foundry_chat: Chat with an Azure AI Model

In foundryR: Data Frame Workflows for 'Microsoft Foundry'

Chat with an Azure AI Model

Description

Send a message to an Azure AI Foundry deployed model and receive a response. Returns a tibble with the assistant's response and usage metadata.

Usage

foundry_chat(
  message,
  system = NULL,
  model = NULL,
  history = NULL,
  temperature = NULL,
  max_tokens = NULL,
  max_completion_tokens = NULL,
  top_p = NULL,
  frequency_penalty = NULL,
  presence_penalty = NULL,
  stop = NULL,
  reasoning_effort = NULL,
  api = c("v1", "deployment"),
  api_key = NULL,
  api_version = NULL,
  ...
)

Arguments

message	Character. The user message to send.
system	Character. Optional system prompt to set the assistant's behavior.
model	Character. The deployment name. Defaults to the environment variable AZURE_FOUNDRY_MODEL or must be specified.
history	List. Optional conversation history as a list of message objects, each with role and content fields.
temperature	Numeric. Sampling temperature between 0 and 2. Higher values make output more random, lower values more deterministic. Default: 1.
max_tokens	Integer. Maximum tokens in response (legacy parameter, use max_completion_tokens for newer models).
max_completion_tokens	Integer. Maximum tokens in response. Preferred parameter for newer models (gpt-4o, etc.). Takes precedence over max_tokens.
top_p	Numeric. Nucleus sampling parameter between 0 and 1. Default: 1.
frequency_penalty	Numeric. Penalty for token frequency (-2.0 to 2.0). Default: 0.
presence_penalty	Numeric. Penalty for token presence (-2.0 to 2.0). Default: 0.
stop	Character vector. Up to 4 sequences where the API will stop generating.
reasoning_effort	Character. Optional reasoning effort ("low", "medium", or "high") for reasoning models that accept this control.
api	Character. Endpoint style. "v1" (default) sends requests to ⁠/openai/v1/chat/completions⁠ with model in the JSON body. "deployment" keeps the legacy deployment-path endpoint.
api_key	Character. Optional API key override.
api_version	Character. Optional API version override.
...	Additional parameters passed to the API.

Value

A tibble with columns:

role

Character. Always "assistant".

content

Character. The generated response text.

model

Character. The deployment/model name used.

finish_reason

Character. Why generation stopped: "stop", "length", etc.

prompt_tokens

Integer. Tokens in the prompt.

completion_tokens

Integer. Tokens in the response.

reasoning_tokens

Integer. Hidden reasoning tokens, when reported.

cached_input_tokens

Integer. Cached prompt tokens, when reported.

total_tokens

Integer. Total tokens used.

Examples

## Not run: 
# Requires a configured Azure endpoint, credentials, and AZURE_FOUNDRY_MODEL
# naming a chat deployment that supports the requested parameters.
# Simple chat
foundry_chat("What is the capital of France?")

# With system prompt
foundry_chat(
  "Explain tibbles",
  system = "You are a helpful R programming tutor. Be concise."
)

# With parameters (use max_completion_tokens for newer models)
foundry_chat(
  "Write a haiku about data science",
  temperature = 0.9,
  max_completion_tokens = 100
)

# With conversation history
history <- list(
  list(role = "user", content = "My name is Alex"),
  list(role = "assistant", content = "Hello Alex! How can I help you?")
)
foundry_chat("What's my name?", history = history)

## End(Not run)

foundryR documentation built on Sept. 25, 2026, 1:10 a.m.