text-generation-webui/modules/utils.py

143 lines
4.4 KiB
Python
Raw Permalink Normal View History

2023-05-06 04:14:56 +02:00
import os
import re
from datetime import datetime
2023-05-06 04:14:56 +02:00
from pathlib import Path
2023-09-26 04:48:30 +02:00
from modules import github, shared
from modules.logging_colors import logger
# Helper function to get multiple values from shared.gradio
def gradio(*keys):
2023-08-13 06:12:15 +02:00
if len(keys) == 1 and type(keys[0]) in [list, tuple]:
keys = keys[0]
return [shared.gradio[k] for k in keys]
def save_file(fname, contents):
if fname == '':
logger.error('File name is empty!')
return
root_folder = Path(__file__).resolve().parent.parent
abs_path_str = os.path.abspath(fname)
rel_path_str = os.path.relpath(abs_path_str, root_folder)
rel_path = Path(rel_path_str)
if rel_path.parts[0] == '..':
logger.error(f'Invalid file path: \"{fname}\"')
return
with open(abs_path_str, 'w', encoding='utf-8') as f:
f.write(contents)
logger.info(f'Saved \"{abs_path_str}\".')
def delete_file(fname):
if fname == '':
logger.error('File name is empty!')
return
root_folder = Path(__file__).resolve().parent.parent
abs_path_str = os.path.abspath(fname)
rel_path_str = os.path.relpath(abs_path_str, root_folder)
rel_path = Path(rel_path_str)
if rel_path.parts[0] == '..':
logger.error(f'Invalid file path: \"{fname}\"')
return
2023-12-14 01:54:43 +01:00
if rel_path.exists():
rel_path.unlink()
logger.info(f'Deleted \"{fname}\".')
2023-05-06 04:14:56 +02:00
def current_time():
return f"{datetime.now().strftime('%Y-%m-%d-%H%M%S')}"
2023-05-06 04:14:56 +02:00
def atoi(text):
return int(text) if text.isdigit() else text.lower()
2023-05-10 06:34:04 +02:00
# Replace multiple string pairs in a string
def replace_all(text, dic):
for i, j in dic.items():
text = text.replace(i, j)
return text
2023-05-06 04:14:56 +02:00
def natural_keys(text):
return [atoi(c) for c in re.split(r'(\d+)', text)]
def get_available_models():
2023-11-08 04:59:27 +01:00
model_list = []
for item in list(Path(f'{shared.args.model_dir}/').glob('*')):
if not item.name.endswith(('.txt', '-np', '.pt', '.json', '.yaml', '.py')) and 'llama-tokenizer' not in item.name:
model_list.append(item.name)
return ['None'] + sorted(model_list, key=natural_keys)
def get_available_ggufs():
model_list = []
for item in Path(f'{shared.args.model_dir}/').glob('*'):
if item.is_file() and item.name.lower().endswith(".gguf"):
model_list.append(item.name)
2023-11-08 04:59:27 +01:00
return ['None'] + sorted(model_list, key=natural_keys)
2023-05-06 04:14:56 +02:00
def get_available_presets():
2023-05-29 03:34:12 +02:00
return sorted(set((k.stem for k in Path('presets').glob('*.yaml'))), key=natural_keys)
2023-05-06 04:14:56 +02:00
def get_available_prompts():
2024-07-21 05:01:42 +02:00
prompt_files = list(Path('prompts').glob('*.txt'))
sorted_files = sorted(prompt_files, key=lambda x: x.stat().st_mtime, reverse=True)
prompts = [file.stem for file in sorted_files]
prompts.append('None')
2023-05-06 04:14:56 +02:00
return prompts
def get_available_characters():
paths = (x for x in Path('characters').iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
return sorted(set((k.stem for k in paths)), key=natural_keys)
2023-05-06 04:14:56 +02:00
def get_available_instruction_templates():
path = "instruction-templates"
2023-05-06 04:14:56 +02:00
paths = []
if os.path.exists(path):
paths = (x for x in Path(path).iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
2023-05-10 06:34:04 +02:00
return ['None'] + sorted(set((k.stem for k in paths)), key=natural_keys)
2023-05-06 04:14:56 +02:00
def get_available_extensions():
2023-09-26 04:48:30 +02:00
extensions = sorted(set(map(lambda x: x.parts[1], Path('extensions').glob('*/script.py'))), key=natural_keys)
extensions = [v for v in extensions if v not in github.new_extensions]
return extensions
2023-05-06 04:14:56 +02:00
def get_available_loras():
2023-10-11 03:20:49 +02:00
return ['None'] + sorted([item.name for item in list(Path(shared.args.lora_dir).glob('*')) if not item.name.endswith(('.txt', '-np', '.pt', '.json'))], key=natural_keys)
2023-05-06 04:14:56 +02:00
def get_datasets(path: str, ext: str):
# include subdirectories for raw txt files to allow training from a subdirectory of txt files
if ext == "txt":
return ['None'] + sorted(set([k.stem for k in list(Path(path).glob('*.txt')) + list(Path(path).glob('*/')) if k.stem != 'put-trainer-datasets-here']), key=natural_keys)
2023-05-06 04:14:56 +02:00
return ['None'] + sorted(set([k.stem for k in Path(path).glob(f'*.{ext}') if k.stem != 'put-trainer-datasets-here']), key=natural_keys)
def get_available_chat_styles():
return sorted(set(('-'.join(k.stem.split('-')[1:]) for k in Path('css').glob('chat_style*.css'))), key=natural_keys)
def get_available_grammars():
return ['None'] + sorted([item.name for item in list(Path('grammars').glob('*.gbnf'))], key=natural_keys)