Automatic Item Generation and Validation via Network-Integrated Evaluation

---

Documentation for package ‘AIGENIE’ version 2.1.2

• DESCRIPTION file
• User guides, package vignettes and other documentation

Help Pages

AIGENIE	Generate, Validate, and Check Items using AI-GENIE
build_item_attributes_from_items	Build item.attributes Object from Items Data Frame
chat	Chat with an LLM via API Calls
check_for_default_APIs	Check for users who pasted the example code but didn't add an API key
check_local_llm_setup	Check Local LLM Setup
embeddings.gpt5.4.example	GPT-5.4 Example Item Embeddings
embedding_matrix_validate_GENIE	Validate Embedding Matrix for GENIE
ensure_aigenie_python	Ensure AI-GENIE Python Environment is Ready
final_community_detection	Run Final Community Detection with EGA
GENIE	The use of the psychometric reduction component of AIGENIE on your pre-existing item pool
get_local_llm	Download a Local LLM Model
install_gpu_support	Install GPU Support for AI-GENIE
install_local_llm_support	Install Local LLM Support
item.examples_validate	Validate and Clean 'item.examples' Against Cleaned 'items.attributes'
item.type.definitions_validate	Validate and Clean 'item.type.definitions'
items.attributes_validate	Validate 'items.attributes'
items.gpt5.4.example	GPT-5.4 Example Item Pool
items_validate_GENIE	Validate Items Data Frame for GENIE
iterative_stability_check	Iteratively run BootEGA to ensure structural stability of items
list_available_models	List Available Models
local_AIGENIE	Generate and Validate Psychometric Scale Items Using Local Models
local_chat	Chat with a local LLM (no API calls)
local_GENIE	Local Generative Network-Integrated Evaluation (local_GENIE)
main.prompts_validate	Validate and Normalize 'main.prompts'
max.tokens_validate	Check that max.tokens is an integer
plot_comparison	Plot Comparisons
plot_stability_comparison	Plot Stability Comparison (network + item stability dotplot, side by side)
print_results	Print Results
python_env_info	Get AI-GENIE Python Environment Info
reduce_redundancy_uva	Reduce Redundancy via Iterative UVA (with Redundant Pair Logging)
reinstall_python_env	Reinstall AI-GENIE Python Environment
resolve_model_name	Resolve and Normalize Model Name
response.options_validate	Validate and Clean 'response.options'
run_flags_validate	Check that the 'run.overall' and 'all.together' flags are logically consistent with the number of item types.
run_item_reduction_pipeline	Run reduction pipeline for all item types
run_pipeline_for_item_type	Run full pipeline for a single item type
select_optimal_embedding	Select Optimal Embedding and EGA Model Based on NMI
set_huggingface_token	Set Hugging Face Token
sparsify_embeddings	Sparsify Embedding Matrix
target.N_validate	Validate and Expand 'target.N' for Each Item Attribute
temperature_validate	Validate 'temperature' for Text Generation
top.p_validate	Validate 'top.p' for Text Generation
uva.cut.off_validate	Validate 'uva.cut.off'
validate_booleans	Validate Boolean Arguments
validate_ega_params	Validate EGA Parameters
validate_local_embedding_model	Validate Local Embedding Model
validate_local_embedding_params	Validate Local Embedding Parameters
validate_local_llm_params	Validate Local LLM Generation Parameters
validate_model.path	Validate Local Model Path
validate_prompt.notes	Validate and Normalize 'prompt.notes'
validate_reps	Check that reps is an integer
validate_strings	Validate That Inputs Are Strings
validate_system.role_prompts	Checks 'system.role' and 'prompts' for the 'chat' function
validate_user_input_AIGENIE	Validate All User Inputs for AI-GENIE
validate_user_input_GENIE	Validate All User Inputs for GENIE
validate_user_input_local_AIGENIE	Validate All User Inputs for Local AI-GENIE
validate_user_input_local_GENIE	Validate All User Inputs for Local GENIE