From 2c51e3a3275092603ba5f9548e4aea7f5e99ebf7 Mon Sep 17 00:00:00 2001 From: NFish Date: Thu, 29 Aug 2024 15:57:43 +0800 Subject: [PATCH 01/21] fix: webapp sso setting may not the latest value when refresh (#7795) --- .../app/(appDetailLayout)/[appId]/layout.tsx | 2 +- .../app/(appDetailLayout)/[appId]/overview/cardView.tsx | 2 +- web/app/components/app/overview/appCard.tsx | 9 ++++----- 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/layout.tsx b/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/layout.tsx index 84ec157323dea2..8723420d849e19 100644 --- a/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/layout.tsx +++ b/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/layout.tsx @@ -128,7 +128,7 @@ const AppDetailLayout: FC = (props) => { if (e.status === 404) router.replace('/apps') }) - }, [appId, isCurrentWorkspaceEditor]) + }, [appId, isCurrentWorkspaceEditor, systemFeatures]) useUnmount(() => { setAppDetail() diff --git a/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/overview/cardView.tsx b/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/overview/cardView.tsx index 3584e137330c99..8f3ee510b86036 100644 --- a/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/overview/cardView.tsx +++ b/web/app/(commonLayout)/app/(appDetailLayout)/[appId]/overview/cardView.tsx @@ -95,7 +95,7 @@ const CardView: FC = ({ appId }) => { if (systemFeatures.enable_web_sso_switch_component) { const [sso_err] = await asyncRunSafe( - updateAppSSO({ id: appId, enabled: params.enable_sso }) as Promise, + updateAppSSO({ id: appId, enabled: Boolean(params.enable_sso) }) as Promise, ) if (sso_err) { handleCallbackResult(sso_err) diff --git a/web/app/components/app/overview/appCard.tsx b/web/app/components/app/overview/appCard.tsx index 0d0b95c0a06dbc..f9f5c1fbfff03a 100644 --- a/web/app/components/app/overview/appCard.tsx +++ b/web/app/components/app/overview/appCard.tsx @@ -134,8 +134,8 @@ function AppCard({ return (
@@ -176,7 +176,6 @@ function AppCard({ {isApp && } {/* button copy link/ button regenerate */} @@ -202,8 +201,8 @@ function AppCard({ onClick={() => setShowConfirmDelete(true)} >
From 962cdbbebd9e0614ea05593aed785faa063d7cf4 Mon Sep 17 00:00:00 2001 From: Yeuoly <45712896+Yeuoly@users.noreply.github.com> Date: Thu, 29 Aug 2024 16:04:01 +0800 Subject: [PATCH 02/21] chore: add app generator overload (#7792) --- .../app/apps/advanced_chat/app_generator.py | 22 ++++++++++++++++- api/core/app/apps/agent_chat/app_generator.py | 20 +++++++++++++++- api/core/app/apps/chat/app_generator.py | 22 +++++++++++++++-- api/core/app/apps/completion/app_generator.py | 24 ++++++++++++++++--- api/core/app/apps/workflow/app_generator.py | 24 +++++++++++++++++-- 5 files changed, 103 insertions(+), 9 deletions(-) diff --git a/api/core/app/apps/advanced_chat/app_generator.py b/api/core/app/apps/advanced_chat/app_generator.py index 5a1e5973cd46ea..e7c9ebe09749de 100644 --- a/api/core/app/apps/advanced_chat/app_generator.py +++ b/api/core/app/apps/advanced_chat/app_generator.py @@ -4,7 +4,7 @@ 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 @@ 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, diff --git a/api/core/app/apps/agent_chat/app_generator.py b/api/core/app/apps/agent_chat/app_generator.py index 53780bdfb003b2..daf37f4a50dd31 100644 --- a/api/core/app/apps/agent_chat/app_generator.py +++ b/api/core/app/apps/agent_chat/app_generator.py @@ -3,7 +3,7 @@ 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 @@ 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, diff --git a/api/core/app/apps/chat/app_generator.py b/api/core/app/apps/chat/app_generator.py index 5b896e28455340..ab15928b744b61 100644 --- a/api/core/app/apps/chat/app_generator.py +++ b/api/core/app/apps/chat/app_generator.py @@ -3,7 +3,7 @@ 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 @@ 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. diff --git a/api/core/app/apps/completion/app_generator.py b/api/core/app/apps/completion/app_generator.py index c4e1caf65a9679..c0b13b40fdb0d6 100644 --- a/api/core/app/apps/completion/app_generator.py +++ b/api/core/app/apps/completion/app_generator.py @@ -3,7 +3,7 @@ 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 @@ 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 @@ def generate_more_like_this(self, app_model: App, 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. diff --git a/api/core/app/apps/workflow/app_generator.py b/api/core/app/apps/workflow/app_generator.py index df40aec154a856..26bb6c0f4f70b8 100644 --- a/api/core/app/apps/workflow/app_generator.py +++ b/api/core/app/apps/workflow/app_generator.py @@ -4,7 +4,7 @@ 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 @@ 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 @@ def _generate( 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. From f0273f00e18d023fd6270307f9eb5c1030567e1b Mon Sep 17 00:00:00 2001 From: hisir Date: Thu, 29 Aug 2024 18:58:19 +0800 Subject: [PATCH 03/21] Fixed when testing the openai compatible interface model, an error is reported when no object is returned (#7808) --- .../model_providers/openai_api_compatible/llm/llm.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py b/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py index 2b729d42932bdb..6279125f46ffa0 100644 --- a/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py +++ b/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py @@ -150,9 +150,9 @@ def validate_credentials(self, model: str, credentials: dict) -> None: 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 From bd6d4d0553696f711e2f4ab101b952a34c3ca33c Mon Sep 17 00:00:00 2001 From: YidaHu Date: Thu, 29 Aug 2024 19:03:08 +0800 Subject: [PATCH 04/21] fix: filter out installed apps without an app (#7799) --- api/controllers/console/explore/installed_app.py | 1 + 1 file changed, 1 insertion(+) diff --git a/api/controllers/console/explore/installed_app.py b/api/controllers/console/explore/installed_app.py index b71078760c6255..3f1e64a2478b4b 100644 --- a/api/controllers/console/explore/installed_app.py +++ b/api/controllers/console/explore/installed_app.py @@ -35,6 +35,7 @@ def get(self): "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: ( From c9e0f0bf20a587e640284a02070b95a1611f37a9 Mon Sep 17 00:00:00 2001 From: Benjamin Date: Fri, 30 Aug 2024 00:03:40 +0800 Subject: [PATCH 05/21] fix: correct typo in environment variable description (#7817) --- web/i18n/zh-Hans/workflow.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/i18n/zh-Hans/workflow.ts b/web/i18n/zh-Hans/workflow.ts index f57eb40bb0ba5a..56d1de6ceb664f 100644 --- a/web/i18n/zh-Hans/workflow.ts +++ b/web/i18n/zh-Hans/workflow.ts @@ -80,7 +80,7 @@ const translation = { }, env: { envPanelTitle: '环境变量', - envDescription: '环境变量是一种存储敏感信息的方法，如 API 密钥、数据库密码等。它们被存储在工作流程中，而不是代码中，以便在不同环墋中共享。', + envDescription: '环境变量是一种存储敏感信息的方法，如 API 密钥、数据库密码等。它们被存储在工作流程中，而不是代码中，以便在不同环境中共享。', envPanelButton: '添加环境变量', modal: { title: '添加环境变量', From dc015c380a94543da572222685bcfbf1af766eee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=9D=9E=E6=B3=95=E6=93=8D=E4=BD=9C?= Date: Fri, 30 Aug 2024 15:08:31 +0800 Subject: [PATCH 06/21] feat: add zhipu glm_4_plus and glm_4v_plus model (#7824) --- .../zhipuai/llm/glm_4_plus.yaml | 39 +++++++++++++++++++ .../zhipuai/llm/glm_4v_plus.yaml | 37 ++++++++++++++++++ .../model_providers/zhipuai/llm/llm.py | 9 +++-- 3 files changed, 81 insertions(+), 4 deletions(-) create mode 100644 api/core/model_runtime/model_providers/zhipuai/llm/glm_4_plus.yaml create mode 100644 api/core/model_runtime/model_providers/zhipuai/llm/glm_4v_plus.yaml diff --git a/api/core/model_runtime/model_providers/zhipuai/llm/glm_4_plus.yaml b/api/core/model_runtime/model_providers/zhipuai/llm/glm_4_plus.yaml new file mode 100644 index 00000000000000..d9132640b291dc --- /dev/null +++ b/api/core/model_runtime/model_providers/zhipuai/llm/glm_4_plus.yaml @@ -0,0 +1,39 @@ +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 diff --git a/api/core/model_runtime/model_providers/zhipuai/llm/glm_4v_plus.yaml b/api/core/model_runtime/model_providers/zhipuai/llm/glm_4v_plus.yaml new file mode 100644 index 00000000000000..4a45c65f641c96 --- /dev/null +++ b/api/core/model_runtime/model_providers/zhipuai/llm/glm_4v_plus.yaml @@ -0,0 +1,37 @@ +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: 8192 diff --git a/api/core/model_runtime/model_providers/zhipuai/llm/llm.py b/api/core/model_runtime/model_providers/zhipuai/llm/llm.py index 13d8f5e5c32102..b2cdc7ad7a4644 100644 --- a/api/core/model_runtime/model_providers/zhipuai/llm/llm.py +++ b/api/core/model_runtime/model_providers/zhipuai/llm/llm.py @@ -153,7 +153,8 @@ def _generate(self, model: str, credentials_kwargs: dict, :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 @@ def _generate(self, model: str, credentials_kwargs: dict, 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 @@ def _generate(self, model: str, credentials_kwargs: dict, 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 @@ def _construct_glm_4v_parameter(self, model: str, prompt_messages: list[PromptMe 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}] From ceb2b150fff62fa515ec26e1aeffce0095d5c7be Mon Sep 17 00:00:00 2001 From: Zhi Date: Fri, 30 Aug 2024 15:53:50 +0800 Subject: [PATCH 07/21] enhance: include workspace name in create-tenant command (#7834) --- api/commands.py | 7 +++++-- api/services/account_service.py | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/api/commands.py b/api/commands.py index 41f1a6444c4581..3bf8bc0ecc45f2 100644 --- a/api/commands.py +++ b/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( diff --git a/api/services/account_service.py b/api/services/account_service.py index cd501c9792411c..e1b70fc9ed93c7 100644 --- a/api/services/account_service.py +++ b/api/services/account_service.py @@ -265,7 +265,7 @@ def create_tenant(name: str) -> Tenant: return tenant @staticmethod - def create_owner_tenant_if_not_exist(account: Account): + def create_owner_tenant_if_not_exist(account: Account, name: Optional[str] = None): """Create owner tenant if not exist""" available_ta = ( TenantAccountJoin.query.filter_by(account_id=account.id).order_by(TenantAccountJoin.id.asc()).first() @@ -274,7 +274,10 @@ def create_owner_tenant_if_not_exist(account: Account): if available_ta: return - tenant = TenantService.create_tenant(f"{account.name}'s Workspace") + if name: + tenant = TenantService.create_tenant(name) + else: + tenant = TenantService.create_tenant(f"{account.name}'s Workspace") TenantService.create_tenant_member(tenant, account, role="owner") account.current_tenant = tenant db.session.commit() From 62bfc4dba6e5e99ddf162b659b4cf07054c16559 Mon Sep 17 00:00:00 2001 From: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com> Date: Fri, 30 Aug 2024 18:13:54 +0800 Subject: [PATCH 08/21] fix: tooltip size sets improperly (#7836) --- .../common/retrieval-param-config/index.tsx | 2 +- .../system-model-selector/index.tsx | 13 +++++-------- .../config-credentials.tsx | 2 +- 3 files changed, 7 insertions(+), 10 deletions(-) diff --git a/web/app/components/datasets/common/retrieval-param-config/index.tsx b/web/app/components/datasets/common/retrieval-param-config/index.tsx index 54a0963f597a45..323e47f3b4ae24 100644 --- a/web/app/components/datasets/common/retrieval-param-config/index.tsx +++ b/web/app/components/datasets/common/retrieval-param-config/index.tsx @@ -191,7 +191,7 @@ const RetrievalParamConfig: FC = ({
{option.label}
{option.tips}
} - triggerClassName='ml-0.5 w-3.5 h-4.5' + triggerClassName='ml-0.5 w-3.5 h-3.5' />
)) diff --git a/web/app/components/header/account-setting/model-provider-page/system-model-selector/index.tsx b/web/app/components/header/account-setting/model-provider-page/system-model-selector/index.tsx index 6e181425e2db0d..15747858981e59 100644 --- a/web/app/components/header/account-setting/model-provider-page/system-model-selector/index.tsx +++ b/web/app/components/header/account-setting/model-provider-page/system-model-selector/index.tsx @@ -148,7 +148,7 @@ const SystemModel: FC = ({ {t('common.modelProvider.systemReasoningModel.tip')} } - triggerClassName='ml-0.5' + triggerClassName='ml-0.5 w-4 h-4 shrink-0' />
@@ -168,8 +168,7 @@ const SystemModel: FC = ({ {t('common.modelProvider.embeddingModel.tip')}
} - needsDelay={false} - triggerClassName='ml-0.5' + triggerClassName='ml-0.5 w-4 h-4 shrink-0' />
@@ -189,8 +188,7 @@ const SystemModel: FC = ({ {t('common.modelProvider.rerankModel.tip')}
} - needsDelay={false} - triggerClassName='ml-0.5' + triggerClassName='ml-0.5 w-4 h-4 shrink-0' />
@@ -210,8 +208,7 @@ const SystemModel: FC = ({ {t('common.modelProvider.speechToTextModel.tip')}
} - needsDelay={false} - triggerClassName='ml-0.5' + triggerClassName='ml-0.5 w-4 h-4 shrink-0' />
@@ -231,7 +228,7 @@ const SystemModel: FC = ({ {t('common.modelProvider.ttsModel.tip')}
} - triggerClassName='ml-0.5' + triggerClassName='ml-0.5 w-4 h-4 shrink-0' />
diff --git a/web/app/components/tools/edit-custom-collection-modal/config-credentials.tsx b/web/app/components/tools/edit-custom-collection-modal/config-credentials.tsx index c7685d496d9620..d580c00102f49e 100644 --- a/web/app/components/tools/edit-custom-collection-modal/config-credentials.tsx +++ b/web/app/components/tools/edit-custom-collection-modal/config-credentials.tsx @@ -114,7 +114,7 @@ const ConfigCredential: FC = ({ {t('tools.createTool.authMethod.keyTooltip')}
} - triggerClassName='ml-0.5' + triggerClassName='ml-0.5 w-4 h-4' /> Date: Fri, 30 Aug 2024 18:48:05 +0800 Subject: [PATCH 09/21] fix: an issue of keyword search feature in application log list (#7816) --- api/controllers/console/app/conversation.py | 27 +++++++++------------ 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/api/controllers/console/app/conversation.py b/api/controllers/console/app/conversation.py index 753a6be20cd1a6..c3aac6690e4c3d 100644 --- a/api/controllers/console/app/conversation.py +++ b/api/controllers/console/app/conversation.py @@ -173,21 +173,18 @@ def get(self, app_model): 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 From 0c2a62f8479d4cfcc18751b5859290af7d24370b Mon Sep 17 00:00:00 2001 From: Bowen Liang Date: Fri, 30 Aug 2024 19:09:10 +0800 Subject: [PATCH 10/21] =?UTF-8?q?fix:=20correct=20http=20timeout=20configs?= =?UTF-8?q?=E2=80=98=20default=20values=20and=20ignorance=20by=20HttpReque?= =?UTF-8?q?stNode=20(#7762)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- api/configs/feature/__init__.py | 23 ++++++++----------- .../nodes/http_request/http_request_node.py | 15 +++++------- .../unit_tests/configs/test_dify_config.py | 7 ++++++ 3 files changed, 23 insertions(+), 22 deletions(-) diff --git a/api/configs/feature/__init__.py b/api/configs/feature/__init__.py index f2efa52de3ecba..303bce2aa5050c 100644 --- a/api/configs/feature/__init__.py +++ b/api/configs/feature/__init__.py @@ -1,4 +1,4 @@ -from typing import Optional +from typing import Annotated, Optional from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field from pydantic_settings import BaseSettings @@ -217,20 +217,17 @@ def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]: 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="", diff --git a/api/core/workflow/nodes/http_request/http_request_node.py b/api/core/workflow/nodes/http_request/http_request_node.py index f6c8ea3c83422d..037a7a1848ccfa 100644 --- a/api/core/workflow/nodes/http_request/http_request_node.py +++ b/api/core/workflow/nodes/http_request/http_request_node.py @@ -19,9 +19,9 @@ from models.workflow import WorkflowNodeExecutionStatus HTTP_REQUEST_DEFAULT_TIMEOUT = HttpRequestNodeTimeout( - connect=min(10, dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT), - read=min(60, dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT), - write=min(20, dify_config.HTTP_REQUEST_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, ) @@ -96,12 +96,9 @@ def _get_request_timeout(node_data: HttpRequestNodeData) -> HttpRequestNodeTimeo if timeout is None: return HTTP_REQUEST_DEFAULT_TIMEOUT - timeout.connect = min(timeout.connect or HTTP_REQUEST_DEFAULT_TIMEOUT.connect, - dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT) - timeout.read = min(timeout.read or HTTP_REQUEST_DEFAULT_TIMEOUT.read, - dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT) - timeout.write = min(timeout.write or HTTP_REQUEST_DEFAULT_TIMEOUT.write, - dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT) + timeout.connect = timeout.connect or HTTP_REQUEST_DEFAULT_TIMEOUT.connect + timeout.read = timeout.read or HTTP_REQUEST_DEFAULT_TIMEOUT.read + timeout.write = timeout.write or HTTP_REQUEST_DEFAULT_TIMEOUT.write return timeout @classmethod diff --git a/api/tests/unit_tests/configs/test_dify_config.py b/api/tests/unit_tests/configs/test_dify_config.py index fb415483dd39ad..3f639ccacc48f5 100644 --- a/api/tests/unit_tests/configs/test_dify_config.py +++ b/api/tests/unit_tests/configs/test_dify_config.py @@ -19,6 +19,7 @@ def example_env_file(tmp_path, monkeypatch) -> str: """ CONSOLE_API_URL=https://example.com CONSOLE_WEB_URL=https://example.com + HTTP_REQUEST_MAX_WRITE_TIMEOUT=30 """ ) ) @@ -48,6 +49,12 @@ def test_dify_config(example_env_file): assert config.API_COMPRESSION_ENABLED is False assert config.SENTRY_TRACES_SAMPLE_RATE == 1.0 + # annotated field with default value + assert config.HTTP_REQUEST_MAX_READ_TIMEOUT == 60 + + # annotated field with configured value + assert config.HTTP_REQUEST_MAX_WRITE_TIMEOUT == 30 + # NOTE: If there is a `.env` file in your Workspace, this test might not succeed as expected. # This is due to `pymilvus` loading all the variables from the `.env` file into `os.environ`. From 1f56a20b626d2e721404ecab179fac81a5dffe90 Mon Sep 17 00:00:00 2001 From: sino Date: Sat, 31 Aug 2024 10:56:32 +0800 Subject: [PATCH 11/21] feat: support auth by api key for ark provider (#7845) --- .../model_providers/volcengine_maas/client.py | 19 +++++++++-- .../volcengine_maas/volcengine_maas.yaml | 34 +++++++++++++++++++ 2 files changed, 50 insertions(+), 3 deletions(-) diff --git a/api/core/model_runtime/model_providers/volcengine_maas/client.py b/api/core/model_runtime/model_providers/volcengine_maas/client.py index 61f3521a43634f..a4d89dabcbc076 100644 --- a/api/core/model_runtime/model_providers/volcengine_maas/client.py +++ b/api/core/model_runtime/model_providers/volcengine_maas/client.py @@ -71,11 +71,24 @@ def from_credentials(cls, credentials): 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"] = DEFAULT_V3_ENDPOINT + args = { + **args, + "base_url": DEFAULT_V3_ENDPOINT + } client = ArkClientV3( **args diff --git a/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml b/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml index 735ba2b31431fb..13e00da76fb149 100644 --- a/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml +++ b/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: From ef82a29e2307f08c3ce6ce51720afc43e2d5bfc1 Mon Sep 17 00:00:00 2001 From: zhujinle <32472522+zhujinle@users.noreply.github.com> Date: Sun, 1 Sep 2024 14:52:27 +0800 Subject: [PATCH 12/21] fix: crash when ECharts accesses undefined objects (#7853) --- web/app/components/base/markdown.tsx | 30 ++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/web/app/components/base/markdown.tsx b/web/app/components/base/markdown.tsx index af4b13ff70deaf..6e8ae6c9e62f0b 100644 --- a/web/app/components/base/markdown.tsx +++ b/web/app/components/base/markdown.tsx @@ -8,7 +8,7 @@ import RemarkGfm from 'remark-gfm' import SyntaxHighlighter from 'react-syntax-highlighter' import { atelierHeathLight } from 'react-syntax-highlighter/dist/esm/styles/hljs' import type { RefObject } from 'react' -import { memo, useEffect, useMemo, useRef, useState } from 'react' +import { Component, memo, useEffect, useMemo, useRef, useState } from 'react' import type { CodeComponent } from 'react-markdown/lib/ast-to-react' import cn from '@/utils/classnames' import CopyBtn from '@/app/components/base/copy-btn' @@ -104,7 +104,7 @@ const CodeBlock: CodeComponent = memo(({ inline, className, children, ...props } const match = /language-(\w+)/.exec(className || '') const language = match?.[1] const languageShowName = getCorrectCapitalizationLanguageName(language || '') - let chartData = JSON.parse(String('{"title":{"text":"Something went wrong."}}').replace(/\n$/, '')) + let chartData = JSON.parse(String('{"title":{"text":"ECharts error - Wrong JSON format."}}').replace(/\n$/, '')) if (language === 'echarts') { try { chartData = JSON.parse(String(children).replace(/\n$/, '')) @@ -143,10 +143,10 @@ const CodeBlock: CodeComponent = memo(({ inline, className, children, ...props } ? () : ( (language === 'echarts') - ? (
-
) + ) : ( ) } + +// **Add an ECharts runtime error handler +// Avoid error #7832 (Crash when ECharts accesses undefined objects) +// This can happen when a component attempts to access an undefined object that references an unregistered map, causing the program to crash. + +export default class ErrorBoundary extends Component { + constructor(props) { + super(props) + this.state = { hasError: false } + } + + componentDidCatch(error, errorInfo) { + this.setState({ hasError: true }) + console.error(error, errorInfo) + } + + render() { + if (this.state.hasError) + return
Oops! ECharts reported a runtime error.
(see the browser console for more information)
+ return this.props.children + } +} From 024d688b77f7fafdabf66498ee77efec9631d769 Mon Sep 17 00:00:00 2001 From: Hirotaka Miyagi <31152321+MH4GF@users.noreply.github.com> Date: Sun, 1 Sep 2024 15:57:50 +0900 Subject: [PATCH 13/21] fix(RetrievalConfig): Fix score threshold assignment for zero value (#7865) --- .../nodes/knowledge-retrieval/components/retrieval-config.tsx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/app/components/workflow/nodes/knowledge-retrieval/components/retrieval-config.tsx b/web/app/components/workflow/nodes/knowledge-retrieval/components/retrieval-config.tsx index ebe9d2151ea12c..b335b62e339e7d 100644 --- a/web/app/components/workflow/nodes/knowledge-retrieval/components/retrieval-config.tsx +++ b/web/app/components/workflow/nodes/knowledge-retrieval/components/retrieval-config.tsx @@ -70,7 +70,7 @@ const RetrievalConfig: FC = ({ } onMultipleRetrievalConfigChange({ top_k: configs.top_k, - score_threshold: configs.score_threshold_enabled ? (configs.score_threshold || DATASET_DEFAULT.score_threshold) : null, + score_threshold: configs.score_threshold_enabled ? (configs.score_threshold ?? DATASET_DEFAULT.score_threshold) : null, reranking_model: payload.retrieval_mode === RETRIEVE_TYPE.oneWay ? undefined : (!configs.reranking_model?.reranking_provider_name From 1510bdbcf66dfdb14a269eeb22605a0182fdd450 Mon Sep 17 00:00:00 2001 From: Hirotaka Miyagi <31152321+MH4GF@users.noreply.github.com> Date: Sun, 1 Sep 2024 15:58:12 +0900 Subject: [PATCH 14/21] refactor: Remove typecasting by any (#7862) --- web/app/(commonLayout)/apps/Apps.tsx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/web/app/(commonLayout)/apps/Apps.tsx b/web/app/(commonLayout)/apps/Apps.tsx index c16512bd50db1f..132096c6b455ee 100644 --- a/web/app/(commonLayout)/apps/Apps.tsx +++ b/web/app/(commonLayout)/apps/Apps.tsx @@ -139,7 +139,7 @@ const Apps = () => {