mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
cf7f5ce9bf
Verified against current dev; the compat/behavior decisions (#7 api_key semantics, #10 CLI flags, #11 doc-description default) are deferred. Crashes: - page_index(): snapshot args before importing IndexConfig — locals() was capturing the imported class and IndexConfig(extra='forbid') made every call raise ValidationError. - process_none_page_numbers: pop('page', None) instead of del (a TOC item without 'page' raised KeyError mid-pipeline). - pipeline._run_async: guard only the loop detection, not the run, so a real RuntimeError from the coroutine isn't masked as "asyncio.run() cannot be called from a running event loop". Silent-wrong / robustness: - LocalBackend.get_document_structure and the agent get_document / get_document_structure tools now surface a missing doc (raise / error-JSON) instead of returning empty, matching get_page_content and the cloud backend. - cloud delete_collection drops the cached folder_id. - cloud query raises on an empty collection instead of POSTing doc_id:[]. - LocalClient skips the API-key check for keyless providers (ollama, lm_studio, …) so keyless LiteLLM models aren't rejected at construction. Compat / cleanup: - md_to_tree coerces legacy 'yes'/'no' string flags (a bare 'no' was truthy). - FileTypeError also subclasses ValueError (0.2.x raised ValueError). - _validate_llm_provider no longer mutates global litellm.model_cost_map_url. - __all__ re-includes legacy exports (page_index, md_to_tree, get_*). - Rewrite examples/agentic_vectorless_rag_demo.py to the Collection API and use the in-repo attention.pdf (the old workspace=/client.index/client.documents API no longer exists). Adds tests/test_review_fixes.py (10 regressions). Full suite: 189 passed. Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
71 lines
2.4 KiB
Python
71 lines
2.4 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",
|
|
# Legacy top-level exports (pre-SDK API), kept so `from pageindex import *`
|
|
# still binds them.
|
|
"page_index",
|
|
"md_to_tree",
|
|
"get_document",
|
|
"get_document_structure",
|
|
"get_page_content",
|
|
]
|