Google Vertex Chat 模型节点#

¥Google Vertex Chat Model node

使用 Google Vertex AI Chat Model 节点，将 Google 的 Vertex AI 聊天模型与对话式 agents 结合使用。

¥Use the Google Vertex AI Chat Model node to use Google's Vertex AI chat models with conversational agents.

本页提供 Google Vertex AI Chat Model 节点的参数以及更多资源的链接。

¥On this page, you'll find the node parameters for the Google Vertex AI Chat Model node, and links to more resources.

Credentials

你可以在此处中找到此节点的身份验证信息。

¥You can find authentication information for this node here.

Parameter resolution in sub-nodes

Sub-nodes behave differently to other nodes when processing multiple items using an expression.

Most nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five name values, the expression {{ $json.name }} resolves to each name in turn.

In sub-nodes, the expression always resolves to the first item. For example, given an input of five name values, the expression {{ $json.name }} always resolves to the first name.

节点参数#

¥Node parameters

项目 ID：选择要使用的 Google Cloud 账户中的项目 ID。n8n 会从 Google Cloud 账户动态加载项目，你也可以手动输入。

¥Project ID: Select the project ID from your Google Cloud account to use. n8n dynamically loads projects from the Google Cloud account, but you can also enter it manually.

模型名称：选择用于生成补全的模型名称，例如 gemini-1.5-flash-001、gemini-1.5-pro-001 等。有关可用模型的列表，请参阅 Google 模型。

¥Model Name: Select the name of the model to use to generate the completion, for example gemini-1.5-flash-001, gemini-1.5-pro-001, etc. Refer to Google models for a list of available models.

节点选项#

¥Node options

最大令牌数：请输入使用的最大令牌数，这将设置完成时长。

¥Maximum Number of Tokens: Enter the maximum number of tokens used, which sets the completion length.

采样温度：使用此选项可控制采样过程的随机性。更高的温度会产生更多样化的采样，但会增加出现幻觉的风险。

¥Sampling Temperature: Use this option to control the randomness of the sampling process. A higher temperature creates more diverse sampling, but increases the risk of hallucinations.

考虑预算：控制思维模型的推断标记。设置为 0 可禁用自动思考。设置为 -1 可启用动态思考。留空以启用自动模式。

¥Thinking Budget: Controls reasoning tokens for thinking models. Set to 0 to disable automatic thinking. Set to -1 for dynamic thinking. Leave empty for auto mode.

顶部 K：输入模型用于生成下一个令牌的令牌选择数。

¥Top K: Enter the number of token choices the model uses to generate the next token.

顶部 P：使用此选项可设置完成概率。使用较低的值来忽略可能性较小的选项。

¥Top P: Use this option to set the probability the completion should use. Use a lower value to ignore less probable options.

安全设置：Gemini 支持可调节的安全设置。更多信息请参阅 Google 的 Gemini API 安全设置文档，了解有关可用过滤器和级别的信息。

¥Safety Settings: Gemini supports adjustable safety settings. Refer to Google's Gemini API safety settings for information on the available filters and levels.

模板和示例#

¥Templates and examples

Google Vertex Chat 模型节点#

节点参数#

节点选项#

模板和示例#

相关资源#