{% extends "base.html" %} {% block title %}Embedding Settings{% endblock %} {% block content %}

Default Embedding Settings

Configure default embedding models for new collections and semantic search

Important: Existing Collections

Changing these settings will only affect NEW collections. Existing collections keep their original embedding settings to ensure data integrity and search consistency.

Once a collection is indexed, its embedding settings are locked. To change settings for an existing collection, you must re-index the entire collection, which will delete the current index.

Configuration

Saved Default Settings

Loading...

These are your saved defaults for new collections. Change them using the form below.

Default Embedding Configuration

Characters per chunk
Overlap between chunks
How documents are split into chunks. Semantic uses AI to find natural breakpoints (slower but smarter)
Cosine similarity recommended for text embeddings
HNSW recommended for >10K documents (50-60× faster)
Recommended: Ensures fair comparison regardless of document length
JSON array of separators. Default works for 80% of use cases. For code: add language-specific separators like "\nclass", "\ndef"
These settings will be used as defaults for new collections. Existing collections will continue using their current settings unless re-indexed with new defaults.

Provider Information

Loading provider information...

Test Configuration

Test the currently selected embedding model to ensure it's working correctly.

{% endblock %}