@
+from typing import Any, Union
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+ALPHAVANTAGE_API_URL = "https://www.alphavantage.co/query"
+
+
+class QueryStockTool(BuiltinTool):
+
+    def _invoke(self,
+                user_id: str,
+                tool_parameters: dict[str, Any],
+                ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+
+        stock_code = tool_parameters.get('code', '')
+        if not stock_code:
+            return self.create_text_message('Please tell me your stock code')
+
+        if 'api_key' not in self.runtime.credentials or not self.runtime.credentials.get('api_key'):
+            return self.create_text_message("Alpha Vantage API key is required.")
+
+        params = {
+            "function": "TIME_SERIES_DAILY",
+            "symbol": stock_code,
+            "outputsize": "compact",
+            "datatype": "json",
+            "apikey": self.runtime.credentials['api_key']
+        }
+        response = requests.get(url=ALPHAVANTAGE_API_URL, params=params)
+        response.raise_for_status()
+        result = self._handle_response(response.json())
+        return self.create_json_message(result)
+
+    def _handle_response(self, response: dict[str, Any]) -> dict[str, Any]:
+        result = response.get('Time Series (Daily)', {})
+        if not result:
+            return {}
+        stock_result = {}
+        for k, v in result.items():
+            stock_result[k] = {}
+            stock_result[k]['open'] = v.get('1. open')
+            stock_result[k]['high'] = v.get('2. high')
+            stock_result[k]['low'] = v.get('3. low')
+            stock_result[k]['close'] = v.get('4. close')
+            stock_result[k]['volume'] = v.get('5. volume')
+        return stock_result

api/core/tools/provider/builtin/alphavantage/tools/query_stock.yaml

@@ -0,0 +1,27 @@
+identity:
+  name: query_stock
+  author: zhuhao
+  label:
+    en_US: query_stock
+    zh_Hans: query_stock
+    pt_BR: query_stock
+description:
+  human:
+    en_US: Retrieve information such as daily opening price, daily highest price, daily lowest price, daily closing price, and daily trading volume for a specified stock symbol.
+    zh_Hans: 获取指定股票代码的每日开盘价、每日最高价、每日最低价、每日收盘价和每日交易量等信息。
+    pt_BR: Retrieve information such as daily opening price, daily highest price, daily lowest price, daily closing price, and daily trading volume for a specified stock symbol
+  llm: Retrieve information such as daily opening price, daily highest price, daily lowest price, daily closing price, and daily trading volume for a specified stock symbol
+parameters:
+  - name: code
+    type: string
+    required: true
+    label:
+      en_US: stock code
+      zh_Hans: 股票代码
+      pt_BR: stock code
+    human_description:
+      en_US: stock code
+      zh_Hans: 股票代码
+      pt_BR: stock code
+    llm_description: stock code for query from alphavantage
+    form: llm

api/core/tools/provider/builtin/feishu_document/_assets/icon.svg

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg xmlns="http://www.w3.org/2000/svg" version="1.1" width="64px" height="64px" style="shape-rendering:geometricPrecision; text-rendering:geometricPrecision; image-rendering:optimizeQuality; fill-rule:evenodd; clip-rule:evenodd" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g><path style="opacity:1" fill="#fefefe" d="M -0.5,-0.5 C 20.8333,-0.5 42.1667,-0.5 63.5,-0.5C 63.5,20.8333 63.5,42.1667 63.5,63.5C 42.1667,63.5 20.8333,63.5 -0.5,63.5C -0.5,42.1667 -0.5,20.8333 -0.5,-0.5 Z"/></g>
+<g><path style="opacity:1" fill="#346df3" d="M 47.5,33.5 C 43.3272,29.8779 38.9939,29.7112 34.5,33C 32.682,35.4897 30.3487,37.3231 27.5,38.5C 23.5003,43.5136 24.167,47.847 29.5,51.5C 24.1563,51.666 18.8229,51.4994 13.5,51C 13,50.5 12.5,50 12,49.5C 11.3333,36.8333 11.3333,24.1667 12,11.5C 12.5,11 13,10.5 13.5,10C 24.1667,9.33333 34.8333,9.33333 45.5,10C 46,10.5 46.5,11 47,11.5C 47.4997,18.8258 47.6663,26.1591 47.5,33.5 Z"/></g>
+<g><path style="opacity:1" fill="#f9fafe" d="M 20.5,19.5 C 25.1785,19.3342 29.8452,19.5008 34.5,20C 35.8333,21 35.8333,22 34.5,23C 29.8333,23.6667 25.1667,23.6667 20.5,23C 19.3157,21.8545 19.3157,20.6879 20.5,19.5 Z"/></g>
+<g><path style="opacity:1" fill="#f3f6fe" d="M 20.5,27.5 C 22.5273,27.3379 24.5273,27.5045 26.5,28C 27.8333,29 27.8333,30 26.5,31C 24.5,31.6667 22.5,31.6667 20.5,31C 19.3157,29.8545 19.3157,28.6879 20.5,27.5 Z"/></g>
+<g><path style="opacity:1" fill="#36d4c1" d="M 47.5,33.5 C 48.7298,35.2972 49.3964,37.2972 49.5,39.5C 51.3904,39.2965 52.8904,39.9632 54,41.5C 55.1825,45.2739 54.3492,48.4406 51.5,51C 44.1742,51.4997 36.8409,51.6663 29.5,51.5C 24.167,47.847 23.5003,43.5136 27.5,38.5C 30.3487,37.3231 32.682,35.4897 34.5,33C 38.9939,29.7112 43.3272,29.8779 47.5,33.5 Z"/></g>
+</svg>

api/core/tools/provider/builtin/feishu_document/feishu_document.py

@@ -0,0 +1,15 @@
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class FeishuDocumentProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict) -> None:
+        app_id = credentials.get('app_id')
+        app_secret = credentials.get('app_secret')
+        if not app_id or not app_secret:
+            raise ToolProviderCredentialValidationError("app_id and app_secret is required")
+        try:
+            assert FeishuRequest(app_id, app_secret).tenant_access_token is not None
+        except Exception as e:
+            raise ToolProviderCredentialValidationError(str(e))

api/core/tools/provider/builtin/feishu_document/feishu_document.yaml

@@ -0,0 +1,34 @@
+identity:
+  author: Doug Lea
+  name: feishu_document
+  label:
+    en_US: Lark Cloud Document
+    zh_Hans: 飞书云文档
+  description:
+    en_US: Lark Cloud Document
+    zh_Hans: 飞书云文档
+  icon: icon.svg
+  tags:
+    - social
+    - productivity
+credentials_for_provider:
+  app_id:
+    type: text-input
+    required: true
+    label:
+      en_US: APP ID
+    placeholder:
+      en_US: Please input your feishu app id
+      zh_Hans: 请输入你的飞书 app id
+    help:
+      en_US: Get your app_id and app_secret from Feishu
+      zh_Hans: 从飞书获取您的 app_id 和 app_secret
+    url: https://open.feishu.cn
+  app_secret:
+    type: secret-input
+    required: true
+    label:
+      en_US: APP Secret
+    placeholder:
+      en_US: Please input your app secret
+      zh_Hans: 请输入你的飞书 app secret

api/core/tools/provider/builtin/feishu_document/tools/create_document.py

@@ -0,0 +1,19 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class CreateDocumentTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        app_id = self.runtime.credentials.get('app_id')
+        app_secret = self.runtime.credentials.get('app_secret')
+        client = FeishuRequest(app_id, app_secret)
+
+        title = tool_parameters.get('title')
+        content = tool_parameters.get('content')
+        folder_token = tool_parameters.get('folder_token')
+
+        res = client.create_document(title, content, folder_token)
+        return self.create_json_message(res)

api/core/tools/provider/builtin/feishu_document/tools/create_document.yaml

@@ -0,0 +1,47 @@
+identity:
+  name: create_document
+  author: Doug Lea
+  label:
+    en_US: Create Lark document
+    zh_Hans: 创建飞书文档
+description:
+  human:
+    en_US: Create Lark document
+    zh_Hans: 创建飞书文档，支持创建空文档和带内容的文档，支持 markdown 语法创建。
+  llm: A tool for creating Feishu documents.
+parameters:
+  - name: title
+    type: string
+    required: false
+    label:
+      en_US: Document title
+      zh_Hans: 文档标题
+    human_description:
+      en_US: Document title, only supports plain text content.
+      zh_Hans: 文档标题，只支持纯文本内容。
+    llm_description: 文档标题，只支持纯文本内容，可以为空。
+    form: llm
+
+  - name: content
+    type: string
+    required: false
+    label:
+      en_US: Document content
+      zh_Hans: 文档内容
+    human_description:
+      en_US: Document content, supports markdown syntax, can be empty.
+      zh_Hans: 文档内容，支持 markdown 语法，可以为空。
+    llm_description: 文档内容，支持 markdown 语法，可以为空。
+    form: llm
+
+  - name: folder_token
+    type: string
+    required: false
+    label:
+      en_US: folder_token
+      zh_Hans: 文档所在文件夹的 Token
+    human_description:
+      en_US: The token of the folder where the document is located. If it is not passed or is empty, it means the root directory.
+      zh_Hans: 文档所在文件夹的 Token，不传或传空表示根目录。
+    llm_description: 文档所在文件夹的 Token，不传或传空表示根目录。
+    form: llm

api/core/tools/provider/builtin/feishu_document/tools/get_document_raw_content.py

@@ -0,0 +1,17 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class GetDocumentRawContentTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        app_id = self.runtime.credentials.get('app_id')
+        app_secret = self.runtime.credentials.get('app_secret')
+        client = FeishuRequest(app_id, app_secret)
+
+        document_id = tool_parameters.get('document_id')
+
+        res = client.get_document_raw_content(document_id)
+        return self.create_json_message(res)

api/core/tools/provider/builtin/feishu_document/tools/get_document_raw_content.yaml

@@ -0,0 +1,23 @@
+identity:
+  name: get_document_raw_content
+  author: Doug Lea
+  label:
+    en_US: Get Document Raw Content
+    zh_Hans: 获取文档纯文本内容
+description:
+  human:
+    en_US: Get document raw content
+    zh_Hans: 获取文档纯文本内容
+  llm: A tool for getting the plain text content of Feishu documents
+parameters:
+  - name: document_id
+    type: string
+    required: true
+    label:
+      en_US: document_id
+      zh_Hans: 飞书文档的唯一标识
+    human_description:
+      en_US: Unique ID of Feishu document document_id
+      zh_Hans: 飞书文档的唯一标识 document_id
+    llm_description: 飞书文档的唯一标识 document_id
+    form: llm

api/core/tools/provider/builtin/feishu_document/tools/list_document_block.py

@@ -0,0 +1,19 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class ListDocumentBlockTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        app_id = self.runtime.credentials.get('app_id')
+        app_secret = self.runtime.credentials.get('app_secret')
+        client = FeishuRequest(app_id, app_secret)
+
+        document_id = tool_parameters.get('document_id')
+        page_size = tool_parameters.get('page_size', 500)
+        page_token = tool_parameters.get('page_token', '')
+
+        res = client.list_document_block(document_id, page_token, page_size)
+        return self.create_json_message(res)

api/core/tools/provider/builtin/feishu_document/tools/list_document_block.yaml

@@ -0,0 +1,48 @@
+identity:
+  name: list_document_block
+  author: Doug Lea
+  label:
+    en_US: List Document Block
+    zh_Hans: 获取飞书文档所有块
+description:
+  human:
+    en_US: List document block
+    zh_Hans: 获取飞书文档所有块的富文本内容并分页返回。
+  llm: A tool to get all blocks of Feishu documents
+parameters:
+  - name: document_id
+    type: string
+    required: true
+    label:
+      en_US: document_id
+      zh_Hans: 飞书文档的唯一标识
+    human_description:
+      en_US: Unique ID of Feishu document document_id
+      zh_Hans: 飞书文档的唯一标识 document_id
+    llm_description: 飞书文档的唯一标识 document_id
+    form: llm
+
+  - name: page_size
+    type: number
+    required: false
+    default: 500
+    label:
+      en_US: page_size
+      zh_Hans: 分页大小
+    human_description:
+      en_US: Paging size, the default and maximum value is 500.
+      zh_Hans: 分页大小, 默认值和最大值为 500。
+    llm_description: 分页大小, 表示一次请求最多返回多少条数据，默认值和最大值为 500。
+    form: llm
+
+  - name: page_token
+    type: string
+    required: false
+    label:
+      en_US: page_token
+      zh_Hans: 分页标记
+    human_description:
+      en_US: Pagination tag, used to paginate query results so that more items can be obtained in the next traversal.
+      zh_Hans: 分页标记，用于分页查询结果，以便下次遍历时获取更多项。
+    llm_description: 分页标记，第一次请求不填，表示从头开始遍历；分页查询结果还有更多项时会同时返回新的 page_token，下次遍历可采用该 page_token 获取查询结果。
+    form: llm

api/core/tools/provider/builtin/feishu_document/tools/write_document.py

@@ -0,0 +1,19 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class CreateDocumentTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        app_id = self.runtime.credentials.get('app_id')
+        app_secret = self.runtime.credentials.get('app_secret')
+        client = FeishuRequest(app_id, app_secret)
+
+        document_id = tool_parameters.get('document_id')
+        content = tool_parameters.get('content')
+        position = tool_parameters.get('position')
+
+        res = client.write_document(document_id, content, position)
+        return self.create_json_message(res)

api/core/tools/provider/builtin/feishu_document/tools/write_document.yaml

@@ -0,0 +1,56 @@
+identity:
+  name: write_document
+  author: Doug Lea
+  label:
+    en_US: Write Document
+    zh_Hans: 在飞书文档中新增内容
+description:
+  human:
+    en_US: Adding new content to Lark documents
+    zh_Hans: 在飞书文档中新增内容
+  llm: A tool for adding new content to Lark documents.
+parameters:
+  - name: document_id
+    type: string
+    required: true
+    label:
+      en_US: document_id
+      zh_Hans: 飞书文档的唯一标识
+    human_description:
+      en_US: Unique ID of Feishu document document_id
+      zh_Hans: 飞书文档的唯一标识 document_id
+    llm_description: 飞书文档的唯一标识 document_id
+    form: llm
+
+  - name: content
+    type: string
+    required: true
+    label:
+      en_US: document content
+      zh_Hans: 文档内容
+    human_description:
+      en_US: Document content, supports markdown syntax, can be empty.
+      zh_Hans: 文档内容，支持 markdown 语法，可以为空。
+    llm_description:
+    form: llm
+
+  - name: position
+    type: select
+    required: true
+    default: start
+    label:
+      en_US: Choose where to add content
+      zh_Hans: 选择添加内容的位置
+    human_description:
+      en_US: Please fill in start or end to add content at the beginning or end of the document respectively.
+      zh_Hans: 请填入 start 或 end, 分别表示在文档开头(start)或结尾(end)添加内容。
+    form: llm
+    options:
+      - value: start
+        label:
+          en_US: start
+          zh_Hans: 在文档开头添加内容
+      - value: end
+        label:
+          en_US: end
+          zh_Hans: 在文档结尾添加内容

api/core/tools/provider/builtin/feishu_message/_assets/icon.svg

@@ -0,0 +1,19 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="64px" height="64px" viewBox="0 0 64 64" enable-background="new 0 0 64 64" xml:space="preserve">  <image id="image0" width="64" height="64" x="0" y="0"
+    xlink:href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAMAAACdt4HsAAAAIGNIUk0AAHomAACAhAAA+gAAAIDo
+AAB1MAAA6mAAADqYAAAXcJy6UTwAAAC9UExURf///////+bs/vL2/qa/+n+j+E1/9TNt9FmI9nOa
++Obt/sza/GaR97PI+9nk/aa/+5m2+oCk+Iyt+Yys+eXt/oCj+L/R+4yt+HOb+Ex/9TOA6jOi2jO8
+zTPJxzPWwDOa3eb69zN67X/l2DOb3TPPw0DZxLPv55nq4LPw6DOB6vL9+0B29TOo16bt4zPCynPj
+00zbyDN08WbgzzOH50DYxFmI9bLI+5nr34zn3OX699n384zo21ndyzTWwJnq37nAcdIAAAABdFJO
+U/4a4wd9AAAAAWJLR0QAiAUdSAAAAAlwSFlzAAAWJQAAFiUBSVIk8AAAAAd0SU1FB+gHEggfEk4D
+XiUAAAFOSURBVFjD7dVZU8IwFAXgpq2NtFFRUVTKtYC4gCvu6///WcCMI9Cc3CR2fLLn/XyT3KRp
+IComqIEa+GMgDMNfA1G8lsh51htx6g9kSi5HbfgBm6v1eZLUA9iSKE1nYFviqMgNMPVn44xcgB1p
+jnIAmpLLrhVoST6ZDdizAMoCZNKWjAdsC8BLWACRtS9lygH7DkDMAW0H4IADlANwyAEJUzzq5F2i
+bn5cMIC53svpJ/3CHxic0FKGp75Ah0o585uB1ic69zmFnt6nYQEBfA9yAFDf/SZeEMwIfgtjAFxi
+4AoBcA/XGLiBAHoPcJ9uISAaWv/OABAGWuOKgIgrbgHM0TDEiQnQHnavY0Tfwz0GCgMA/kweVxm/
+y2gJD4UJQJd5wE6gfIxlIXlsPz1rwIsRwNGFkR8gXicVASHe3j++u5+zfHlugU8N1MD/AQI2U2Cm
+Yux2lsz2AAAAJXRFWHRkYXRlOmNyZWF0ZQAyMDI0LTA3LTE4VDA4OjMxOjE4KzAwOjAwPdC6HgAA
+ACV0RVh0ZGF0ZTptb2RpZnkAMjAyNC0wNy0xOFQwODozMToxOCswMDowMEyNAqIAAAAodEVYdGRh
+dGU6dGltZXN0YW1wADIwMjQtMDctMThUMDg6MzE6MTgrMDA6MDAbmCN9AAAAAElFTkSuQmCC" />
+</svg>

api/core/tools/provider/builtin/feishu_message/feishu_message.py

@@ -0,0 +1,15 @@
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class FeishuMessageProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict) -> None:
+        app_id = credentials.get('app_id')
+        app_secret = credentials.get('app_secret')
+        if not app_id or not app_secret:
+            raise ToolProviderCredentialValidationError("app_id and app_secret is required")
+        try:
+            assert FeishuRequest(app_id, app_secret).tenant_access_token is not None
+        except Exception as e:
+            raise ToolProviderCredentialValidationError(str(e))

api/core/tools/provider/builtin/feishu_message/feishu_message.yaml

@@ -0,0 +1,34 @@
+identity:
+  author: Doug Lea
+  name: feishu_message
+  label:
+    en_US: Lark Message
+    zh_Hans: 飞书消息
+  description:
+    en_US: Lark Message
+    zh_Hans: 飞书消息
+  icon: icon.svg
+  tags:
+    - social
+    - productivity
+credentials_for_provider:
+  app_id:
+    type: text-input
+    required: true
+    label:
+      en_US: APP ID
+    placeholder:
+      en_US: Please input your feishu app id
+      zh_Hans: 请输入你的飞书 app id
+    help:
+      en_US: Get your app_id and app_secret from Feishu
+      zh_Hans: 从飞书获取您的 app_id 和 app_secret
+    url: https://open.feishu.cn
+  app_secret:
+    type: secret-input
+    required: true
+    label:
+      en_US: APP Secret
+    placeholder:
+      en_US: Please input your app secret
+      zh_Hans: 请输入你的飞书 app secret

api/core/tools/provider/builtin/feishu_message/tools/send_bot_message.py

@@ -0,0 +1,20 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class SendBotMessageTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage:
+        app_id = self.runtime.credentials.get('app_id')
+        app_secret = self.runtime.credentials.get('app_secret')
+        client = FeishuRequest(app_id, app_secret)
+
+        receive_id_type = tool_parameters.get('receive_id_type')
+        receive_id = tool_parameters.get('receive_id')
+        msg_type = tool_parameters.get('msg_type')
+        content = tool_parameters.get('content')
+
+        res = client.send_bot_message(receive_id_type, receive_id, msg_type, content)
+        return self.create_json_message(res)

api/core/tools/provider/builtin/feishu_message/tools/send_bot_message.yaml

@@ -0,0 +1,91 @@
+identity:
+  name: send_bot_message
+  author: Doug Lea
+  label:
+    en_US: Send Bot Message
+    zh_Hans: 发送飞书应用消息
+description:
+  human:
+    en_US: Send bot message
+    zh_Hans: 发送飞书应用消息
+  llm: A tool for sending Feishu application messages.
+parameters:
+  - name: receive_id_type
+    type: select
+    required: true
+    options:
+      - value: open_id
+        label:
+          en_US: open id
+          zh_Hans: open id
+      - value: union_id
+        label:
+          en_US: union id
+          zh_Hans: union id
+      - value: user_id
+        label:
+          en_US: user id
+          zh_Hans: user id
+      - value: email
+        label:
+          en_US: email
+          zh_Hans: email
+      - value: chat_id
+        label:
+          en_US: chat id
+          zh_Hans: chat id
+    label:
+      en_US: User ID Type
+      zh_Hans: 用户 ID 类型
+    human_description:
+      en_US: User ID Type
+      zh_Hans: 用户 ID 类型，可选值有 open_id、union_id、user_id、email、chat_id。
+    llm_description: 用户 ID 类型，可选值有 open_id、union_id、user_id、email、chat_id。
+    form: llm
+
+  - name: receive_id
+    type: string
+    required: true
+    label:
+      en_US: Receive Id
+      zh_Hans: 消息接收者的 ID
+    human_description:
+      en_US: The ID of the message receiver. The ID type should correspond to the query parameter receive_id_type.
+      zh_Hans: 消息接收者的 ID，ID 类型应与查询参数 receive_id_type 对应。
+    llm_description: 消息接收者的 ID，ID 类型应与查询参数 receive_id_type 对应。
+    form: llm
+
+  - name: msg_type
+    type: string
+    required: true
+    options:
+      - value: text
+        label:
+          en_US: text
+          zh_Hans: 文本
+      - value: interactive
+        label:
+          en_US: message card
+          zh_Hans: 消息卡片
+    label:
+      en_US: Message type
+      zh_Hans: 消息类型
+    human_description:
+      en_US: Message type, optional values are, text (text), interactive (message card).
+      zh_Hans: 消息类型，可选值有：text(文本)、interactive(消息卡片)。
+    llm_description: 消息类型，可选值有：text(文本)、interactive(消息卡片)。
+    form: llm
+
+  - name: content
+    type: string
+    required: true
+    label:
+      en_US: Message content
+      zh_Hans: 消息内容
+    human_description:
+      en_US: Message content
+      zh_Hans: |
+        消息内容，JSON 结构序列化后的字符串。不同 msg_type 对应不同内容，
+        具体格式说明参考：https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json
+    llm_description: 消息内容，JSON 结构序列化后的字符串。不同 msg_type 对应不同内容。
+    form: llm

api/core/tools/provider/builtin/feishu_message/tools/send_webhook_message.py

@@ -0,0 +1,19 @@
+from typing import Any
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+from core.tools.utils.feishu_api_utils import FeishuRequest
+
+
+class SendWebhookMessageTool(BuiltinTool):
+    def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) ->ToolInvokeMessage:
+        app_id = self.runtime.credentials.get('app_id')
+        app_secret = self.runtime.credentials.get('app_secret')
+        client = FeishuRequest(app_id, app_secret)
+
+        webhook = tool_parameters.get('webhook')
+        msg_type = tool_parameters.get('msg_type')
+        content = tool_parameters.get('content')
+
+        res = client.send_webhook_message(webhook, msg_type, content)
+        return self.create_json_message(res)

api/core/tools/provider/builtin/feishu_message/tools/send_webhook_message.yaml

@@ -0,0 +1,58 @@
+identity:
+  name: send_webhook_message
+  author: Doug Lea
+  label:
+    en_US: Send Webhook Message
+    zh_Hans: 使用自定义机器人发送飞书消息
+description:
+  human:
+    en_US: Send webhook message
+    zh_Hans: 使用自定义机器人发送飞书消息
+  llm: A tool for sending Lark messages using a custom robot.
+parameters:
+  - name: webhook
+    type: string
+    required: true
+    label:
+      en_US: webhook
+      zh_Hans: webhook 的地址
+    human_description:
+      en_US: The address of the webhook
+      zh_Hans: webhook 的地址
+    llm_description: webhook 的地址
+    form: llm
+
+  - name: msg_type
+    type: string
+    required: true
+    options:
+      - value: text
+        label:
+          en_US: text
+          zh_Hans: 文本
+      - value: interactive
+        label:
+          en_US: message card
+          zh_Hans: 消息卡片
+    label:
+      en_US: Message type
+      zh_Hans: 消息类型
+    human_description:
+      en_US: Message type, optional values are, text (text), interactive (message card).
+      zh_Hans: 消息类型，可选值有：text(文本)、interactive(消息卡片)。
+    llm_description: 消息类型，可选值有：text(文本)、interactive(消息卡片)。
+    form: llm
+
+  - name: content
+    type: string
+    required: true
+    label:
+      en_US: Message content
+      zh_Hans: 消息内容
+    human_description:
+      en_US: Message content
+      zh_Hans: |
+        消息内容，JSON 结构序列化后的字符串。不同 msg_type 对应不同内容，
+        具体格式说明参考：https://open.larkoffice.com/document/server-docs/im-v1/message-content-description/create_json
+    llm_description: 消息内容，JSON 结构序列化后的字符串。不同 msg_type 对应不同内容。
+    form: llm

api/core/tools/provider/builtin/perplexity/_assets/icon.svg

@@ -0,0 +1,3 @@
+<svg width="400" height="400" viewBox="0 0 400 400" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path fill-rule="evenodd" clip-rule="evenodd" d="M101.008 42L190.99 124.905L190.99 124.886L190.99 42.1913H208.506L208.506 125.276L298.891 42V136.524L336 136.524V272.866H299.005V357.035L208.506 277.525L208.506 357.948H190.99L190.99 278.836L101.11 358V272.866H64V136.524H101.008V42ZM177.785 153.826H81.5159V255.564H101.088V223.472L177.785 153.826ZM118.625 231.149V319.392L190.99 255.655L190.99 165.421L118.625 231.149ZM209.01 254.812V165.336L281.396 231.068V272.866H281.489V318.491L209.01 254.812ZM299.005 255.564H318.484V153.826L222.932 153.826L299.005 222.751V255.564ZM281.375 136.524V81.7983L221.977 136.524L281.375 136.524ZM177.921 136.524H118.524V81.7983L177.921 136.524Z" fill="black"/>
+</svg>

api/core/tools/provider/builtin/perplexity/perplexity.py

@@ -0,0 +1,46 @@
+from typing import Any
+
+import requests
+
+from core.tools.errors import ToolProviderCredentialValidationError
+from core.tools.provider.builtin.perplexity.tools.perplexity_search import PERPLEXITY_API_URL
+from core.tools.provider.builtin_tool_provider import BuiltinToolProviderController
+
+
+class PerplexityProvider(BuiltinToolProviderController):
+    def _validate_credentials(self, credentials: dict[str, Any]) -> None:
+        headers = {
+            "Authorization": f"Bearer {credentials.get('perplexity_api_key')}",
+            "Content-Type": "application/json"
+        }
+        
+        payload = {
+            "model": "llama-3.1-sonar-small-128k-online",
+            "messages": [
+                {
+                    "role": "system",
+                    "content": "You are a helpful assistant."
+                },
+                {
+                    "role": "user",
+                    "content": "Hello"
+                }
+            ],
+            "max_tokens": 5,
+            "temperature": 0.1,
+            "top_p": 0.9,
+            "stream": False
+        }
+
+        try:
+            response = requests.post(PERPLEXITY_API_URL, json=payload, headers=headers)
+            response.raise_for_status()
+        except requests.RequestException as e:
+            raise ToolProviderCredentialValidationError(
+                f"Failed to validate Perplexity API key: {str(e)}"
+            )
+
+        if response.status_code != 200:
+            raise ToolProviderCredentialValidationError(
+                f"Perplexity API key is invalid. Status code: {response.status_code}"
+            )

api/core/tools/provider/builtin/perplexity/perplexity.yaml

@@ -0,0 +1,26 @@
+identity:
+  author: Dify
+  name: perplexity
+  label:
+    en_US: Perplexity
+    zh_Hans: Perplexity
+  description:
+    en_US: Perplexity.AI
+    zh_Hans: Perplexity.AI
+  icon: icon.svg
+  tags:
+    - search
+credentials_for_provider:
+  perplexity_api_key:
+    type: secret-input
+    required: true
+    label:
+      en_US: Perplexity API key
+      zh_Hans: Perplexity API key
+    placeholder:
+      en_US: Please input your Perplexity API key
+      zh_Hans: 请输入你的 Perplexity API key
+    help:
+      en_US: Get your Perplexity API key from Perplexity
+      zh_Hans: 从 Perplexity 获取您的 Perplexity API key
+    url: https://www.perplexity.ai/settings/api

api/core/tools/provider/builtin/perplexity/tools/perplexity_search.py

@@ -0,0 +1,72 @@
+import json
+from typing import Any, Union
+
+import requests
+
+from core.tools.entities.tool_entities import ToolInvokeMessage
+from core.tools.tool.builtin_tool import BuiltinTool
+
+PERPLEXITY_API_URL = "https://api.perplexity.ai/chat/completions"
+
+class PerplexityAITool(BuiltinTool):
+    def _parse_response(self, response: dict) -> dict:
+        """Parse the response from Perplexity AI API"""
+        if 'choices' in response and len(response['choices']) > 0:
+            message = response['choices'][0]['message']
+            return {
+                'content': message.get('content', ''),
+                'role': message.get('role', ''),
+                'citations': response.get('citations', [])
+            }
+        else:
+            return {'content': 'Unable to get a valid response', 'role': 'assistant', 'citations': []}
+
+    def _invoke(self,
+                user_id: str,
+                tool_parameters: dict[str, Any],
+                ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
+        headers = {
+            "Authorization": f"Bearer {self.runtime.credentials['perplexity_api_key']}",
+            "Content-Type": "application/json"
+        }
+        
+        payload = {
+            "model": tool_parameters.get('model', 'llama-3.1-sonar-small-128k-online'),
+            "messages": [
+                {
+                    "role": "system",
+                    "content": "Be precise and concise."
+                },
+                {
+                    "role": "user",
+                    "content": tool_parameters['query']
+                }
+            ],
+            "max_tokens": tool_parameters.get('max_tokens', 4096),
+            "temperature": tool_parameters.get('temperature', 0.7),
+            "top_p": tool_parameters.get('top_p', 1),
+            "top_k": tool_parameters.get('top_k', 5),
+            "presence_penalty": tool_parameters.get('presence_penalty', 0),
+            "frequency_penalty": tool_parameters.get('frequency_penalty', 1),
+            "stream": False
+        }
+        
+        if 'search_recency_filter' in tool_parameters:
+            payload['search_recency_filter'] = tool_parameters['search_recency_filter']
+        if 'return_citations' in tool_parameters:
+            payload['return_citations'] = tool_parameters['return_citations']
+        if 'search_domain_filter' in tool_parameters:
+            if isinstance(tool_parameters['search_domain_filter'], str):
+                payload['search_domain_filter'] = [tool_parameters['search_domain_filter']]
+            elif isinstance(tool_parameters['search_domain_filter'], list):
+                payload['search_domain_filter'] = tool_parameters['search_domain_filter']
+        
+
+        response = requests.post(url=PERPLEXITY_API_URL, json=payload, headers=headers)
+        response.raise_for_status()
+        valuable_res = self._parse_response(response.json())
+        
+        return [
+            self.create_json_message(valuable_res),
+            self.create_text_message(json.dumps(valuable_res, ensure_ascii=False, indent=2))
+        ]

api/core/tools/provider/builtin/perplexity/tools/perplexity_search.yaml

@@ -0,0 +1,178 @@
+identity:
+  name: perplexity
+  author: Dify
+  label:
+    en_US: Perplexity Search
+description:
+  human:
+    en_US: Search information using Perplexity AI's language models.
+  llm: This tool is used to search information using Perplexity AI's language models.
+parameters:
+  - name: query
+    type: string
+    required: true
+    label:
+      en_US: Query
+      zh_Hans: 查询
+    human_description:
+      en_US: The text query to be processed by the AI model.
+      zh_Hans: 要由 AI 模型处理的文本查询。
+    form: llm
+  - name: model
+    type: select
+    required: false
+    label:
+      en_US: Model Name
+      zh_Hans: 模型名称
+    human_description:
+      en_US: The Perplexity AI model to use for generating the response.
+      zh_Hans: 用于生成响应的 Perplexity AI 模型。
+    form: form
+    default: "llama-3.1-sonar-small-128k-online"
+    options:
+      - value: llama-3.1-sonar-small-128k-online
+        label:
+          en_US: llama-3.1-sonar-small-128k-online
+          zh_Hans: llama-3.1-sonar-small-128k-online
+      - value: llama-3.1-sonar-large-128k-online
+        label:
+          en_US: llama-3.1-sonar-large-128k-online
+          zh_Hans: llama-3.1-sonar-large-128k-online
+      - value: llama-3.1-sonar-huge-128k-online
+        label:
+          en_US: llama-3.1-sonar-huge-128k-online
+          zh_Hans: llama-3.1-sonar-huge-128k-online
+  - name: max_tokens
+    type: number
+    required: false
+    label:
+      en_US: Max Tokens
+      zh_Hans: 最大令牌数
+      pt_BR: Máximo de Tokens
+    human_description:
+      en_US: The maximum number of tokens to generate in the response.
+      zh_Hans: 在响应中生成的最大令牌数。
+      pt_BR: O número máximo de tokens a serem gerados na resposta.
+    form: form
+    default: 4096
+    min: 1
+    max: 4096
+  - name: temperature
+    type: number
+    required: false
+    label:
+      en_US: Temperature
+      zh_Hans: 温度
+      pt_BR: Temperatura
+    human_description:
+      en_US: Controls randomness in the output. Lower values make the output more focused and deterministic.
+      zh_Hans: 控制输出的随机性。较低的值使输出更加集中和确定。
+    form: form
+    default: 0.7
+    min: 0
+    max: 1
+  - name: top_k
+    type: number
+    required: false
+    label:
+      en_US: Top K
+      zh_Hans: 取样数量
+    human_description:
+      en_US: The number of top results to consider for response generation.
+      zh_Hans: 用于生成响应的顶部结果数量。
+    form: form
+    default: 5
+    min: 1
+    max: 100
+  - name: top_p
+    type: number
+    required: false
+    label:
+      en_US: Top P
+      zh_Hans: Top P
+    human_description:
+      en_US: Controls diversity via nucleus sampling.
+      zh_Hans: 通过核心采样控制多样性。
+    form: form
+    default: 1
+    min: 0.1
+    max: 1
+    step: 0.1
+  - name: presence_penalty
+    type: number
+    required: false
+    label:
+      en_US: Presence Penalty
+      zh_Hans: 存在惩罚
+    human_description:
+      en_US: Positive values penalize new tokens based on whether they appear in the text so far.
+      zh_Hans: 正值会根据新词元是否已经出现在文本中来对其进行惩罚。
+    form: form
+    default: 0
+    min: -1.0
+    max: 1.0
+    step: 0.1
+  - name: frequency_penalty
+    type: number
+    required: false
+    label:
+      en_US: Frequency Penalty
+      zh_Hans: 频率惩罚
+    human_description:
+      en_US: Positive values penalize new tokens based on their existing frequency in the text so far.
+      zh_Hans: 正值会根据新词元在文本中已经出现的频率来对其进行惩罚。
+    form: form
+    default: 1
+    min: 0.1
+    max: 1.0
+    step: 0.1
+  - name: return_citations
+    type: boolean
+    required: false
+    label:
+      en_US: Return Citations
+      zh_Hans: 返回引用
+    human_description:
+      en_US: Whether to return citations in the response.
+      zh_Hans: 是否在响应中返回引用。
+    form: form
+    default: true
+  - name: search_domain_filter
+    type: string
+    required: false
+    label:
+      en_US: Search Domain Filter
+      zh_Hans: 搜索域过滤器
+    human_description:
+      en_US: Domain to filter the search results.
+      zh_Hans: 用于过滤搜索结果的域名。
+    form: form
+    default: ""
+  - name: search_recency_filter
+    type: select
+    required: false
+    label:
+      en_US: Search Recency Filter
+      zh_Hans: 搜索时间过滤器
+    human_description:
+      en_US: Filter for search results based on recency.
+      zh_Hans: 基于时间筛选搜索结果。
+    form: form
+    default: "month"
+    options:
+      - value: day
+        label:
+          en_US: Day
+          zh_Hans: 天
+      - value: week
+        label:
+          en_US: Week
+          zh_Hans: 周
+      - value: month
+        label:
+          en_US: Month
+          zh_Hans: 月
+      - value: year
+        label:
+          en_US: Year
+          zh_Hans: 年

api/core/tools/utils/feishu_api_utils.py

@@ -0,0 +1,143 @@
+import httpx
+
+from extensions.ext_redis import redis_client
+
+
+class FeishuRequest:
+    def __init__(self, app_id: str, app_secret: str):
+        self.app_id = app_id
+        self.app_secret = app_secret
+
+    @property
+    def tenant_access_token(self):
+        feishu_tenant_access_token = f"tools:{self.app_id}:feishu_tenant_access_token"
+        if redis_client.exists(feishu_tenant_access_token):
+            return redis_client.get(feishu_tenant_access_token).decode()
+        res = self.get_tenant_access_token(self.app_id, self.app_secret)
+        redis_client.setex(feishu_tenant_access_token, res.get("expire"), res.get("tenant_access_token"))
+        return res.get("tenant_access_token")
+
+    def _send_request(self, url: str, method: str = "post", require_token: bool = True, payload: dict = None,
+                      params: dict = None):
+        headers = {
+            "Content-Type": "application/json",
+            "user-agent": "Dify",
+        }
+        if require_token:
+            headers["tenant-access-token"] = f"{self.tenant_access_token}"
+        res = httpx.request(method=method, url=url, headers=headers, json=payload, params=params, timeout=30).json()
+        if res.get("code") != 0:
+            raise Exception(res)
+        return res
+
+    def get_tenant_access_token(self, app_id: str, app_secret: str) -> dict:
+        """
+        API url: https://open.feishu.cn/document/server-docs/authentication-management/access-token/tenant_access_token_internal
+        Example Response:
+        {
+            "code": 0,
+            "msg": "ok",
+            "tenant_access_token": "t-caecc734c2e3328a62489fe0648c4b98779515d3",
+            "expire": 7200
+        }
+        """
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/access_token/get_tenant_access_token"
+        payload = {
+            "app_id": app_id,
+            "app_secret": app_secret
+        }
+        res = self._send_request(url, require_token=False, payload=payload)
+        return res
+
+    def create_document(self, title: str, content: str, folder_token: str) -> dict:
+        """
+        API url: https://open.larkoffice.com/document/server-docs/docs/docs/docx-v1/document/create
+        Example Response:
+        {
+            "data": {
+                "title": "title",
+                "url": "https://svi136aogf123.feishu.cn/docx/VWbvd4fEdoW0WSxaY1McQTz8n7d",
+                "type": "docx",
+                "token": "VWbvd4fEdoW0WSxaY1McQTz8n7d"
+            },
+            "log_id": "021721281231575fdbddc0200ff00060a9258ec0000103df61b5d",
+            "code": 0,
+            "msg": "创建飞书文档成功，请查看"
+        }
+        """
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/document/create_document"
+        payload = {
+            "title": title,
+            "content": content,
+            "folder_token": folder_token,
+        }
+        res = self._send_request(url, payload=payload)
+        return res.get("data")
+
+    def write_document(self, document_id: str, content: str, position: str = "start") -> dict:
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/document/write_document"
+        payload = {
+            "document_id": document_id,
+            "content": content,
+            "position": position
+        }
+        res = self._send_request(url, payload=payload)
+        return res.get("data")
+
+    def get_document_raw_content(self, document_id: str) -> dict:
+        """
+        API url: https://open.larkoffice.com/document/server-docs/docs/docs/docx-v1/document/raw_content
+        Example Response:
+        {
+            "code": 0,
+            "msg": "success",
+            "data": {
+                "content": "云文档\n多人实时协同，插入一切元素。不仅是在线文档，更是强大的创作和互动工具\n云文档：专为协作而生\n"
+            }
+        }
+        """
+        params = {
+            "document_id": document_id,
+        }
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/document/get_document_raw_content"
+        res = self._send_request(url, method="get", params=params)
+        return res.get("data").get("content")
+
+    def list_document_block(self, document_id: str, page_token: str, page_size: int = 500) -> dict:
+        """
+        API url: https://open.larkoffice.com/document/server-docs/docs/docs/docx-v1/document/list
+        """
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/document/list_document_block"
+        params = {
+            "document_id": document_id,
+            "page_size": page_size,
+            "page_token": page_token,
+        }
+        res = self._send_request(url, method="get", params=params)
+        return res.get("data")
+
+    def send_bot_message(self, receive_id_type: str, receive_id: str, msg_type: str, content: str) -> dict:
+        """
+        API url: https://open.larkoffice.com/document/server-docs/im-v1/message/create
+        """
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/message/send_bot_message"
+        params = {
+            "receive_id_type": receive_id_type,
+        }
+        payload = {
+            "receive_id": receive_id,
+            "msg_type": msg_type,
+            "content": content,
+        }
+        res = self._send_request(url, params=params, payload=payload)
+        return res.get("data")
+
+    def send_webhook_message(self, webhook: str, msg_type: str, content: str) -> dict:
+        url = "https://lark-plugin-api.solutionsuite.cn/lark-plugin/message/send_webhook_message"
+        payload = {
+            "webhook": webhook,
+            "msg_type": msg_type,
+            "content": content,
+        }
+        res = self._send_request(url, require_token=False, payload=payload)
+        return res

api/core/tools/utils/yaml_utils.py

@@ -26,7 +26,6 @@ def load_yaml_file(file_path: str, ignore_error: bool = True, default_value: Any
                 raise YAMLError(f'Failed to load YAML file {file_path}: {e}')
     except Exception as e:
         if ignore_error:
-            logger.debug(f'Failed to load YAML file {file_path}: {e}')
             return default_value
         else:
             raise e

api/core/workflow/nodes/code/code_node.py

@@ -88,9 +88,9 @@ class CodeNode(BaseNode):
             else:
                 raise ValueError(f"Output variable `{variable}` must be a string")
         
-        if len(value) > dify_config.CODE_MAX_STRING_ARRAY_LENGTH:
+        if len(value) > dify_config.CODE_MAX_STRING_LENGTH:
             raise ValueError(f'The length of output variable `{variable}` must be'
-                             f' less than {dify_config.CODE_MAX_STRING_ARRAY_LENGTH} characters')
+                             f' less than {dify_config.CODE_MAX_STRING_LENGTH} characters')
 
         return value.replace('\x00', '')
 

api/core/workflow/nodes/http_request/entities.py

@@ -5,10 +5,6 @@ from pydantic import BaseModel, ValidationInfo, field_validator
 from configs import dify_config
 from core.workflow.entities.base_node_data_entities import BaseNodeData
 
-MAX_CONNECT_TIMEOUT = dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT
-MAX_READ_TIMEOUT = dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT
-MAX_WRITE_TIMEOUT = dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT
-
 
 class HttpRequestNodeAuthorizationConfig(BaseModel):
     type: Literal[None, 'basic', 'bearer', 'custom']
@@ -41,9 +37,9 @@ class HttpRequestNodeBody(BaseModel):
 
 
 class HttpRequestNodeTimeout(BaseModel):
-    connect: int = MAX_CONNECT_TIMEOUT
-    read: int = MAX_READ_TIMEOUT
-    write: int = MAX_WRITE_TIMEOUT
+    connect: int = dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT
+    read: int = dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT
+    write: int = dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT
 
 
 class HttpRequestNodeData(BaseNodeData):

api/core/workflow/nodes/http_request/http_request_node.py

@@ -3,6 +3,7 @@ from mimetypes import guess_extension
 from os import path
 from typing import cast
 
+from configs import dify_config
 from core.app.segments import parser
 from core.file.file_obj import FileTransferMethod, FileType, FileVar
 from core.tools.tool_file_manager import ToolFileManager
@@ -11,9 +12,6 @@ from core.workflow.entities.node_entities import NodeRunResult, NodeType
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.nodes.base_node import BaseNode
 from core.workflow.nodes.http_request.entities import (
-    MAX_CONNECT_TIMEOUT,
-    MAX_READ_TIMEOUT,
-    MAX_WRITE_TIMEOUT,
     HttpRequestNodeData,
     HttpRequestNodeTimeout,
 )
@@ -21,9 +19,9 @@ from core.workflow.nodes.http_request.http_executor import HttpExecutor, HttpExe
 from models.workflow import WorkflowNodeExecutionStatus
 
 HTTP_REQUEST_DEFAULT_TIMEOUT = HttpRequestNodeTimeout(
-    connect=min(10, MAX_CONNECT_TIMEOUT),
-    read=min(60, MAX_READ_TIMEOUT),
-    write=min(20, MAX_WRITE_TIMEOUT),
+    connect=dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
+    read=dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
+    write=dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
 )
 
 
@@ -43,9 +41,9 @@ class HttpRequestNode(BaseNode):
                 'body': {'type': 'none'},
                 'timeout': {
                     **HTTP_REQUEST_DEFAULT_TIMEOUT.model_dump(),
-                    'max_connect_timeout': MAX_CONNECT_TIMEOUT,
-                    'max_read_timeout': MAX_READ_TIMEOUT,
-                    'max_write_timeout': MAX_WRITE_TIMEOUT,
+                    'max_connect_timeout': dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
+                    'max_read_timeout': dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
+                    'max_write_timeout': dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
                 },
             },
         }
@@ -92,17 +90,15 @@ class HttpRequestNode(BaseNode):
             },
         )
 
-    def _get_request_timeout(self, node_data: HttpRequestNodeData) -> HttpRequestNodeTimeout:
+    @staticmethod
+    def _get_request_timeout(node_data: HttpRequestNodeData) -> HttpRequestNodeTimeout:
         timeout = node_data.timeout
         if timeout is None:
             return HTTP_REQUEST_DEFAULT_TIMEOUT
 
         timeout.connect = timeout.connect or HTTP_REQUEST_DEFAULT_TIMEOUT.connect
-        timeout.connect = min(timeout.connect, MAX_CONNECT_TIMEOUT)
         timeout.read = timeout.read or HTTP_REQUEST_DEFAULT_TIMEOUT.read
-        timeout.read = min(timeout.read, MAX_READ_TIMEOUT)
         timeout.write = timeout.write or HTTP_REQUEST_DEFAULT_TIMEOUT.write
-        timeout.write = min(timeout.write, MAX_WRITE_TIMEOUT)
         return timeout
 
     @classmethod

api/core/workflow/nodes/variable_aggregator/entities.py

@@ -17,7 +17,7 @@ class AdvancedSettings(BaseModel):
         """
         Group.
         """
-        output_type: Literal['string', 'number', 'array', 'object']
+        output_type: Literal['string', 'number', 'object', 'array[string]', 'array[number]', 'array[object]']
         variables: list[list[str]]
         group_name: str
 
@@ -30,4 +30,4 @@ class VariableAssignerNodeData(BaseNodeData):
     type: str = 'variable-assigner'
     output_type: str
     variables: list[list[str]]
-    advanced_settings: Optional[AdvancedSettings] = None
+    advanced_settings: Optional[AdvancedSettings] = None

api/events/event_handlers/create_site_record_when_app_created.py

@@ -17,6 +17,8 @@ def handle(sender, **kwargs):
         default_language=account.interface_language,
         customize_token_strategy="not_allow",
         code=Site.generate_code(16),
+        created_by=app.created_by,
+        updated_by=app.updated_by,
     )
 
     db.session.add(site)

api/extensions/ext_sentry.py

@@ -1,3 +1,4 @@
+import openai
 import sentry_sdk
 from sentry_sdk.integrations.celery import CeleryIntegration
 from sentry_sdk.integrations.flask import FlaskIntegration
@@ -9,7 +10,7 @@ def init_app(app):
         sentry_sdk.init(
             dsn=app.config.get("SENTRY_DSN"),
             integrations=[FlaskIntegration(), CeleryIntegration()],
-            ignore_errors=[HTTPException, ValueError],
+            ignore_errors=[HTTPException, ValueError, openai.APIStatusError],
             traces_sample_rate=app.config.get("SENTRY_TRACES_SAMPLE_RATE", 1.0),
             profiles_sample_rate=app.config.get("SENTRY_PROFILES_SAMPLE_RATE", 1.0),
             environment=app.config.get("DEPLOY_ENV"),

api/extensions/storage/aliyun_storage.py

@@ -15,6 +15,7 @@ class AliyunStorage(BaseStorage):
 
         app_config = self.app.config
         self.bucket_name = app_config.get("ALIYUN_OSS_BUCKET_NAME")
+        self.folder = app.config.get("ALIYUN_OSS_PATH")
         oss_auth_method = aliyun_s3.Auth
         region = None
         if app_config.get("ALIYUN_OSS_AUTH_VERSION") == "v4":
@@ -30,15 +31,29 @@ class AliyunStorage(BaseStorage):
         )
 
     def save(self, filename, data):
+        if not self.folder or self.folder.endswith("/"):
+            filename = self.folder + filename
+        else:
+            filename = self.folder + "/" + filename
         self.client.put_object(filename, data)
 
     def load_once(self, filename: str) -> bytes:
+        if not self.folder or self.folder.endswith("/"):
+            filename = self.folder + filename
+        else:
+            filename = self.folder + "/" + filename
+
         with closing(self.client.get_object(filename)) as obj:
             data = obj.read()
         return data
 
     def load_stream(self, filename: str) -> Generator:
         def generate(filename: str = filename) -> Generator:
+            if not self.folder or self.folder.endswith("/"):
+                filename = self.folder + filename
+            else:
+                filename = self.folder + "/" + filename
+
             with closing(self.client.get_object(filename)) as obj:
                 while chunk := obj.read(4096):
                     yield chunk
@@ -46,10 +61,24 @@ class AliyunStorage(BaseStorage):
         return generate()
 
     def download(self, filename, target_filepath):
+        if not self.folder or self.folder.endswith("/"):
+            filename = self.folder + filename
+        else:
+            filename = self.folder + "/" + filename
+
         self.client.get_object_to_file(filename, target_filepath)
 
     def exists(self, filename):
+        if not self.folder or self.folder.endswith("/"):
+            filename = self.folder + filename
+        else:
+            filename = self.folder + "/" + filename
+
         return self.client.object_exists(filename)
 
     def delete(self, filename):
+        if not self.folder or self.folder.endswith("/"):
+            filename = self.folder + filename
+        else:
+            filename = self.folder + "/" + filename
         self.client.delete_object(filename)