[Feature] Support importing existing PageIndex Cloud indices #88

Feature Request

As a user who already has documents indexed in PageIndex Developer Cloud,
I would like OpenKB to be able to leverage my existing corpus without
requiring full reprocessing through the local pipeline.

Motivation

Currently, OpenKB creates its own local PageIndex database
(.openkb/pageindex.db) and requires all documents to be reprocessed
via col.add() even when they are already indexed in PageIndex Cloud.

For users already invested in the PageIndex ecosystem with large document
collections, this means:

• Redundant processing time and costs
• Duplicate storage of the same document indices
• Slower onboarding to OpenKB's wiki capabilities

Proposed Solution

Add a new command or flag to import existing PageIndex Cloud documents
into an OpenKB knowledge base, for example:

openkb import-from-pageindex --doc-id <existing_cloud_doc_id>  
# or  [header-1](#header-1)
openkb add --from-pageindex-cloud <document_identifier>