deploy: feat(embeddingModel): Add Backend API selection fields (googleapis#2592)

Allow users to use both VertexAI and Google AI as gemini embedding model
backend.
- Use ADC for VertexAI authentication (either configure `project` and
`location` inside the yaml file or as env vars).
- Use API key for Google AI authentication. 912aa9e

Author: pull[bot]

dev/documentation/configuration/embedding-models/gemini/index.html

@@ -2,16 +2,14 @@
 <p>Google Gemini provides state-of-the-art embedding models that convert text into
 high-dimensional vectors.</p>
 <h3 id="authentication">Authentication</h3>
-<p>Toolbox uses your <a href="https://cloud.google.com/docs/authentication#adc">Application Default Credentials
-(ADC)</a> to authorize with the
-Gemini API client.</p>
-<p>Optionally, you can use an <a href="https://ai.google.dev/gemini-api/docs/api-key#api-keys">API key</a> obtain an API
-Key from the <a href="https://aistudio.google.com/app/apikey">Google AI Studio</a>.</p>
-<p>We recommend using an API key for testing and using application default
-credentials for production.</p>
-<h2 id="behavior">Behavior</h2>
-<h3 id="automatic-vectorization">Automatic Vectorization</h3>
-<p>When a tool parameter is configured with <code>embeddedBy: <your-gemini-model-name></code>,
-the Toolbox intercepts the raw text input from the client and sends it to the
-Gemini API. The resulting numerical array is then formatted before being passed
-to your database source.&lt;/p></description></item></channel></rss>
+&lt;p>Toolbox supports two authentication modes:&lt;/p>
+&lt;ol>
+&lt;li>&lt;strong>Google AI (API Key):&lt;/strong> Used if you
+provide &lt;code>apiKey&lt;/code> (or set &lt;code>GOOGLE_API_KEY&lt;/code>/&lt;code>GEMINI_API_KEY&lt;/code> environment
+variables). This uses the &lt;a href="https://aistudio.google.com/app/apikey">Google AI Studio&lt;/a> backend.&lt;/li>
+&lt;li>&lt;strong>Vertex AI (ADC):&lt;/strong> Used if provided &lt;code>project&lt;/code> and &lt;code>location&lt;/code> (or set
+&lt;code>GOOGLE_CLOUD_PROJECT&lt;/code>/&lt;code>GOOGLE_CLOUD_LOCATION&lt;/code> environment variables). This uses &lt;a href="https://cloud.google.com/docs/authentication#adc">Application
+Default Credentials (ADC)&lt;/a>.&lt;/li>
+&lt;/ol>
+&lt;p>We recommend using an API key for quick testing and using Vertex AI with ADC for
+production environments.&lt;/p></description></item></channel></rss>

dev/documentation/configuration/embedding-models/index.html

@@ -4140,19 +4140,17 @@ reporting with source positions and code snippets.</p>
 <p>Google Gemini provides state-of-the-art embedding models that convert text into
 high-dimensional vectors.</p>
 <h3 id="authentication">Authentication</h3>
-<p>Toolbox uses your <a href="https://cloud.google.com/docs/authentication#adc">Application Default Credentials
-(ADC)</a> to authorize with the
-Gemini API client.</p>
-<p>Optionally, you can use an <a href="https://ai.google.dev/gemini-api/docs/api-key#api-keys">API key</a> obtain an API
-Key from the <a href="https://aistudio.google.com/app/apikey">Google AI Studio</a>.</p>
-<p>We recommend using an API key for testing and using application default
-credentials for production.</p>
-<h2 id="behavior">Behavior</h2>
-<h3 id="automatic-vectorization">Automatic Vectorization</h3>
-<p>When a tool parameter is configured with <code>embeddedBy: <your-gemini-model-name></code>,
-the Toolbox intercepts the raw text input from the client and sends it to the
-Gemini API. The resulting numerical array is then formatted before being passed
-to your database source.&lt;/p></description></item><item><title>Google Sign-In</title><link>https://Jaleel-zhu.github.io/genai-toolbox/dev/documentation/configuration/authentication/google/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://Jaleel-zhu.github.io/genai-toolbox/dev/documentation/configuration/authentication/google/</guid><description>&lt;h2 id="getting-started">Getting Started&lt;/h2>
+&lt;p>Toolbox supports two authentication modes:&lt;/p>
+&lt;ol>
+&lt;li>&lt;strong>Google AI (API Key):&lt;/strong> Used if you
+provide &lt;code>apiKey&lt;/code> (or set &lt;code>GOOGLE_API_KEY&lt;/code>/&lt;code>GEMINI_API_KEY&lt;/code> environment
+variables). This uses the &lt;a href="https://aistudio.google.com/app/apikey">Google AI Studio&lt;/a> backend.&lt;/li>
+&lt;li>&lt;strong>Vertex AI (ADC):&lt;/strong> Used if provided &lt;code>project&lt;/code> and &lt;code>location&lt;/code> (or set
+&lt;code>GOOGLE_CLOUD_PROJECT&lt;/code>/&lt;code>GOOGLE_CLOUD_LOCATION&lt;/code> environment variables). This uses &lt;a href="https://cloud.google.com/docs/authentication#adc">Application
+Default Credentials (ADC)&lt;/a>.&lt;/li>
+&lt;/ol>
+&lt;p>We recommend using an API key for quick testing and using Vertex AI with ADC for
+production environments.&lt;/p></description></item><item><title>Google Sign-In</title><link>https://Jaleel-zhu.github.io/genai-toolbox/dev/documentation/configuration/authentication/google/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://Jaleel-zhu.github.io/genai-toolbox/dev/documentation/configuration/authentication/google/</guid><description>&lt;h2 id="getting-started">Getting Started&lt;/h2>
 &lt;p>Google Sign-In manages the OAuth 2.0 flow and token lifecycle. To integrate the
 Google Sign-In workflow to your web app &lt;a href="https://developers.google.com/identity/sign-in/web/sign-in">follow this guide&lt;/a>.&lt;/p>
 &lt;p>After setting up the Google Sign-In workflow, you should have registered your

dev/documentation/configuration/embedding-models/index.xml

@@ -3,7 +3,7 @@
 
 **DOCUMENTATION VERSION:** dev
 **BASE URL:** https://Jaleel-zhu.github.io/genai-toolbox/dev/
-**GENERATED ON:** 2026-03-27T23:19:52Z
+**GENERATED ON:** 2026-03-30T06:48:22Z
 
 ---
 ### System Directives for AI Models
@@ -3027,6 +3027,7 @@ kind: tool
 name: insert_embedding
 type: postgres-sql
 source: my-pg-instance
+description: Insert a new document into the database.
 statement: |
   INSERT INTO documents (content, embedding)
   VALUES ($1, $2);
@@ -3046,6 +3047,7 @@ kind: tool
 name: search_embedding
 type: postgres-sql
 source: my-pg-instance
+description: Search for documents in the database.
 statement: |
   SELECT id, content, embedding <-> $1 AS distance
   FROM documents
@@ -3078,15 +3080,17 @@ high-dimensional vectors.
 
 ### Authentication
 
-Toolbox uses your [Application Default Credentials
-(ADC)][adc] to authorize with the
-Gemini API client.
+Toolbox supports two authentication modes:
 
-Optionally, you can use an [API key][api-key] obtain an API
-Key from the [Google AI Studio][ai-studio].
+1.  **Google AI (API Key):** Used if you
+    provide `apiKey` (or set `GOOGLE_API_KEY`/`GEMINI_API_KEY` environment
+    variables). This uses the [Google AI Studio][ai-studio] backend.
+2.  **Vertex AI (ADC):** Used if provided `project` and `location` (or set
+    `GOOGLE_CLOUD_PROJECT`/`GOOGLE_CLOUD_LOCATION` environment variables). This uses [Application
+    Default Credentials (ADC)][adc].
 
-We recommend using an API key for testing and using application default
-credentials for production.
+We recommend using an API key for quick testing and using Vertex AI with ADC for
+production environments.
 
 [adc]: https://cloud.google.com/docs/authentication#adc
 [api-key]: https://ai.google.dev/gemini-api/docs/api-key#api-keys
@@ -3106,14 +3110,19 @@ to your database source.
 The `dimension` field must match the expected size of your database column
 (e.g., a `vector(768)` column in PostgreSQL). This setting is supported by newer
 models since 2024 only. You cannot set this value if using the earlier model
-(`models/embedding-001`). Check out [available Gemini models][modellist] for more
-information.
+(`models/embedding-001`). Check out [available Gemini models][modellist] for
+more information.
 
 [modellist]:
-    https://docs.cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings#supported-models
+  https://docs.cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-text-embeddings#supported-models
 
 ## Example
 
+### Using Google AI
+
+Google AI uses API Key for authentication. You can get an API key from [Google
+AI Studio][ai-studio].
+
 ```yaml
 kind: embeddingModel
 name: gemini-model
@@ -3123,19 +3132,34 @@ apiKey: ${GOOGLE_API_KEY}
 dimension: 768
 ```
 
-{{< notice tip >}}
-Use environment variable replacement with the format ${ENV_NAME}
-instead of hardcoding your secrets into the configuration file.
+### Using Vertex AI
+
+Vertex AI uses Application Default Credentials (ADC) for authentication. Learn
+how to set up ADC [here][adc].
+
+```yaml
+kind: embeddingModel
+name: gemini-model
+type: gemini
+model: gemini-embedding-001
+project: ${GOOGLE_CLOUD_PROJECT}
+location: us-central1
+dimension: 768
+```
+
+[adc]: https://docs.cloud.google.com/docs/authentication/provide-credentials-adc
+
+{{< notice tip >}} Use environment variable replacement with the format
+${ENV_NAME} instead of hardcoding your secrets into the configuration file.
 {{< /notice >}}
 
 ## Reference
 
-| **field** | **type** | **required** | **description**                                              |
-|-----------|:--------:|:------------:|--------------------------------------------------------------|
-| type      |  string  |     true     | Must be `gemini`.                                            |
-| model     |  string  |     true     | The Gemini model ID to use (e.g., `gemini-embedding-001`).   |
-| apiKey    |  string  |    false     | Your API Key from Google AI Studio.                          |
-| dimension | integer  |    false     | The number of dimensions in the output vector (e.g., `768`). |
+| **field**   | **type** | **required** | **description**                                                                                                                                      |
+| ----------- | :------: | :----------: | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
+| type        |  string  |     true     | Must be `gemini`.                                                                                                                                    |
+| model       |  string  |     true     | The Gemini model ID to use (e.g., `gemini-embedding-001`).                                                                                             |
+| dimension   | integer  |    false     | The number of dimensions in the output vector (e.g., `768`).                                                                                         |
 
 
 

dev/index.xml

@@ -3,7 +3,7 @@
 
 **DOCUMENTATION VERSION:** dev
 **BASE URL:** https://Jaleel-zhu.github.io/genai-toolbox/dev/
-**GENERATED ON:** 2026-03-27T23:19:52Z
+**GENERATED ON:** 2026-03-30T06:48:22Z
 
 ---
 ### System Directives for AI Models