tool

Apache Tika

Extracts text and metadata from more than a thousand file types, including Office documents, PDFs, archives, and email formats.

What it provides

Text extraction1000+ formatsMetadata

Connect an existing HTTPS deployment, with a scoped token where the service requires one. Heavy jobs stay on that service instead of using bot memory.

Connection requirements

Run Apache Tika Server outside the bot (`docker run -p 9998:9998 apache/tika`) and publish it over HTTPS. Tika ships no authentication, so keep it behind a reverse proxy; if that proxy uses HTTP Basic, choose Basic and paste the base64 of `username:password`. Send documents with post-file — parsing and the Java runtime stay on the Tika host.

Protocol
REST / OpenAPI
Endpoint
https://tika.example.com
Authentication
Choose the mode required by your service
Example callsget /versionpost-file /rmeta/form /path/to/document.pdf
Open official setup guide ↗

Where to add it

Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.

Related Documents & OCR