224b7b74c1
* feat: accept pdf, images and office files * refactor: rename FileConverter to FileParser, simplify file retain API - Rename engine/converters/ → engine/parsers/, FileConverter → FileParser, ConverterRegistry → FileParserRegistry, MarkitdownConverter → MarkitdownParser - Rename env var HINDSIGHT_API_FILE_CONVERTER → HINDSIGHT_API_FILE_PARSER - Remove async/document_tags params from FileRetainRequest (always async now) - Add retain_files() to Python Hindsight client and retainFiles() to TypeScript client - Add sample.pdf to doc examples for working file upload demonstrations - Update test_file_retain.py to use new parser names and always-async behavior - Fix Go client missing os import in api_files.go - Simplify postgresql.py storage to minimal schema * fix: update rust CLI tests to use is_supported_file instead of is_text_file * fix: patch Go api_files.go to add missing 'os' import after generation * fix: insert 'os' import after 'net/url' in api_files.go patch for correct position * chore: regenerate OpenAPI spec and clients (converter→parser description update)
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
"""Google Cloud Storage backend using obstore."""
|
|
|
|
import logging
|
|
from datetime import timedelta
|
|
|
|
import obstore as obs
|
|
from obstore.store import GCSStore
|
|
|
|
from .base import FileStorage
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class GCSFileStorage(FileStorage):
|
|
"""
|
|
Google Cloud Storage backend.
|
|
|
|
Uses obstore (Rust-backed) for high-throughput async access to GCS.
|
|
Supports Application Default Credentials, service account keys, and explicit credentials.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
bucket: str,
|
|
service_account_key: str | None = None,
|
|
):
|
|
kwargs: dict = {}
|
|
if service_account_key:
|
|
kwargs["service_account_key"] = service_account_key
|
|
|
|
self._store = GCSStore(bucket, **kwargs)
|
|
logger.info(f"Initialized GCS file storage: bucket={bucket}")
|
|
|
|
async def store(self, file_data: bytes, key: str, metadata: dict[str, str] | None = None) -> str:
|
|
await obs.put_async(self._store, key, file_data)
|
|
logger.debug(f"Stored file {key} ({len(file_data)} bytes) in GCS")
|
|
return key
|
|
|
|
async def retrieve(self, key: str) -> bytes:
|
|
try:
|
|
response = await obs.get_async(self._store, key)
|
|
return await response.bytes_async()
|
|
except Exception as e:
|
|
if "not found" in str(e).lower():
|
|
raise FileNotFoundError(f"File not found: {key}") from e
|
|
raise
|
|
|
|
async def delete(self, key: str) -> None:
|
|
await obs.delete_async(self._store, key)
|
|
|
|
async def exists(self, key: str) -> bool:
|
|
try:
|
|
await obs.head_async(self._store, key)
|
|
return True
|
|
except Exception:
|
|
return False
|
|
|
|
async def get_download_url(self, key: str, expires_in: int = 3600) -> str:
|
|
return await obs.sign_async(self._store, "GET", key, timedelta(seconds=expires_in))
|