f08aef1804
* Rebuild Studio branch on top of main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix security and code quality issues for Studio PR #4237 - Validate models_dir query param against allowed directory roots to prevent path traversal in /api/models/local endpoint - Replace string startswith() with Path.is_relative_to() for frontend path traversal check in serve_frontend - Sanitize SSE error messages to not leak exception details to clients (4 locations in inference.py) - Bind port-discovery socket to 127.0.0.1 instead of all interfaces in llama_cpp backend - Import datasets_root and resolve_output_dir in embedding training function to fix NameError and use managed output directory - Remove stale .gitignore entries for package-lock.json and test directories so tests can be tracked in version control - Add venv-reexecution logic to ui CLI command matching the studio command behavior * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Move models_dir path validation before try/except block The HTTPException(403) was inside the try/except Exception handler, so it would be caught and re-raised as a 500. Moving the validation before the try block ensures the 403 is returned directly and also makes the control flow clearer for static analysis (path is validated before any filesystem operations). * Use os.path.realpath + startswith for models_dir validation CodeQL py/path-injection does not recognize Path.is_relative_to() as a sanitizer. Switched to os.path.realpath + str.startswith which is a recognized sanitizer pattern in CodeQL's taint analysis. The startswith check uses root_str + os.sep to prevent prefix collisions (e.g. /app/models_evil matching /app/models). * Never pass user input to Path constructor in models_dir validation CodeQL traces taint through Path(resolved) even after a startswith barrier guard. Fix: the user-supplied models_dir is only used as a string for comparison against allowed roots. The Path object passed to _scan_models_dir comes from the trusted allowed_roots list, not from user input. This fully breaks the taint chain. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
105 lines
2.8 KiB
Python
105 lines
2.8 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""
|
|
Dataset utilities package.
|
|
|
|
This package provides utilities for dataset format detection, conversion,
|
|
and processing for LLM and VLM fine-tuning workflows.
|
|
|
|
Modules:
|
|
- format_detection: Detect dataset formats (Alpaca, ShareGPT, ChatML)
|
|
- format_conversion: Convert between dataset formats
|
|
- chat_templates: Apply chat templates to datasets
|
|
- vlm_processing: Vision-Language Model processing utilities
|
|
- data_collators: Custom data collators for training
|
|
- model_mappings: Model-to-template mapping constants
|
|
"""
|
|
|
|
# Format detection
|
|
from .format_detection import (
|
|
detect_dataset_format,
|
|
detect_custom_format_heuristic,
|
|
detect_multimodal_dataset,
|
|
detect_vlm_dataset_structure,
|
|
)
|
|
|
|
# Format conversion
|
|
from .format_conversion import (
|
|
standardize_chat_format,
|
|
convert_chatml_to_alpaca,
|
|
convert_alpaca_to_chatml,
|
|
convert_to_vlm_format,
|
|
convert_llava_to_vlm_format,
|
|
convert_sharegpt_with_images_to_vlm_format,
|
|
)
|
|
|
|
# Chat templates
|
|
from .chat_templates import (
|
|
apply_chat_template_to_dataset,
|
|
get_dataset_info_summary,
|
|
get_tokenizer_chat_template,
|
|
DEFAULT_ALPACA_TEMPLATE,
|
|
)
|
|
|
|
# VLM processing
|
|
from .vlm_processing import (
|
|
generate_smart_vlm_instruction,
|
|
)
|
|
|
|
# Data collators
|
|
from .data_collators import (
|
|
DataCollatorSpeechSeq2SeqWithPadding,
|
|
DeepSeekOCRDataCollator,
|
|
VLMDataCollator,
|
|
)
|
|
|
|
# Model mappings (constants)
|
|
from .model_mappings import (
|
|
TEMPLATE_TO_MODEL_MAPPER,
|
|
MODEL_TO_TEMPLATE_MAPPER,
|
|
TEMPLATE_TO_RESPONSES_MAPPER,
|
|
)
|
|
|
|
# Legacy imports from the original dataset_utils.py for backward compatibility
|
|
# These functions have not yet been refactored into separate modules
|
|
from .dataset_utils import (
|
|
check_dataset_format,
|
|
format_and_template_dataset,
|
|
format_dataset,
|
|
)
|
|
|
|
# Public API
|
|
__all__ = [
|
|
# Detection
|
|
"detect_dataset_format",
|
|
"detect_custom_format_heuristic",
|
|
"detect_multimodal_dataset",
|
|
"detect_vlm_dataset_structure",
|
|
# Conversion
|
|
"standardize_chat_format",
|
|
"convert_chatml_to_alpaca",
|
|
"convert_alpaca_to_chatml",
|
|
"convert_to_vlm_format",
|
|
"convert_llava_to_vlm_format",
|
|
"convert_sharegpt_with_images_to_vlm_format",
|
|
# Templates
|
|
"apply_chat_template_to_dataset",
|
|
"get_dataset_info_summary",
|
|
"get_tokenizer_chat_template",
|
|
"DEFAULT_ALPACA_TEMPLATE",
|
|
# VLM
|
|
"generate_smart_vlm_instruction",
|
|
# Collators
|
|
"DataCollatorSpeechSeq2SeqWithPadding",
|
|
"DeepSeekOCRDataCollator",
|
|
"VLMDataCollator",
|
|
# Mappings
|
|
"TEMPLATE_TO_MODEL_MAPPER",
|
|
"MODEL_TO_TEMPLATE_MAPPER",
|
|
"TEMPLATE_TO_RESPONSES_MAPPER",
|
|
# Main entry points
|
|
"check_dataset_format",
|
|
"format_and_template_dataset",
|
|
"format_dataset",
|
|
]
|