id: 1
unit: def launch()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 69 LOC
McCabe index: 11
number of parameters: 0

id: 2
unit: def process_tar_index()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 55 LOC
McCabe index: 6
number of parameters: 3

id: 3
unit: def process_tar_index()
file: create_only_with_pdfs/load_data.py
start line: 0
end line: 0
size: 40 LOC
McCabe index: 5
number of parameters: 3

id: 4
unit: def create_tasks()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 26 LOC
McCabe index: 6
number of parameters: 3

id: 5
unit: def extract_chunks()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 23 LOC
McCabe index: 9
number of parameters: 4

id: 6
unit: def process_outputs_to_df()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 21 LOC
McCabe index: 4
number of parameters: 1

id: 7
unit: def process_group()
file: create_only_with_pdfs/load_data.py
start line: 0
end line: 0
size: 21 LOC
McCabe index: 6
number of parameters: 1

id: 8
unit: def process_group()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 21 LOC
McCabe index: 6
number of parameters: 1

id: 9
unit: def load_and_concatenate_dataframes()
file: create_only_with_pdfs/load_data.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 8
number of parameters: 0

id: 10
unit: def load_and_concatenate_dataframes()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 8
number of parameters: 0

id: 11
unit: def is_valid_question_or_answer()
file: create_only_with_pdfs/load_data.py
start line: 0
end line: 0
size: 15 LOC
McCabe index: 4
number of parameters: 1

id: 12
unit: def resize_large_images()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 15 LOC
McCabe index: 6
number of parameters: 2

id: 13
unit: def is_valid_question_or_answer()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 15 LOC
McCabe index: 4
number of parameters: 1

id: 14
unit: def get_datasets()
file: create_only_with_pdfs/upload_data.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 5
number of parameters: 0

id: 15
unit: def count_words()
file: analysis/count_words_in_dataset.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 2
number of parameters: 2

id: 16
unit: def create_prompts()
file: generation/base_prompts.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 2
number of parameters: 1

id: 17
unit: def create_llm_prompt()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 2

id: 18
unit: def text_generator()
file: florence_2_dataset/create_florence_2_dataset.py
start line: 0
end line: 0
size: 8 LOC
McCabe index: 2
number of parameters: 1

id: 19
unit: def save_checkpoint()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 1
number of parameters: 2

id: 20
unit: def img_generator()
file: florence_2_dataset/create_florence_2_dataset.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 2
number of parameters: 1

id: 21
unit: def extract_text_per_page_from_sample()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 2
number of parameters: 2

id: 22
unit: def extract_qa_pairs()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 3
number of parameters: 1

id: 23
unit: def load_checkpoint()
file: generation/llm_swarm_script.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 2
number of parameters: 0

id: 24
unit: def convert_img_to_png_bytes()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 1
number of parameters: 1

id: 25
unit: def process_images()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 2
number of parameters: 1

id: 26
unit: def _decode_pdf_pages()
file: clean_and_create/load_data.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 0