mirror of
https://github.com/perstarkse/minne.git
synced 2026-06-12 17:24:26 +02:00
Per Stark
4e20da538d
Expose fastembed_model in config and a model dropdown on Admin → Models. Persist dimension from the chosen model, require restart to load it, and align legacy OpenAI default settings so fresh local-embedding installs start cleanly.
9 lines
380 B
Plaintext
9 lines
380 B
Plaintext
-- Align persisted embedding settings when FastEmbed is the recorded backend but the model
|
|
-- name is still the OpenAI migration default (invalid for FastEmbed `from_str`).
|
|
|
|
UPDATE system_settings:current SET
|
|
embedding_model = 'Xenova/bge-small-en-v1.5',
|
|
embedding_dimensions = 384
|
|
WHERE embedding_backend = 'fastembed'
|
|
AND embedding_model = 'text-embedding-3-small';
|