Package index • AIscreenR

Screen with GPT API models

R functions to automate title and abstract screeening with GPT API models

tabscreen_gpt.tools() tabscreen_gpt() stable: Title and abstract screening with GPT API models using function calls via the tools argument

tabscreen_gpt.original() deprecated: Title and abstract screening with GPT API models using function calls via the original function call arguments

Screen failed requests

R functions to re-screen failied title and abstract requests

screen_errors() experimental: Generic function to re-screen failed title and abstract requests.

screen_errors(<gpt>) experimental: Re-screen failed requests.

screen_errors(<chatgpt>) deprecated: Re-screen failed requests.

Analyze screening performance

R functions to analyze agreement between humans and GPT

screen_analyzer() stable: Analyze performance between the human and AI screening.

Fine tuning

R functions generate data that can be used for fine tuning of models

create_fine_tune_data(): Function to generate dataset to be used for fine-tuning models

save_fine_tune_data(): Function to write/save fine tune dataset in required jsonl format

API management

R functions to ease and automate API management

set_api_key(): Creating a temporary R environment API key variable

get_api_key(): Get API key from R environment variable.

Rate limits

R functions to find api rate limits

rate_limits_per_minute() stable: Find updated rate limits for API models

Datasets

Datasets in the package

filges2015_dat: RIS file data from Functional Family Therapy (FFT) systematic review

model_prizes: Model prize data (last updated August 14, 2025)

Coercion

is_chatgpt() deprecated: Test if the object is a 'chatgpt' object

is_chatgpt_tbl() deprecated: Test if the object is a 'chatgpt_tbl' object

is_gpt(): Test if the object is a 'gpt' object

is_gpt_tbl(): Test if the object is a 'gpt_tbl' object

is_gpt_agg_tbl(): Test if the object is a 'gpt_agg_tbl' object

Print methods

print(<gpt>): Print methods for 'gpt' objects

print(<chatgpt>): Print methods for 'chatgpt' objects

print(<gpt_price>): Print methods for 'gpt_price' objects

Pricing

approximate_price_gpt() experimental: Approximate price estimation for title and abstract screening using OpenAI's GPT API models

Sample references

Sample references to construct test dataset

sample_references(): Random sample references