pipeline.add(name="...").<node>(...). Each entry lists the node’s configuration parameters. See the Pipeline reference for add, run, and lifecycle methods.
llm — LLM
LLM
Platform docs: LLM
Select the LLM provider to be used
Whether to stream the response
Whether to return the response as a JSON object
Whether to show the sources used to generate the response
Select the LLM model to be used
The data that is sent to the LLM. Add data from other nodes with double curly braces e.g., {{input_0.text}}
The system prompt to be used
Your API key
The metadata of the sources used to generate the response
Enable Claude’s built-in web search tool to search the web during response generation
The schema of the JSON response
Controls the depth of reasoning for GPT-5 models (“none” is only supported on GPT-5.1 variants).
One of:
default, high, low, medium, minimal, noneIf enabled, the context window will be reduced to fit the model’s maximum context window.
Controls the verbosity of GPT-5 responses.
One of:
default, high, low, mediumWhether to enable moderation
Whether to enable PII address
Whether to enable PII cc
Whether to enable PII email
Whether to enable PII name
Whether to enable PII phone
Whether to enable PII ssn
The maximum number of retries
The maximum amount of input + output tokens the model will take in and generate per run (1 token = 4 characters). Note: different models have different token limits and the workflow will error if the max token is reached.
The interval between retries in milliseconds
Enable retrying when the node execution fails
The “creativity” of the response - increase the temperature for more creative responses.
The “randomness” of the output - higher Top P values increase the randomness
The deployment ID for the Azure OpenAI model. This is required when using Azure OpenAI services.
The Azure OpenAI endpoint URL (e.g., https://your-resource-name.openai.azure.com)
The maximum number of tokens the model can use for thinking
Use your finetuned model for response generation. Make sure to select the matching base model from the dropdown.
The base URL of the custom LLM provider
Your AWS Access Key ID
AWS region where Bedrock models are enabled
Your AWS Secret Access Key