From f0273f00e18d023fd6270307f9eb5c1030567e1b Mon Sep 17 00:00:00 2001 From: hisir Date: Thu, 29 Aug 2024 18:58:19 +0800 Subject: [PATCH 1/6] 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 2b729d4293..6279125f46 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 @@ 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 From bd6d4d0553696f711e2f4ab101b952a34c3ca33c Mon Sep 17 00:00:00 2001 From: YidaHu Date: Thu, 29 Aug 2024 19:03:08 +0800 Subject: [PATCH 2/6] 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 b71078760c..3f1e64a247 100644 --- a/api/controllers/console/explore/installed_app.py +++ b/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: ( From c9e0f0bf20a587e640284a02070b95a1611f37a9 Mon Sep 17 00:00:00 2001 From: Benjamin Date: Fri, 30 Aug 2024 00:03:40 +0800 Subject: [PATCH 3/6] 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 f57eb40bb0..56d1de6ceb 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 4/6] 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 0000000000..d9132640b2 --- /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 0000000000..4a45c65f64 --- /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 13d8f5e5c3..b2cdc7ad7a 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 @@ 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}] From ceb2b150fff62fa515ec26e1aeffce0095d5c7be Mon Sep 17 00:00:00 2001 From: Zhi Date: Fri, 30 Aug 2024 15:53:50 +0800 Subject: [PATCH 5/6] 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 41f1a6444c..3bf8bc0ecc 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 cd501c9792..e1b70fc9ed 100644 --- a/api/services/account_service.py +++ b/api/services/account_service.py @@ -265,7 +265,7 @@ class TenantService: 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 @@ class TenantService: 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 6/6] 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 54a0963f59..323e47f3b4 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 6e181425e2..1574785898 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 c7685d496d..d580c00102 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' />