Bulk import in Rabbithole

[spark shoal]

What is this?
This is a plugin (tool) for the Cheshire Cat Project, which allows you to bulk import URLS and Documents into the Rabbit Hole.

Install
Download the cc_bulk_import folder into the cheshire-cat/core/cat/plugins one. Create a folder "bulkimport" into the /core/cat/static one.

Usage
IMPORT URLS
Ask the cat "bulkimport url LIST OF URLS COMMA SEPARATED" Example: bulkimport url https://cheshirecat.ai/code-of-ethics/,https://cheshirecat.ai/

IMPORT DOCUMENTS
Put a COPY (after import files wil be deleted, so put a copy not the original one) of files you want to import into /core/cat/static/bulkimport folder and then ask the cat "bulkimport docs"

Output
The cat will give a feedback after the import process is completed, so if you have multiple urls on multiple document you need to wait for having a response from the cat.

The cat responde with a table containing the status (OK or KO) for any single url/document setn to the rabbit hole.

Repo URL: https://github.com/team-sviluppo/cc_bulk_import

[tiny nacelle]

Cool!

[rigid coral]

it's an amazing idea,congrats, so let's imagine i'm preparing an univerity exam and i upload inside my notes, it can ask me question based on my notes? and there is a limit to the storage?

[spark shoal]

Yes you can ask about content in your notes. The limit of storage is the disk size of machine where the cat is running

[radiant mica]

Brother the plugin isnt working

I tried since yesterday I want to bulk import my books

[tiny nacelle]

Going strong!

P.s. if you run this regularly on the same docs/urls, remember to call DELETE endpoint on declarative collection

[shut cliff]

I think you can avoid deleting the declarative memory if ccat-dietician plugin is activated. Dietician will automatically avoid multiple ingestions

[jagged silo]

https://github.com/AlessandroSpallina/ccat-dietician

[tiny nacelle]

Lovely