gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(watch-folders): add local/FTP/SFTP watch folder ingest with settings, tasks, tests, docs

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-03-07 21:06:42 +00:00
parent ca717aa01f
commit bdb67de5cb
10 changed files with 1395 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/config.py
+77
View File
@@ -190,6 +190,83 @@ class Settings(BaseSettings):
stripe_success_url: Optional[str] = None # e.g. https://app.example.com/billing/success
stripe_cancel_url: Optional[str] = None # e.g. https://app.example.com/pricing
# ---------------------------------------------------------------------------
# Watch Folder Ingestion
# ---------------------------------------------------------------------------
# Local filesystem watch folders (comma-separated list of absolute paths).
# DocuElevate will poll each path for new files and automatically ingest them.
# Works with any mounted path, including SMB/CIFS (via system mount), NFS, etc.
# Example: /watchfolders/scanner,/mnt/shared/inbox
watch_folders: Optional[str] = Field(
default=None,
description=(
"Comma-separated list of local filesystem paths (absolute) that DocuElevate will "
"poll for new files to ingest. Each file found is enqueued for document processing. "
"Works with any mounted path including SMB/CIFS (mounted via system) and NFS. "
"Example: /watchfolders/scanner,/mnt/shared/inbox"
),
)
watch_folder_poll_interval: int = Field(
default=1,
description=(
"Poll interval in minutes for local watch folder scanning. Default: 1 minute."
),
)
watch_folder_delete_after_process: bool = Field(
default=False,
description=(
"Delete files from local watch folders after they have been successfully enqueued "
"for processing. When False (default), files are left in place and tracked via a "
"cache file to avoid re-ingesting them."
),
)
# FTP Ingest / Watch Folder
# Uses the existing FTP credentials (ftp_host, ftp_username, ftp_password) to poll
# a source folder on the FTP server for new files to ingest.
ftp_ingest_folder: Optional[str] = Field(
default=None,
description=(
"FTP folder path to monitor for new files to ingest. "
"Uses the existing FTP connection settings (FTP_HOST, FTP_USERNAME, FTP_PASSWORD). "
"When set, DocuElevate will periodically poll this folder and download new files for processing."
),
)
ftp_ingest_enabled: bool = Field(
default=False,
description="Enable FTP watch folder ingestion. Requires FTP_INGEST_FOLDER and FTP connection settings.",
)
ftp_ingest_delete_after_process: bool = Field(
default=False,
description=(
"Delete files from the FTP ingest folder after they have been successfully downloaded "
"and enqueued for processing. Default: False (files are left in place)."
),
)
# SFTP Ingest / Watch Folder
# Uses the existing SFTP credentials (sftp_host, sftp_username, sftp_password/sftp_private_key)
# to poll a source folder on the SFTP server for new files to ingest.
sftp_ingest_folder: Optional[str] = Field(
default=None,
description=(
"SFTP folder path to monitor for new files to ingest. "
"Uses the existing SFTP connection settings (SFTP_HOST, SFTP_USERNAME, SFTP_PASSWORD/SFTP_PRIVATE_KEY). "
"When set, DocuElevate will periodically poll this folder and download new files for processing."
),
)
sftp_ingest_enabled: bool = Field(
default=False,
description="Enable SFTP watch folder ingestion. Requires SFTP_INGEST_FOLDER and SFTP connection settings.",
)
sftp_ingest_delete_after_process: bool = Field(
default=False,
description=(
"Delete files from the SFTP ingest folder after they have been successfully downloaded "
"and enqueued for processing. Default: False (files are left in place)."
),
)
# IMAP 1
imap1_host: Optional[str] = None
imap1_port: Optional[int] = 993