mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-24 21:41:04 +02:00
15b0b18857
Once litellm/PyPDF2 moved inside the functions that use them, the legacy modules became cheap to import — the PEP 562 __getattr__ table in __init__ was guarding a door that no longer needs guarding. Restore plain eager imports (~0.3s total, still zero heavy deps at import); keep only the small submodule __getattr__ for pageindex.utils / pageindex.page_index_md attribute access.
79 lines
2.3 KiB
Python
79 lines
2.3 KiB
Python
# pageindex/__init__.py
|
|
# Load .env first so env-based credentials (e.g. OPENAI_API_KEY) are set.
|
|
from dotenv import load_dotenv as _load_dotenv
|
|
_load_dotenv()
|
|
|
|
# Backward compatibility: honor CHATGPT_API_KEY as an alias for OPENAI_API_KEY.
|
|
import os as _os
|
|
_chatgpt_key = _os.getenv("CHATGPT_API_KEY")
|
|
if not _os.getenv("OPENAI_API_KEY") and _chatgpt_key:
|
|
_os.environ["OPENAI_API_KEY"] = _chatgpt_key
|
|
|
|
# Legacy (pre-SDK) exports. Cheap to import eagerly: litellm/PyPDF2 load
|
|
# inside the functions that use them, not at module import.
|
|
from .index.page_index import * # noqa: E402
|
|
from .index.page_index_md import md_to_tree
|
|
from .retrieve import get_document, get_document_structure, get_page_content
|
|
|
|
# SDK exports
|
|
from .client import PageIndexClient, LocalClient, CloudClient
|
|
from .config import IndexConfig, set_llm_params
|
|
from .collection import Collection
|
|
from .types import DocumentInfo, DocumentDetail, PageContent
|
|
from .parser.protocol import ContentNode, ParsedDocument, DocumentParser
|
|
from .storage.protocol import StorageEngine
|
|
from .events import QueryEvent
|
|
from .errors import (
|
|
PageIndexError,
|
|
PageIndexAPIError,
|
|
CollectionNotFoundError,
|
|
DocumentNotFoundError,
|
|
IndexingError,
|
|
CloudAPIError,
|
|
FileTypeError,
|
|
)
|
|
|
|
__all__ = [
|
|
"PageIndexClient",
|
|
"LocalClient",
|
|
"CloudClient",
|
|
"IndexConfig",
|
|
"set_llm_params",
|
|
"Collection",
|
|
"DocumentInfo",
|
|
"DocumentDetail",
|
|
"PageContent",
|
|
"ContentNode",
|
|
"ParsedDocument",
|
|
"DocumentParser",
|
|
"StorageEngine",
|
|
"QueryEvent",
|
|
"PageIndexError",
|
|
"PageIndexAPIError",
|
|
"CollectionNotFoundError",
|
|
"DocumentNotFoundError",
|
|
"IndexingError",
|
|
"CloudAPIError",
|
|
"FileTypeError",
|
|
# Legacy top-level exports (pre-SDK API), kept so `from pageindex import *`
|
|
# still binds them.
|
|
"page_index",
|
|
"page_index_main",
|
|
"tree_parser",
|
|
"ConfigLoader",
|
|
"llm_completion",
|
|
"llm_acompletion",
|
|
"md_to_tree",
|
|
"get_document",
|
|
"get_document_structure",
|
|
"get_page_content",
|
|
]
|
|
|
|
|
|
def __getattr__(name):
|
|
# `pageindex.utils` / `pageindex.page_index_md` attribute access without an
|
|
# explicit submodule import.
|
|
if name in ("utils", "page_index_md"):
|
|
import importlib
|
|
return importlib.import_module(f".{name}", __name__)
|
|
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|