Interface for Large Language Model APIs in R

Documentation for package ‘LLMR’ version 0.8.6

Help Pages

as.character.llmr_response	LLMR Response Object
as.data.frame.llm_chat_session	Chat Session Object and Methods
bind_tools	Bind tools to a config (provider-agnostic)
build_factorial_experiments	Build Factorial Experiment Design
call_llm	Call an LLM (chat/completions or embeddings) with optional multimodal input
call_llm.ollama	Call an LLM (chat/completions or embeddings) with optional multimodal input
call_llm_broadcast	Parallel API calls: Fixed Config, Multiple Messages
call_llm_compare	Parallel API calls: Multiple Configs, Fixed Message
call_llm_par	Parallel LLM Processing with Tibble-Based Experiments (Core Engine)
call_llm_par_structured	Parallel experiments with structured parsing
call_llm_par_tags	Parallel experiments with tag parsing
call_llm_robust	Robustly Call LLM API (Simple Retry)
call_llm_stream	Stream a chat completion token by token
call_llm_sweep	Parallel API calls: Parameter Sweep - Vary One Parameter, Fixed Message
call_llm_tools	Call an LLM with tools and run the tool loop
chat_session	Chat Session Object and Methods
diagnostics	Machine-readable diagnostics for an LLMR-family result object
disable_structured_output	Disable Structured Output (clean provider toggles)
enable_structured_output	Enable Structured Output (Provider-Agnostic)
expand_llm_config	Expand an LLM Config Grid
finish_reason	LLMR Response Object
format.llm_config	Print an LLM configuration with the API key masked
get_batched_embeddings	Generate Embeddings in Batches
head.llm_chat_session	Chat Session Object and Methods
is_truncated	LLMR Response Object
llmr_response	LLMR Response Object
llm_agreement	Agreement across replicated LLM annotations
llm_api_key_env	Declare an API key sourced from an environment variable
llm_batch_cancel	Cancel a batch job
llm_batch_fetch	Fetch the results of a batch job
llm_batch_status	Check the status of a batch job
llm_batch_submit	Submit a batch job to a provider's batch API
llm_chat_session	Chat Session Object and Methods
llm_config	Create an LLM configuration (provider-agnostic)
llm_cross_design	Cross a data frame with LLM configs
llm_failures	List the rows of an LLM run that failed or were truncated
llm_fn	Apply an LLM prompt over vectors/data frames
llm_fn_structured	Vectorized structured-output LLM
llm_fn_tags	Vectorized LLM with tag extraction
llm_hash	Content hash for research artifacts
llm_judge	LLM-as-a-Judge Evaluation
llm_logprobs	Extract token log-probabilities from a response
llm_log_disable	Record every LLM call in a local audit log
llm_log_enable	Record every LLM call in a local audit log
llm_log_read	Read an LLMR audit log into records and a manifest
llm_log_status	Record every LLM call in a local audit log
llm_methods_text	Draft a methods-section paragraph from an LLM run
llm_mutate	Mutate a data frame with LLM output
llm_mutate_structured	Data-frame mutate with structured output
llm_mutate_tags	Data-frame mutate with XML-like tag output
llm_parse_rowpack_tags	Parse a batched, row-wrapped tag response into per-row field lists
llm_parse_structured	Parse structured output emitted by an LLM
llm_parse_structured_col	Parse structured fields from a column into typed vectors
llm_parse_tags	Parse XML-like tags emitted by an LLM
llm_parse_tags_col	Parse XML-like tag fields from a column
llm_par_resume	Resume failed parallel LLM calls
llm_preview	Preview a tidy LLM call without spending anything
llm_render_messages	Render tidy messages without calling any API
llm_replicate	Run the same prompt several times per row
llm_request_from_log	Rebuild a callable request from a logged record
llm_request_hash	Stable request hash for an LLM call
llm_response_record	Flatten one LLM response to a provenance row
llm_tool	Define a tool the model may call
llm_usage	Summarize token usage and outcomes of an LLM run
llm_validate_structured_col	Validate structured JSON objects against a JSON Schema (locally)
parse_embeddings	Parse Embedding Response into a Numeric Matrix
print.llmr_response	LLMR Response Object
print.llm_chat_session	Chat Session Object and Methods
print.llm_config	Print an LLM configuration with the API key masked
report	Draft a methods-section report from an LLMR-family result object
reset	Reset a stateful object to its initial position
reset_llm_parallel	Reset Parallel Environment
setup_llm_parallel	Setup Parallel Environment for LLM Processing
summary.llm_chat_session	Chat Session Object and Methods
tail.llm_chat_session	Chat Session Object and Methods
tokens	LLMR Response Object
tool_calls	Extract tool calls from a response