Marketing Architects icon

Marketing Architects

Consume Marketing Architects API
Join our community

Actions7

Overview

The node integrates with the Marketing Architects API to perform text completion tasks using a specified language model. It sends a series of messages (with roles such as user, assistant, or system) to the API and receives generated text completions in response. This is useful for scenarios like generating conversational replies, drafting content, or creating structured text outputs based on prompts.

Practical examples include:

  • Automating customer support responses by providing user queries and receiving assistant-generated answers.
  • Generating creative writing or marketing copy from given prompts.
  • Producing structured data outputs if the chosen model supports specific response formats.

Properties

Name Meaning
Model Select the language model to use for text generation. Options are dynamically loaded from the API.
Messages A collection of message objects forming the conversation history or prompt context. Each message has:
- Role: one of Assistant, System, or User
- Content: the textual content of the message
Options Additional optional parameters for the text generation request. Currently supports specifying a response format (structured output), if supported by the model.
Retry Settings Configuration for retrying the request on failure, including:
- Enable Retry on Failure (boolean)
- Max Retry Attempts (number between 1 and 10)
- Retry Delay in seconds (1-60)
- Backoff Strategy: Fixed delay or Exponential delay

Output

The node outputs JSON data containing the text completion results returned by the Marketing Architects API. The exact structure depends on the model and options used but generally includes the generated text or structured response as per the requested format.

If the model supports structured output, the response can be parsed into JSON objects for further workflow processing.

No binary data output is indicated for this operation.

Dependencies

  • Requires an API key credential for authenticating with the Marketing Architects API.
  • The base URL for requests is https://pushbtn.api.misfitsandmachines.com.
  • The node uses HTTP POST requests to /generation/open-router endpoint for text completion.
  • Dynamic loading of available models is done via a GET request to /generation/openrouter/models.

Troubleshooting

  • Common Issues:

    • Invalid or missing API key will cause authentication failures.
    • Selecting a model that does not support requested features (e.g., structured output) may result in unexpected responses.
    • Network issues or API downtime can cause request failures.

  • Error Messages:

    • Errors returned by the API are processed and surfaced by the node. Typical errors include authorization errors, invalid parameters, or rate limiting.
    • If retries are enabled, transient errors may be retried automatically according to configured settings.

  • Resolution Tips:

    • Verify API credentials are correctly configured.
    • Ensure the selected model supports the desired features.
    • Adjust retry settings to handle intermittent network or service issues.

Links and References

Discussion