stream_text: Stream Text

In aisdk: Unified Interface for AI Model Providers

Stream Text

Description

Generate text using a language model with streaming output. This function provides a real-time stream of tokens through a callback.

Usage

stream_text(
  model = NULL,
  prompt,
  callback = NULL,
  system = NULL,
  temperature = 0.7,
  max_tokens = NULL,
  tools = NULL,
  max_steps = 1,
  max_tool_result_errors = 2,
  require_post_tool_protocol = FALSE,
  sandbox = FALSE,
  skills = NULL,
  session = NULL,
  hooks = NULL,
  registry = NULL,
  renderer = NULL,
  .stream_event_callback = NULL,
  ...
)

Arguments

model	Either a LanguageModelV1 object, or a string ID like "openai:gpt-4o".
prompt	A character string prompt, or a list of messages.
callback	A function called for each text chunk: callback(text, done).
system	Optional system prompt.
temperature	Sampling temperature (0-2). Default 0.7.
max_tokens	Maximum tokens to generate.
tools	Optional list of Tool objects for function calling.
max_steps	Number of model/tool steps in one execution window. Default 1. The runtime treats this as a budget checkpoint, not as a hard task stop.
max_tool_result_errors	Historical compatibility option. Tool result errors are recorded as task observations; runtime policy decides whether to continue, finalize, ask the user, or block.
require_post_tool_protocol	Logical. If TRUE, after any tool results are returned the model must either make another tool call or wrap its final answer in a ⁠<final_answer>...</final_answer>⁠ block. This is enabled automatically for text-based tool fallback.
sandbox	Logical. If TRUE, enables R-native programmatic sandbox mode. See generate_text for details. Default FALSE.
skills	Optional path to skills directory, or a SkillRegistry object.
session	Optional ChatSession object for shared state.
hooks	Optional HookHandler object.
registry	Optional ProviderRegistry to use.
renderer	Optional Renderer for agent output. Defaults to the cli terminal backend (create_stream_renderer()); pass any Renderer-conforming object (e.g. from a web UI, create_capture_renderer(), or create_null_renderer()) to render agent output elsewhere.
.stream_event_callback	Internal callback for typed stream events.
...	Additional arguments passed to the model.

Value

A GenerateResult object (accumulated from the stream).

Examples

if (interactive()) {
  model <- create_openai()$language_model("gpt-4o")
  stream_text(model, "Tell me a story", callback = function(text, done) {
    if (!done) cat(text)
  })
}

aisdk documentation built on May 29, 2026, 9:07 a.m.