Pairs of documents with high semantic similarity, ranked by score.
Embeddings are computed during document ingestion; a background task
also backfills any files that were processed before this feature was enabled.
{{ total_files }}
Total Files
{{ files_with_embedding }}
With Embedding
{{ files_missing_embedding }}
Missing Embedding
{{ embedding_model }}
Embedding Model
{% if files_missing_embedding > 0 %}
{{ files_missing_embedding }} file(s) have OCR text but no embedding yet.
The background task will compute them automatically every 5 minutes, or you can
.
{% endif %}
Scanning for similar document pairs…
No similar pairs found
No document pairs exceed the similarity threshold.