Skip to content

Commit dfa6013

Browse files
committed
New translations ai-assistant.md (Chinese Simplified)
1 parent 08474a5 commit dfa6013

1 file changed

Lines changed: 14 additions & 14 deletions

File tree

localizedContent/zh/content/features/ai-assistant.md

Lines changed: 14 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -72,31 +72,31 @@ AI 助手采用自带密钥 BYOK 模式。 你只需从受支持的提供商中
7272
7373
### Azure OpenAI
7474

75-
Select **Azure OpenAI** as the provider and configure three fields:
75+
选择 **Azure OpenAI** 作为提供商,并配置以下三个字段:
7676

77-
- **API key**the access key for your Azure OpenAI resource
78-
- **Service endpoint**the endpoint URL for your resource, for example `https://your-resource.openai.azure.com`. Use the resource URL, not the `privatelink` alias; the SSL certificate is issued for `*.openai.azure.com` and connecting directly to `*.privatelink.openai.azure.com` fails certificate validation
79-
- **Model name**the **deployment name**, not the underlying model name and not the resource name
77+
- **API 密钥**用于访问你的 Azure OpenAI 资源的密钥
78+
- **服务终结点**你的资源的终结点 URL,例如 `https://your-resource.openai.azure.com`。 使用资源 URL,不要使用 `privatelink` 别名;SSL 证书是为 `*.openai.azure.com` 签发的,直接连接到 `*.privatelink.openai.azure.com` 会导致证书验证失败
79+
- **模型名称**填写的是 **部署名称**,不是底层模型名称,也不是资源名称
8080

81-
Azure OpenAI requires the deployment name in every API call. A deployment name is chosen when the deployment is created, so it can be any string. Deployments are often named after the model they serve (for example `gpt-4o`), but that is a convention, not a requirement. If you enter the resource name or a raw model name that does not exist as a deployment, the request fails.
81+
Azure OpenAI 要求在每次 API 调用中都提供部署名称。 部署名称是在创建部署时指定的,因此它可以是任意字符串。 部署通常会以其所服务的模型命名(例如 `gpt-4o`),但这只是约定,并非强制要求。 如果你输入的是资源名称,或者一个并未作为部署存在的底层模型名称,请求就会失败。
8282

83-
#### Finding your deployment name
83+
#### 查找部署名称
8484

85-
In the [Azure AI Foundry portal](https://ai.azure.com):
85+
[Azure AI Foundry 门户](https://ai.azure.com) 中:
8686

87-
1. Sign in and select your Azure OpenAI resource
88-
2. Open **Deployments** (or **Models + endpoints** if the resource has been upgraded to Foundry)
89-
3. Copy the value from the **Name** column
87+
1. 登录并选择你的 Azure OpenAI 资源
88+
2. 打开 **部署**(如果资源已升级到 Foundry,则为 **模型 + 终结点**
89+
3. 复制 **名称** 列中的值
9090

91-
Deployments created before your organization adopted Azure AI Foundry may not appear in the portal. List them from the Azure CLI:
91+
在你的组织采用 Azure AI Foundry 之前创建的部署,可能不会显示在门户中。 可通过 Azure CLI 列出它们:
9292

9393
```bash
9494
az cognitiveservices account deployment list --name "<resource-name>" --resource-group "<resource-group>" --output table
9595
```
9696

97-
See [Create and deploy an Azure OpenAI resource](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/create-resource#deploy-a-model) for more details.
97+
更多详情见 [创建并部署 Azure OpenAI 资源](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/create-resource#deploy-a-model)
9898

99-
For 403 errors, SSL failures or "DeploymentNotFound" responses, see @azure-openai-connection-errors.
99+
有关 403 错误、SSL 失败或 "DeploymentNotFound" 响应,请参阅 @azure-openai-connection-errors
100100

101101
### 自定义(OpenAI 兼容)
102102

@@ -320,7 +320,7 @@ AI 助手在向 AI 提供商发送数据之前会先征求你的同意。 同意
320320

321321
其他减少 token 使用量的方法:
322322

323-
- Ask focused questions about specific tables, measures or columns rather than broad questions about the entire model. A vague prompt such as _"Set display folders on all measures"_ forces the assistant to retrieve metadata for the entire model. A specific prompt such as _"Set display folders on the measures I have selected"_ limits the context to the current selection and uses far fewer tokens
323+
- 围绕特定的表、度量值或列提出更聚焦的问题,而不是对整个模型提出泛泛的问题。 像 _“为所有度量值设置显示文件夹”_ 这样含糊的提示,会迫使助手检索整个模型的元数据。 像 _“为我选中的度量值设置显示文件夹”_ 这样具体的提示,会将上下文限制在当前选择范围内,并且消耗的 token 少得多
324324
- 切换话题时开启新对话,避免累积过长的对话历史
325325
- 进行探索性提问时,使用更小或成本更低的模型
326326

0 commit comments

Comments
 (0)