Skip to content

NVIDIA Nemotron 聊天模型节点(NVIDIA Nemotron Chat Model node)#

使用 NVIDIA Nemotron 聊天模型节点访问带有会话代理的 NVIDIA Nemotron 模型。该节点可与托管在 build.nvidia.com 的 Nemotron 模型以及自托管的 NVIDIA 推断微服务（NIM）一起使用。

🌐 Use the NVIDIA Nemotron Chat Model node to access NVIDIA Nemotron models with conversational agents. The node works with Nemotron models hosted on build.nvidia.com and with self-hosted NVIDIA Inference Microservices (NIM).

在此页面上，你将找到 NVIDIA Nemotron Chat 模型节点的节点参数以及更多资源的链接。

🌐 On this page, you'll find the node parameters for the NVIDIA Nemotron Chat Model node and links to more resources.

凭证

你可以在这里找到此节点的认证信息。

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)#

模型(Model)#

选择要用于生成完成的 Nemotron 模型。

🌐 Select the Nemotron model to use to generate the completion.

n8n 会根据你凭据中配置的端点动态加载 Nemotron 模型。如果 n8n 无法访问该端点，它会回退到一个经过策划的知名 Nemotron 模型 ID 列表。

🌐 n8n dynamically loads Nemotron models from the endpoint configured in your credential. If n8n can't reach the endpoint, it falls back to a curated list of well-known Nemotron model IDs.

节点选项(Node options)#

使用这些选项来进一步细化节点的行为。

🌐 Use these options to further refine the node's behavior.

频率惩罚(Frequency Penalty)#

使用此选项可以控制模型重复自身的几率。较高的数值可以降低模型重复的可能性。

🌐 Use this option to control the chances of the model repeating itself. Higher values reduce the chance of the model repeating itself.

最大令牌数(Maximum Number of Tokens)#

输入使用的最大令牌数，这会设置完成长度。使用 -1 表示模型默认值。

🌐 Enter the maximum number of tokens used, which sets the completion length. Use -1 for the model default.

响应格式(Response Format)#

选择 文本 或 JSON。JSON 确保模型返回有效的 JSON。当你选择 JSON 时，在链或代理的提示中包含单词 json。

🌐 Choose Text or JSON. JSON ensures the model returns valid JSON. When you choose JSON, include the word json in your prompt in the chain or agent.

在线惩罚(Presence Penalty)#

使用此选项可以控制模型谈论新话题的可能性。数值越高，模型谈论新话题的几率越大。

🌐 Use this option to control the chances of the model talking about new topics. Higher values increase the chance of the model talking about new topics.

采样温度(Sampling Temperature)#

使用此选项可以控制采样过程的随机性。较高的温度会产生更多样化的采样，但也增加了产生幻觉的风险。

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

超时(Timeout)#

请输入最大请求时间（以毫秒为单位）。

🌐 Enter the maximum request time in milliseconds.

最大重试次数(Max Retries)#

请输入请求重试的最大次数。

🌐 Enter the maximum number of times to retry a request.

热门问题(Top P)#

使用此选项设置生成内容应使用的概率。使用较低的值可以忽略不太可能的选项。

🌐 Use this option to set the probability the completion should use. Use a lower value to ignore less probable options.

模板和示例(Templates and examples)#

Template widget placeholder.

请参阅NVIDIA 构建目录以获取 Nemotron 型号列表，并参阅NIM 文档以获取自托管指南。由于 NVIDIA API 与 OpenAI 规范兼容，你可以参阅LangChain 的 OpenAI 文档以获取有关底层客户端的更多信息。

🌐 Refer to NVIDIA's build catalogue for the list of Nemotron models and to the NIM documentation for guidance on self-hosting. As the NVIDIA API is OpenAI-spec compatible, you can refer to LangChain's OpenAI documentation for more information about the underlying client.

View n8n's Advanced AI documentation.