Configure the default LLM provider and settings for dsprrr. Similar to
DSPy's dspy.configure(lm=lm), this sets up a default Chat that will be
used by dsp() and modules when no explicit Chat is provided.
Arguments
- provider
Character string specifying the provider. One of:
"openai","anthropic","google". IfNULL(default), auto-detects from environment variables.- model
Character string specifying the model name. If
NULL, uses the provider's default model.- api_key
Character string with the API key. If
NULL, reads from the appropriate environment variable.- temperature
Numeric value for temperature (0-2). Default is
NULL(use provider default).- ...
Additional arguments passed to the ellmer chat constructor.
Examples
if (FALSE) { # \dontrun{
# Configure with auto-detection (uses env vars)
dsp_configure()
# Configure with specific provider and model
dsp_configure(provider = "openai", model = "gpt-4o-mini")
# Configure with temperature
dsp_configure(provider = "anthropic", model = "claude-3-5-sonnet-latest",
temperature = 0.7)
# Now dsp() uses this configuration
dsp("question -> answer", question = "What is 2+2?")
} # }
