Inline Prompt Node

Optional inputs for variable substitution in the prompt. These inputs are used to replace:

• Variables within Jinja blocks
• Variable blocks in the blocks attribute

You can reference either Workflow inputs or outputs from upstream nodes.

The blocks that make up the Prompt

The model to use for execution (e.g., “gpt-4o”, “claude-3.5-sonnet”)

The functions to include in the prompt

Model parameters for execution. Defaults to:

• stop: []
• temperature: 0.0
• max_tokens: 4096
• top_p: 1.0
• top_k: 0
• frequency_penalty: 0.0
• presence_penalty: 0.0
• logit_bias: None
• custom_parameters: None
  • This field can be used to pass additional parameters to the LLM, like json_schema (learn more here).

Expandable execution fields to include in the response. See more here.

Additional options for request-specific configuration when calling APIs via the SDK. This is used primarily as an optional final parameter for service functions.

• timeout_in_seconds: The number of seconds to await an API call before timing out
• max_retries: The max number of retries to attempt if the API call fails
• additional_headers: A dictionary containing additional parameters to spread into the request’s header dict
• additional_query_parameters: A dictionary containing additional parameters to spread into the request’s query parameters dict
• additional_body_parameters: A dictionary containing additional parameters to spread into the request’s body parameters dict

The generated text output from the prompt execution

The array of results from the prompt execution. PromptOutput is a union of the following types:

• StringVellumValue
• JsonVellumValue
• ErrorVellumValue
• FunctionCallVellumValue