Package: AIGENIE 2.1.0

AIGENIE: Automatic Item Generation and Validation via Network-Integrated Evaluation

Automated psychological scale development and structural validation using large language models (LLMs) and network psychometric methods. Implements the AI-GENIE framework (Automatic Item Generation and Validation via Network-Integrated Evaluation) to generate candidate items, compute embedding representations, and estimate dimensional structure using Exploratory Graph Analysis (EGA). Item quality is evaluated using Unique Variable Analysis to identify redundant items and Bootstrap EGA to assess item and dimension stability. Supports both fully automated item generation and analysis of user-provided item sets, facilitating efficient, theory-informed measurement development prior to empirical data collection.

Authors:Lara Russell-Lasalandra [cre], Alexander Christensen [aut], Hudson Golino [aut]

AIGENIE_2.1.0.tar.gz
AIGENIE_2.1.0.zip(r-4.7)AIGENIE_2.1.0.zip(r-4.6)AIGENIE_2.1.0.zip(r-4.5)
AIGENIE_2.1.0.tgz(r-4.6-any)AIGENIE_2.1.0.tgz(r-4.5-any)
AIGENIE_2.1.0.tar.gz(r-4.7-any)AIGENIE_2.1.0.tar.gz(r-4.6-any)
AIGENIE_2.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html
DESCRIPTION
card.svg |card.png
AIGENIE/json (API)

# Install 'AIGENIE' in R:
install.packages('AIGENIE', repos = c('https://laralee.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/laralee/aigenie/issues

On CRAN:

Conda:

4.07 score 18 stars 4 scripts 15 exports 169 dependencies

Last updated from:e72bb46f29. Checks:7 WARNING, 2 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64WARNING273
source / vignettesOK268
linux-release-x86_64WARNING246
macos-release-arm64WARNING116
macos-oldrel-arm64WARNING117
windows-develWARNING213
windows-releaseWARNING179
windows-oldrelWARNING211
wasm-releaseOK197

Exports:AIGENIEchatcheck_local_llm_setupensure_aigenie_pythonGENIEget_local_llminstall_gpu_supportinstall_local_llm_supportlist_available_modelslocal_AIGENIElocal_chatlocal_GENIEpython_env_inforeinstall_python_envset_huggingface_token

Dependencies:abindarmbackportsbase64encBHbootbroombslibcachemcarcarDatacheckmatecliclueclustercodacodetoolscolorspacecorpcorcorrplotcowplotcpp11crayondata.tabledendextendDerivdigestdoBydplyrEGAnetevaluatefarverfastmapfdrtoolfontawesomeforcatsforecastforeignFormulafracdifffsfuturefuture.applygenericsGGallyggplot2ggpubrggrepelggsciggsignifggstatsglassoglassoFastglobalsglueGPArotationgridExtragtablegtoolsherehighrHmischmshtmlTablehtmltoolshtmlwidgetsigraphisobandjpegjquerylibjsonliteknitrkutilslabelinglatticelavaanlifecyclelisrelToRlistenvlme4lmtestmagrittrMASSMatrixMatrixModelsmemoisemgcvmimimeminqamnormtmodelrmvtnormnetworknlmenloptrnnetnumDerivOpenMxopenxlsxparallellypatchworkpbapplypbivnormpbkrtestpillarpkgconfigplyrpngpolynomprettyunitsprogressprogressrpsychpurrrqgraphquadprogquantregR6rappdirsrbibutilsRColorBrewerRcppRcppArmadilloRcppEigenRcppParallelRcppTOMLRdpackreformulasreshape2reticulaterlangrmarkdownrockchalkrpartrpfrprojrootrstatixrstudioapiRUnitS7sassscalessemsemPlotsnaSparseMStanHeadersstatnet.commonstringistringrsurvivaltibbletidyrtidyselecttimeDatetinytexurcautf8vctrsviridisviridisLitewithrxfunXMLxtableyamlzipzoo

Readme and manuals

Help Manual

Help pageTopics
Generate, Validate, and Check Items using AI-GENIEAIGENIE
Build item.attributes Object from Items Data Framebuild_item_attributes_from_items
Build the proper return object based on if the initial items should be kept and if an overall analysis was runbuild_return
Run bootstrapped EGA on the initial set of itemscalc_final_stability
Chat with an LLM via API Callschat
Check for users who pasted the example code but didn't add an API keycheck_for_default_APIs
Check Local LLM Setupcheck_local_llm_setup
Validate Embedding Matrix for GENIEembedding_matrix_validate_GENIE
Ensure AI-GENIE Python Environment is Readyensure_aigenie_python
Run Final Community Detection with EGAfinal_community_detection
The use of the psychometric reduction component of AIGENIE on your pre-existing item poolGENIE
Download a Local LLM Modelget_local_llm
Install GPU Support for AI-GENIEinstall_gpu_support
Install Local LLM Supportinstall_local_llm_support
Validate and Clean 'item.examples' Against Cleaned 'items.attributes'item.examples_validate
Validate and Clean 'item.type.definitions'item.type.definitions_validate
Validate Items Data Frame for GENIEitems_validate_GENIE
Validate 'items.attributes'items.attributes_validate
Iteratively run BootEGA to ensure structural stability of itemsiterative_stability_check
List Available Modelslist_available_models
Generate and Validate Psychometric Scale Items Using Local Modelslocal_AIGENIE
Chat with a local LLM (no API calls)local_chat
Local Generative Network-Integrated Evaluation (local_GENIE)local_GENIE
Validate and Normalize 'main.prompts'main.prompts_validate
Check that max.tokens is an integermax.tokens_validate
Plot Comparisonsplot_comparison
Plot Stability Comparison (network + item stability dotplot, side by side)plot_stability_comparison
Print Resultsprint_results
Get AI-GENIE Python Environment Infopython_env_info
Reduce Redundancy via Iterative UVA (with Redundant Pair Logging)reduce_redundancy_uva
Reinstall AI-GENIE Python Environmentreinstall_python_env
Resolve and Normalize Model Nameresolve_model_name
Validate and Clean 'response.options'response.options_validate
Modify the items data frame to run the reduction on all items togetherrun_all_together
Check that the 'run.overall' and 'all.together' flags are logically consistent with the number of item types.run_flags_validate
Run reduction pipeline for all item typesrun_item_reduction_pipeline
Run full pipeline for all items in the samplerun_pipeline_for_all
Run full pipeline for a single item typerun_pipeline_for_item_type
Select Optimal Embedding and EGA Model Based on NMIselect_optimal_embedding
Set Hugging Face Tokenset_huggingface_token
Sparsify Embedding Matrixsparsify_embeddings
Validate and Expand 'target.N' for Each Item Attributetarget.N_validate
Validate 'temperature' for Text Generationtemperature_validate
Validate 'top.p' for Text Generationtop.p_validate
Validate 'uva.cut.off'uva.cut.off_validate
Validate Boolean Argumentsvalidate_booleans
Validate EGA Parametersvalidate_ega_params
Validate Local Embedding Modelvalidate_local_embedding_model
Validate Local Embedding Parametersvalidate_local_embedding_params
Validate Local LLM Generation Parametersvalidate_local_llm_params
Validate Local Model Pathvalidate_model.path
Validate and Normalize 'prompt.notes'validate_prompt.notes
Check that reps is an integervalidate_reps
Validate That Inputs Are Stringsvalidate_strings
Checks 'system.role' and 'prompts' for the 'chat' functionvalidate_system.role_prompts
Validate All User Inputs for AI-GENIEvalidate_user_input_AIGENIE
Validate All User Inputs for GENIEvalidate_user_input_GENIE
Validate All User Inputs for Local AI-GENIEvalidate_user_input_local_AIGENIE
Validate All User Inputs for Local GENIEvalidate_user_input_local_GENIE