mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
2a69c76b7f
Address PR #272 review: - get_md_page_content / retrieve._get_md_page_content returned every node whose line_num fell in [min(pages), max(pages)], so a non-contiguous spec like "5,100" over-fetched everything in between. Match the exact requested line numbers instead, mirroring the PDF path. (Same bug as #280.) - Restore the CHATGPT_API_KEY -> OPENAI_API_KEY backward-compat alias dropped when pageindex/utils.py became a re-export shim; users with only CHATGPT_API_KEY set would otherwise fail auth after upgrading. It now runs in __init__.py right after load_dotenv. Adds regression tests for both. Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
64 lines
2.2 KiB
Python
64 lines
2.2 KiB
Python
# pageindex/__init__.py
|
|
# Load .env explicitly, before anything else, so environment-based credentials
|
|
# (OPENAI_API_KEY for local mode, PAGEINDEX_API_KEY that callers read via
|
|
# os.environ for cloud mode) are populated by PageIndex itself — not left to
|
|
# litellm's incidental dotenv loading, which would vanish if litellm changes or
|
|
# its import is ever made lazy.
|
|
from dotenv import load_dotenv as _load_dotenv
|
|
_load_dotenv()
|
|
|
|
# Backward compatibility: honor CHATGPT_API_KEY as an alias for OPENAI_API_KEY
|
|
# (kept from the pre-SDK pageindex.utils). Runs after load_dotenv so a value in
|
|
# .env is picked up too; only fills OPENAI_API_KEY when it isn't already set.
|
|
import os as _os
|
|
if not _os.getenv("OPENAI_API_KEY") and _os.getenv("CHATGPT_API_KEY"):
|
|
_os.environ["OPENAI_API_KEY"] = _os.getenv("CHATGPT_API_KEY")
|
|
|
|
# Upstream exports (backward compatibility). Import from the canonical
|
|
# pageindex.index.* modules directly so `import pageindex` does NOT trip the
|
|
# top-level deprecation shims (pageindex.page_index / .page_index_md / .utils).
|
|
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",
|
|
]
|