From dd2bff79727d19943a3f4d3fd8ea4c55d0ecece5 Mon Sep 17 00:00:00 2001 From: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com> Date: Mon, 17 Aug 2026 16:26:51 -0500 Subject: [PATCH] add titles to more clearly separate model types --- docs/docs/configuration/genai/config.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/docs/docs/configuration/genai/config.md b/docs/docs/configuration/genai/config.md index d7634dd9b2..a3cabcbace 100644 --- a/docs/docs/configuration/genai/config.md +++ b/docs/docs/configuration/genai/config.md @@ -59,6 +59,8 @@ Running Generative AI models on CPU is not recommended, as high inference times ### Recommended Local Models +#### Vision models + You must use a vision-capable model with Frigate. The following models are recommended for local deployment of the `descriptions` and `chat` roles: | Model | Notes | @@ -67,6 +69,8 @@ You must use a vision-capable model with Frigate. The following models are recom | `qwen3.6`/`qwen3.8` | Strong situational understanding, but missing DeepStack from qwen3-vl leading to worse performance for identifying objects in people's hand and other small details. | | `gemma4` | Strong situational understanding, sometimes resorts to more vague terms like 'interacts' instead of assigning a specific action. | +#### Embedding models + The `embeddings` role needs a different kind of model. Text queries are matched against the stored image embeddings, so the model must be trained to place images and text into the same vector space. A chat or description model will still return vectors when asked, but those vectors are not trained for retrieval and text searches will return poor matches with no error to indicate why. | Model | Notes |