Skip to content

feat: Add remote Tika parsing support - #875

Open
arsaboo wants to merge 1 commit into
HKUDS:devfrom
arsaboo:tika
Open

feat: Add remote Tika parsing support#875
arsaboo wants to merge 1 commit into
HKUDS:devfrom
arsaboo:tika

Conversation

@arsaboo

@arsaboo arsaboo commented Aug 16, 2026

Copy link
Copy Markdown
Contributor

Description

This is a follow-up to #845.

This PR adds Apache Tika as a new document parsing engine. Tika is remote-only: it sends files to a configured tika-server via PUT /tika and writes the extracted text as Markdown, so no local install or model downloads are needed.

What's included:

  • New deeptutor/services/parsing/engines/tika/ engine (config, remote client, adapter)
  • Registered tika in the parser factory and runtime settings
  • TIKA_SERVER_URL env override with default http://localhost:9998
  • POST /api/v1/settings/document-parsing/tika/test endpoint for live connectivity checks
  • Tika settings UI (server URL, test connection, save) in the document-parsing settings page
  • Tests and README updates

Tested against a live Apache Tika 3.3.1 server (including Unicode filenames).

Related Issues

Module(s) Affected

  • agents
  • api
  • config
  • core
  • knowledge
  • logging
  • services
  • tools
  • utils
  • web (Frontend)
  • docs (Documentation)
  • scripts
  • tests
  • Other: ...

Checklist

  • I have read and followed the contribution guidelines.
  • My code follows the project's coding standards.
  • I have run pre-commit run --all-files and fixed any issues.
  • I have added relevant tests for my changes.
  • I have updated the documentation (if necessary).
  • My changes do not introduce any new security vulnerabilities.

Additional Notes

Add any other context or screenshots about the pull request here.

@arsaboo

This comment was marked as outdated.

@arsaboo

arsaboo commented Aug 16, 2026

Copy link
Copy Markdown
Contributor Author

@pancacake thanks for those upstream fixes...all green now :)

@arsaboo
arsaboo force-pushed the tika branch 2 times, most recently from 0c9938f to 5ff5677 Compare August 16, 2026 20:30
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant