Description
n8n-nodes-langsmith-prompt
This is an n8n community node. It lets you use LangSmith prompt templates in your n8n workflows.
LangSmith is a platform for debugging, testing, evaluating, and monitoring LLM applications, allowing you to manage prompts and track their performance.
n8n is a fair-code licensed workflow automation platform.
Installation
Operations
Credentials
Compatibility
Usage
Resources
Installation
Follow the installation guide in the n8n community nodes documentation.
Operations
- Fill Prompt Template: Fetches a prompt template from LangSmith by name and substitutes parameter values into the template's variable placeholders.
Credentials
You need a LangSmith API key to use this node.
- Sign up for an account at LangSmith
- Generate an API key in your account settings
- Use this API key in the LangSmith API credentials in n8n
Compatibility
This node has been tested with n8n version 1.0.0 and later.
Usage
- Add the LangSmith Prompt node to your workflow
- Configure the LangSmith API credentials with your API key
- Enter the Prompt Name of the prompt template you want to fetch from LangSmith
- Add Input Parameters to substitute in the template:
- Click "Add Parameter" to add key-value pairs
- For each parameter, provide:
- Name: The parameter name as it appears in the template (e.g., if template contains {question}, use "question")
- Value: The value to substitute for that parameter
Example: Template Variable Substitution
If your LangSmith prompt template is:
This is your question: "{Question}"
And you add a parameter with:
- Name: Question
- Value: What is artificial intelligence?
The filled template output will be:
This is your question: "What is artificial intelligence?"
Working with Multiple Parameters
If your template has multiple variables like:
Hello {Name}, your question about {Topic} is: "{Question}"
Add three parameters:
- Name: Name, Value: John
- Name: Topic, Value: Machine Learning
- Name: Question, Value: How do neural networks work?
Node Output
The node outputs an object with the prompt name as key and the filled prompt content as value:
{
"my-template": "This is your question: \"What is artificial intelligence?\""
}
You can reference this output in subsequent nodes using expressions such as:
{{$node["LangSmith Prompt"].json["my-template"]}}
Where "my-template" is the name of your prompt.
