FlowEngine LLM Chat ModelInstall

Summary

Send a chat prompt to a selected AI language model hosted by FlowEngine and receive the generated completion response.

Inputs

• Provider — Select the AI model provider to filter available models.
• Model (required) — Choose the specific AI model to use for generating chat completions.
• Options — Configure additional parameters such as sampling temperature to control randomness and maximum number of tokens to limit response length.

Output shape

a single AI language model completion response object

The output contains the model's generated text completion based on the input prompt. An API key is required either from environment or node credentials. The request uses FlowEngine endpoints and supports passing temperature and maxTokens as options.