file

Test JPEG for KG Full

01KJTMMS7QC2C1KGV9KZSZXDDE

Content

test.jpeg

key
test.jpeg
cid
bafkreifhjw43apnzrccsyufncn7pph5vpgzlyahg2owhncuiiem7kota5u
content_type
image/jpeg
size
1.4 MB (1,452,844 bytes)
uploaded_at
2026-03-03T20:01:18.788Z

Properties

ocr_images_extracted
1
ocr_model
mistral-ocr-latest
ocr_source_file_key
test.jpeg
text
# Meet Emma Emma runs a small regional archive. She has thousands of digitized documents—letters, diaries, local government records—but they sit in folders with minimal metadata. No descriptions. No transcriptions. Her three-person team doesn't have the capacity to catalog them properly, let alone make them searchable. The materials technically exist digitally, but they're practically invisible. Researchers can't find them. Search engines can't index them. AI systems don't know they exist. And if her institution's server fails, decades of local history could disappear. ![img-0.jpeg](arke:01KJTMN3DGN807CT8DZXVPCQCX)
text_extracted_at
2026-03-03T20:01:29.416Z
text_source
ocr

Relationships

  • has_extracted01KJTMN3DGN807CT8DZXVPCQCXfile
  • extracted_entityemma
    entity_type
    person
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitydigitized documents
    entity_type
    document_collection
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitysearch engines
    entity_type
    software_system
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entityai systems
    entity_type
    software_system
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitylocal history
    entity_type
    concept
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitycataloging
    entity_type
    process
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitytranscriptions
    entity_type
    data_attribute
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitydescriptions
    entity_type
    data_attribute
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entityregional archive
    entity_type
    archive_institution
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitymetadata
    entity_type
    data_attribute
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entityinstitutions server
    entity_type
    hardware_system
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entityemmas team
    entity_type
    team
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entitydocument searchability
    entity_type
    quality
    extracted_at
    2026-03-03T20:02:14.508Z
  • extracted_entityresearchers
    entity_type
    user_group
    extracted_at
    2026-03-03T20:02:14.508Z