From f357094b5f85b3c66027b701a7393e035688388e Mon Sep 17 00:00:00 2001 From: Patrick Loeber Date: Tue, 25 Aug 2026 14:07:26 +0200 Subject: [PATCH 1/2] Add embedding models to gemini-api-dev and gemini-interactions-api skills --- skills/gemini-api-dev/SKILL.md | 2 ++ skills/gemini-interactions-api/SKILL.md | 3 +++ 2 files changed, 5 insertions(+) diff --git a/skills/gemini-api-dev/SKILL.md b/skills/gemini-api-dev/SKILL.md index 76fa0f5..20f5cac 100644 --- a/skills/gemini-api-dev/SKILL.md +++ b/skills/gemini-api-dev/SKILL.md @@ -22,6 +22,8 @@ description: Use this skill when building applications with Gemini API hosted mo - `gemini-2.5-flash`: 1M tokens, fast, balanced performance, multimodal - `gemma-4-31b-it`: Gemma 4 dense model, 31B parameters - `gemma-4-26b-a4b-it`: Gemma 4 MoE model, 26B total with 4B active parameters +- `gemini-embedding-2`: Multimodal embedding model (text, images, video, audio, documents) +- `gemini-embedding-001`: Text-only embedding model > [!WARNING] > Models like `gemini-2.0-*`, `gemini-1.5-*` are **legacy and deprecated**. Never use them. diff --git a/skills/gemini-interactions-api/SKILL.md b/skills/gemini-interactions-api/SKILL.md index fd6b2f5..da01788 100644 --- a/skills/gemini-interactions-api/SKILL.md +++ b/skills/gemini-interactions-api/SKILL.md @@ -23,6 +23,8 @@ description: Use this skill when writing code that calls the Gemini API for text - `gemini-omni-flash-preview`: video generation, image-referenced video generation, first-frame-to-video, and video editing - `gemma-4-31b-it`: Gemma 4 dense model, 31B parameters - `gemma-4-26b-a4b-it`: Gemma 4 MoE model, 26B total / 4B active parameters +- `gemini-embedding-2`: Multimodal embedding model (text, images, video, audio, documents) +- `gemini-embedding-001`: Text-only embedding model > [!WARNING] > Models like `gemini-2.5-*`, `gemini-2.0-*`, `gemini-1.5-*` are **legacy and deprecated**. Never use them. @@ -346,6 +348,7 @@ For streaming with tools, thinking, agents, and image generation see the full [S - [Image Understanding](https://ai.google.dev/gemini-api/docs/interactions/image-understanding.md.txt) - [Speech Generation](https://ai.google.dev/gemini-api/docs/interactions/speech-generation.md.txt) - [Music Generation](https://ai.google.dev/gemini-api/docs/interactions/music-generation.md.txt) +- [Embeddings](https://ai.google.dev/gemini-api/docs/embeddings.md.txt) **Multimodal Understanding:** - [Audio](https://ai.google.dev/gemini-api/docs/interactions/audio.md.txt) From bcbfc24831a3766caae6977da06bb399920c9d80 Mon Sep 17 00:00:00 2001 From: Patrick Loeber Date: Tue, 25 Aug 2026 14:25:37 +0200 Subject: [PATCH 2/2] Note client.models.embed_content usage for embedding models --- skills/gemini-api-dev/SKILL.md | 4 ++-- skills/gemini-interactions-api/SKILL.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/skills/gemini-api-dev/SKILL.md b/skills/gemini-api-dev/SKILL.md index 20f5cac..8be8333 100644 --- a/skills/gemini-api-dev/SKILL.md +++ b/skills/gemini-api-dev/SKILL.md @@ -22,8 +22,8 @@ description: Use this skill when building applications with Gemini API hosted mo - `gemini-2.5-flash`: 1M tokens, fast, balanced performance, multimodal - `gemma-4-31b-it`: Gemma 4 dense model, 31B parameters - `gemma-4-26b-a4b-it`: Gemma 4 MoE model, 26B total with 4B active parameters -- `gemini-embedding-2`: Multimodal embedding model (text, images, video, audio, documents) -- `gemini-embedding-001`: Text-only embedding model +- `gemini-embedding-2`: Multimodal embedding model (text, images, video, audio, documents), uses `client.models.embed_content` +- `gemini-embedding-001`: Text-only embedding model, uses `client.models.embed_content` > [!WARNING] > Models like `gemini-2.0-*`, `gemini-1.5-*` are **legacy and deprecated**. Never use them. diff --git a/skills/gemini-interactions-api/SKILL.md b/skills/gemini-interactions-api/SKILL.md index da01788..10ca760 100644 --- a/skills/gemini-interactions-api/SKILL.md +++ b/skills/gemini-interactions-api/SKILL.md @@ -23,8 +23,8 @@ description: Use this skill when writing code that calls the Gemini API for text - `gemini-omni-flash-preview`: video generation, image-referenced video generation, first-frame-to-video, and video editing - `gemma-4-31b-it`: Gemma 4 dense model, 31B parameters - `gemma-4-26b-a4b-it`: Gemma 4 MoE model, 26B total / 4B active parameters -- `gemini-embedding-2`: Multimodal embedding model (text, images, video, audio, documents) -- `gemini-embedding-001`: Text-only embedding model +- `gemini-embedding-2`: Multimodal embedding model (text, images, video, audio, documents), uses `client.models.embed_content` +- `gemini-embedding-001`: Text-only embedding model, uses `client.models.embed_content` > [!WARNING] > Models like `gemini-2.5-*`, `gemini-2.0-*`, `gemini-1.5-*` are **legacy and deprecated**. Never use them.