Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
"""Core data layer: database, file I/O, and full-text search."""
from .db import DatabaseManager
from .file_io import FileStat, MetadataExtractionError, compute_sha256, extract_metadata, get_file_stat
from .fts import FTSManager, strip_sep, tokenize_for_index, tokenize_for_query
from .middle_json import read_cached_middle_json
from .parse_artifacts import (
accessible_file_for_sha256,
filter_pages_by_user_range,
load_pages_from_done_batches,
parse_artifact_directory,
parse_batch_is_readable,
parse_batch_json_path,
parse_coverage,
write_parse_payload,
)
__all__ = [
"DatabaseManager",
"accessible_file_for_sha256",
"filter_pages_by_user_range",
"load_pages_from_done_batches",
"parse_artifact_directory",
"parse_batch_is_readable",
"parse_batch_json_path",
"parse_coverage",
"read_cached_middle_json",
"write_parse_payload",
"FTSManager",
"FileStat",
"MetadataExtractionError",
"compute_sha256",
"extract_metadata",
"get_file_stat",
"strip_sep",
"tokenize_for_index",
"tokenize_for_query",
]