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 an optional scoped token. 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
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