mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
284ce005f5
Fixes the cloud/local contract mismatches from the PR #272 review (verified against the official API docs — the cloud API has no folder/collection endpoints publicly, GET /docs supports limit<=100 with offset): - query_stream: emit a terminal answer_done event with the full answer (same contract as the local backend); raise CloudAPIError instead of disguising HTTP errors as answer events; move the initial connect inside try so a connection failure can no longer strand the consumer awaiting a sentinel that never arrives - _request: rewind file objects before retrying so a transient 5xx/429 during upload no longer re-sends an empty multipart body; carry the HTTP status on CloudAPIError (status_code) and keep the last status in the max-retries error - list_documents: paginate with limit/offset instead of a hard-coded limit=100, so >100-doc collections are no longer silently truncated (whole-collection queries rely on this list) - folders: treat only 403/404 as "folders unavailable" (warned via warnings.warn instead of an invisible logger.warning, matched on status_code instead of a "403" substring); transient errors now propagate instead of being permanently cached as folder_id=None - error taxonomy parity: cloud doc endpoints map HTTP 404 to DocumentNotFoundError; local get_document raises DocumentNotFoundError instead of returning {}; local delete_document raises on missing doc_id instead of silently deleting nothing - cloud get_document warns that include_text is not supported instead of silently ignoring it Adds regression tests for each fix (11 new tests). Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
44 lines
1 KiB
Python
44 lines
1 KiB
Python
class PageIndexError(Exception):
|
|
"""Base exception for all PageIndex SDK errors."""
|
|
pass
|
|
|
|
|
|
class CollectionNotFoundError(PageIndexError):
|
|
"""Collection does not exist."""
|
|
pass
|
|
|
|
|
|
class DocumentNotFoundError(PageIndexError):
|
|
"""Document ID not found."""
|
|
pass
|
|
|
|
|
|
class IndexingError(PageIndexError):
|
|
"""Indexing pipeline failure."""
|
|
pass
|
|
|
|
|
|
class PageIndexAPIError(PageIndexError):
|
|
"""PageIndex cloud API returned an error.
|
|
|
|
Kept for compatibility with the pageindex 0.2.x cloud SDK.
|
|
"""
|
|
pass
|
|
|
|
|
|
class CloudAPIError(PageIndexAPIError):
|
|
"""Cloud API returned error.
|
|
|
|
``status_code`` carries the HTTP status when the error came from an HTTP
|
|
response (None for transport-level failures), so callers can branch on it
|
|
instead of parsing the message.
|
|
"""
|
|
|
|
def __init__(self, message: str, status_code: int | None = None):
|
|
super().__init__(message)
|
|
self.status_code = status_code
|
|
|
|
|
|
class FileTypeError(PageIndexError):
|
|
"""Unsupported file type."""
|
|
pass
|