Merge branch 'fix/remove-refreshing-sign' into deploy/dev

api/.ruff.toml

@@ -85,11 +85,11 @@ ignore = [
 ]
 "tests/*" = [
     "F811", # redefined-while-unused
-    "F401", # unused-import
 ]
 
 [lint.pyflakes]
-extend-generics = [
+allowed-unused-imports = [
     "_pytest.monkeypatch",
     "tests.integration_tests",
+    "tests.unit_tests",
 ]

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 expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/controllers/console/app/workflow.py

@@ -2,7 +2,7 @@
 import logging
 
 from flask import abort, request
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_restful import Resource, inputs, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
@@ -14,7 +14,7 @@
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from factories import variable_factory
-from fields.workflow_fields import workflow_fields
+from fields.workflow_fields import workflow_fields, workflow_pagination_fields
 from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
 from libs.helper import TimestampField, uuid_value
@@ -440,6 +440,31 @@ def get(self, app_model: App):
         }
 
 
+class PublishedAllWorkflowApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_pagination_fields)
+    def get(self, app_model: App):
+        """
+        Get published workflows
+        """
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("page", type=inputs.int_range(1, 99999), required=False, default=1, location="args")
+        parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
+        args = parser.parse_args()
+        page = args.get("page")
+        limit = args.get("limit")
+        workflow_service = WorkflowService()
+        workflows, has_more = workflow_service.get_all_published_workflow(app_model=app_model, page=page, limit=limit)
+
+        return {"items": workflows, "page": page, "limit": limit, "has_more": has_more}
+
+
 api.add_resource(DraftWorkflowApi, "/apps/<uuid:app_id>/workflows/draft")
 api.add_resource(WorkflowConfigApi, "/apps/<uuid:app_id>/workflows/draft/config")
 api.add_resource(AdvancedChatDraftWorkflowRunApi, "/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
@@ -454,6 +479,7 @@ def get(self, app_model: App):
     WorkflowDraftRunIterationNodeApi, "/apps/<uuid:app_id>/workflows/draft/iteration/nodes/<string:node_id>/run"
 )
 api.add_resource(PublishedWorkflowApi, "/apps/<uuid:app_id>/workflows/publish")
+api.add_resource(PublishedAllWorkflowApi, "/apps/<uuid:app_id>/workflows")
 api.add_resource(DefaultBlockConfigsApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs")
 api.add_resource(
     DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>"

api/controllers/console/explore/message.py

@@ -66,10 +66,17 @@ def post(self, installed_app, message_id):
 
         parser = reqparse.RequestParser()
         parser.add_argument("rating", type=str, choices=["like", "dislike", None], location="json")
+        parser.add_argument("content", type=str, location="json")
         args = parser.parse_args()
 
         try:
-            MessageService.create_feedback(app_model, message_id, current_user, args.get("rating"), args.get("content"))
+            MessageService.create_feedback(
+                app_model=app_model,
+                message_id=message_id,
+                user=current_user,
+                rating=args.get("rating"),
+                content=args.get("content"),
+            )
         except services.errors.message.MessageNotExistsError:
             raise NotFound("Message Not Exists.")
 

api/controllers/console/workspace/members.py

@@ -122,7 +122,7 @@ def put(self, member_id):
             return {"code": "invalid-role", "message": "Invalid role"}, 400
 
         member = db.session.get(Account, str(member_id))
-        if member:
+        if not member:
             abort(404)
 
         try:

api/controllers/service_api/app/message.py

@@ -108,7 +108,13 @@ def post(self, app_model: App, end_user: EndUser, message_id):
         args = parser.parse_args()
 
         try:
-            MessageService.create_feedback(app_model, message_id, end_user, args.get("rating"), args.get("content"))
+            MessageService.create_feedback(
+                app_model=app_model,
+                message_id=message_id,
+                user=end_user,
+                rating=args.get("rating"),
+                content=args.get("content"),
+            )
         except services.errors.message.MessageNotExistsError:
             raise NotFound("Message Not Exists.")
 

api/controllers/service_api/dataset/document.py

@@ -8,12 +8,16 @@
 import services.dataset_service
 from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
-from controllers.service_api.app.error import ProviderNotInitializeError
+from controllers.service_api.app.error import (
+    FileTooLargeError,
+    NoFileUploadedError,
+    ProviderNotInitializeError,
+    TooManyFilesError,
+    UnsupportedFileTypeError,
+)
 from controllers.service_api.dataset.error import (
     ArchivedDocumentImmutableError,
     DocumentIndexingError,
-    NoFileUploadedError,
-    TooManyFilesError,
 )
 from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
@@ -238,13 +242,18 @@ def post(self, tenant_id, dataset_id, document_id):
             if not file.filename:
                 raise FilenameNotExistsError
 
-            upload_file = FileService.upload_file(
-                filename=file.filename,
-                content=file.read(),
-                mimetype=file.mimetype,
-                user=current_user,
-                source="datasets",
-            )
+            try:
+                upload_file = FileService.upload_file(
+                    filename=file.filename,
+                    content=file.read(),
+                    mimetype=file.mimetype,
+                    user=current_user,
+                    source="datasets",
+                )
+            except services.errors.file.FileTooLargeError as file_too_large_error:
+                raise FileTooLargeError(file_too_large_error.description)
+            except services.errors.file.UnsupportedFileTypeError:
+                raise UnsupportedFileTypeError()
             data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
             args["data_source"] = data_source
         # validate args

api/core/agent/base_agent_runner.py

@@ -339,13 +339,13 @@ def save_agent_thought(
             raise ValueError(f"Agent thought {agent_thought.id} not found")
         agent_thought = queried_thought
 
-        if thought is not None:
+        if thought:
             agent_thought.thought = thought
 
-        if tool_name is not None:
+        if tool_name:
             agent_thought.tool = tool_name
 
-        if tool_input is not None:
+        if tool_input:
             if isinstance(tool_input, dict):
                 try:
                     tool_input = json.dumps(tool_input, ensure_ascii=False)
@@ -354,7 +354,7 @@ def save_agent_thought(
 
             agent_thought.tool_input = tool_input
 
-        if observation is not None:
+        if observation:
             if isinstance(observation, dict):
                 try:
                     observation = json.dumps(observation, ensure_ascii=False)
@@ -363,7 +363,7 @@ def save_agent_thought(
 
             agent_thought.observation = observation
 
-        if answer is not None:
+        if answer:
             agent_thought.answer = answer
 
         if messages_ids is not None and len(messages_ids) > 0:

api/core/model_runtime/model_providers/wenxin/_common.py

@@ -122,6 +122,7 @@ class _CommonWenxin:
         "bge-large-zh": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/bge_large_zh",
         "tao-8k": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/tao_8k",
         "bce-reranker-base_v1": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/reranker/bce_reranker_base",
+        "ernie-lite-pro-128k": "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-lite-pro-128k",
     }
 
     function_calling_supports = [

api/core/model_runtime/model_providers/wenxin/llm/ernie-lite-pro-128k.yaml

@@ -0,0 +1,42 @@
+model: ernie-lite-pro-128k
+label:
+  en_US: Ernie-Lite-Pro-128K
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.1
+    max: 1.0
+    default: 0.8
+  - name: top_p
+    use_template: top_p
+  - name: min_output_tokens
+    label:
+      en_US: "Min Output Tokens"
+      zh_Hans: "最小输出Token数"
+    use_template: max_tokens
+    min: 2
+    max: 2048
+    help:
+      zh_Hans: 指定模型最小输出token数
+      en_US: Specifies the lower limit on the length of generated results.
+  - name: max_output_tokens
+    label:
+      en_US: "Max Output Tokens"
+      zh_Hans: "最大输出Token数"
+    use_template: max_tokens
+    min: 2
+    max: 2048
+    default: 2048
+    help:
+      zh_Hans: 指定模型最大输出token数
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty

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

@@ -1,5 +1,5 @@
 import re
-from typing import Optional
+from typing import Optional, cast
 
 
 class JiebaKeywordTableHandler:
@@ -8,18 +8,20 @@ def __init__(self):
 
         from core.rag.datasource.keyword.jieba.stopwords import STOPWORDS
 
-        jieba.analyse.default_tfidf.stop_words = STOPWORDS
+        jieba.analyse.default_tfidf.stop_words = STOPWORDS  # type: ignore
 
     def extract_keywords(self, text: str, max_keywords_per_chunk: Optional[int] = 10) -> set[str]:
         """Extract keywords with JIEBA tfidf."""
-        import jieba  # type: ignore
+        import jieba.analyse  # type: ignore
 
         keywords = jieba.analyse.extract_tags(
             sentence=text,
             topK=max_keywords_per_chunk,
         )
+        # jieba.analyse.extract_tags returns list[Any] when withFlag is False by default.
+        keywords = cast(list[str], keywords)
 
-        return set(self._expand_tokens_with_subtokens(keywords))
+        return set(self._expand_tokens_with_subtokens(set(keywords)))
 
     def _expand_tokens_with_subtokens(self, tokens: set[str]) -> set[str]:
         """Get subtokens from a list of tokens., filtering for stopwords."""

api/core/rag/extractor/notion_extractor.py

@@ -138,17 +138,24 @@ def _get_notion_block_data(self, page_id: str) -> list[str]:
         block_url = BLOCK_CHILD_URL_TMPL.format(block_id=page_id)
         while True:
             query_dict: dict[str, Any] = {} if not start_cursor else {"start_cursor": start_cursor}
-            res = requests.request(
-                "GET",
-                block_url,
-                headers={
-                    "Authorization": "Bearer " + self._notion_access_token,
-                    "Content-Type": "application/json",
-                    "Notion-Version": "2022-06-28",
-                },
-                params=query_dict,
-            )
-            data = res.json()
+            try:
+                res = requests.request(
+                    "GET",
+                    block_url,
+                    headers={
+                        "Authorization": "Bearer " + self._notion_access_token,
+                        "Content-Type": "application/json",
+                        "Notion-Version": "2022-06-28",
+                    },
+                    params=query_dict,
+                )
+                if res.status_code != 200:
+                    raise ValueError(f"Error fetching Notion block data: {res.text}")
+                data = res.json()
+            except requests.RequestException as e:
+                raise ValueError("Error fetching Notion block data") from e
+            if "results" not in data or not isinstance(data["results"], list):
+                raise ValueError("Error fetching Notion block data")
             for result in data["results"]:
                 result_type = result["type"]
                 result_obj = result[result_type]

api/core/tools/provider/builtin/aws/tools/bedrock_retrieve.py

@@ -21,7 +21,7 @@ def _bedrock_retrieve(
 
             retrieval_configuration = {"vectorSearchConfiguration": {"numberOfResults": num_results}}
 
-            # 如果有元数据过滤条件，则添加到检索配置中
+            # Add metadata filter to retrieval configuration if present
             if metadata_filter:
                 retrieval_configuration["vectorSearchConfiguration"]["filter"] = metadata_filter
 
@@ -77,7 +77,7 @@ def _invoke(
             if not query:
                 return self.create_text_message("Please input query")
 
-            # 获取元数据过滤条件（如果存在）
+            # Get metadata filter conditions (if they exist)
             metadata_filter_str = tool_parameters.get("metadata_filter")
             metadata_filter = json.loads(metadata_filter_str) if metadata_filter_str else None
 
@@ -86,7 +86,7 @@ def _invoke(
                 query_input=query,
                 knowledge_base_id=self.knowledge_base_id,
                 num_results=self.topk,
-                metadata_filter=metadata_filter,  # 将元数据过滤条件传递给检索方法
+                metadata_filter=metadata_filter,
             )
 
             line = 5
@@ -109,7 +109,7 @@ def validate_parameters(self, parameters: dict[str, Any]) -> None:
         if not parameters.get("query"):
             raise ValueError("query is required")
 
-        # 可选：可以验证元数据过滤条件是否为有效的 JSON 字符串（如果提供）
+        # Optional: Validate if metadata filter is a valid JSON string (if provided)
         metadata_filter_str = parameters.get("metadata_filter")
         if metadata_filter_str and not isinstance(json.loads(metadata_filter_str), dict):
             raise ValueError("metadata_filter must be a valid JSON object")

api/core/tools/provider/builtin/aws/tools/bedrock_retrieve.yaml

@@ -73,9 +73,9 @@ parameters:
     llm_description: AWS region where the Bedrock Knowledge Base is located
     form: form
 
-  - name: metadata_filter
-    type: string
-    required: false
+  - name: metadata_filter   # Additional parameter for metadata filtering
+    type: string            # String type, expects JSON-formatted filter conditions
+    required: false         # Optional field - can be omitted
     label:
       en_US: Metadata Filter
       zh_Hans: 元数据过滤器

api/core/tools/provider/builtin/aws/tools/sagemaker_chinese_toxicity_detector.py

@@ -6,8 +6,8 @@
 from core.tools.entities.tool_entities import ToolInvokeMessage
 from core.tools.tool.builtin_tool import BuiltinTool
 
-# 定义标签映射
-LABEL_MAPPING = {"LABEL_0": "SAFE", "LABEL_1": "NO_SAFE"}
+# Define label mappings
+LABEL_MAPPING = {0: "SAFE", 1: "NO_SAFE"}
 
 
 class ContentModerationTool(BuiltinTool):
@@ -28,12 +28,12 @@ def _invoke_sagemaker(self, payload: dict, endpoint: str):
         # Handle nested JSON if present
         if isinstance(json_obj, dict) and "body" in json_obj:
             body_content = json.loads(json_obj["body"])
-            raw_label = body_content.get("label")
+            prediction_result = body_content.get("prediction")
         else:
-            raw_label = json_obj.get("label")
+            prediction_result = json_obj.get("prediction")
 
-        # 映射标签并返回
-        result = LABEL_MAPPING.get(raw_label, "NO_SAFE")  # 如果映射中没有找到，默认返回NO_SAFE
+        # Map labels and return
+        result = LABEL_MAPPING.get(prediction_result, "NO_SAFE")  # If not found in mapping, default to NO_SAFE
         return result
 
     def _invoke(