administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-07 11:45:24 +03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

add tip about .reindex_events to docs

Browse Source
This commit is contained in:
Jason Hunter 2023-12-20 00:40:25 -05:00
parent 1d3dd5ba37
commit 2e3cc127ef
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/docs/configuration/semantic_search.md
View File

@ -14,6 +14,12 @@ semantic_search:
enabled: True enabled: True
``` ```
:::tip
The embeddings database can be re-indexed from the existing events in your database by adding an empty file named `.reindex_events` to the root of your configuration directory. This will delay the startup of Frigate on the next boot while events are being indexed. Depending on the number of events you have, it can take up to 30 minutes to complete and will max out your CPU while indexing.
:::
### OpenAI CLIP ### OpenAI CLIP
This model is able to embed both images and text into the same vector space, which allows `image -> image` and `text -> image` similarity searches. Frigate uses this model on completed events to encode the thumbnail image and store it in Chroma. When searching events via text in the search box, frigate will perform a `text -> image` similarity search against this embedding. When clicking "FIND SIMILAR" next to an event, Frigate will perform an `image -> image` similarity search to retrieve the closest matching thumbnails. This model is able to embed both images and text into the same vector space, which allows `image -> image` and `text -> image` similarity searches. Frigate uses this model on completed events to encode the thumbnail image and store it in Chroma. When searching events via text in the search box, frigate will perform a `text -> image` similarity search against this embedding. When clicking "FIND SIMILAR" next to an event, Frigate will perform an `image -> image` similarity search to retrieve the closest matching thumbnails.