docs(platform): Add support for Google vertex AI

- Adds documentation for vertex ai

Author: junaidbinfarooq

README.md

@@ -13,7 +13,7 @@ Symfony AI is a set of components that integrate AI capabilities into PHP applic
 Symfony AI consists of several lower and higher level **components** and the respective integration **bundles**:
 
 * **Components**
-  * **[Platform](src/platform/README.md)**: A unified interface to various AI platforms like OpenAI, Anthropic, Azure, Gemini, and more.
+  * **[Platform](src/platform/README.md)**: A unified interface to various AI platforms like OpenAI, Anthropic, Azure, Gemini, VertexAI, and more.
   * **[Agent](src/agent/README.md)**: Framework for building AI agents that can interact with users and perform tasks.
   * **[Store](src/store/README.md)**: Data storage abstraction with indexing and retrieval for AI applications.
   * **[MCP SDK](src/mcp-sdk/README.md)**: SDK for [Model Context Protocol](https://modelcontextprotocol.io) enabling communication between AI agents and tools.

examples/.env

@@ -73,8 +73,8 @@ RUN_EXPENSIVE_EXAMPLES=false
 GEMINI_API_KEY=
 
 # Vertex AI
-GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
 GOOGLE_CLOUD_LOCATION=global
+GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
 
 # For using Albert API (French Sovereign AI)
 ALBERT_API_KEY=

src/ai-bundle/doc/index.rst

@@ -34,7 +34,7 @@ Configuration
                     class: 'Symfony\AI\Platform\Bridge\OpenAi\Gpt'
                     name: !php/const Symfony\AI\Platform\Bridge\OpenAi\Gpt::GPT_4O_MINI
 
-**Advanced Example with Anthropic, Azure, Gemini and multiple agents**
+**Advanced Example with Anthropic, Azure, Gemini, VertexAi and multiple agents**
 
 .. code-block:: yaml
 
@@ -52,6 +52,9 @@ Configuration
                     api_version: '%env(AZURE_GPT_VERSION)%'
             gemini:
                 api_key: '%env(GEMINI_API_KEY)%'
+            vertexAi:
+                location: '%env(GOOGLE_CLOUD_LOCATION)%'
+                project_id: '%env(GOOGLE_CLOUD_PROJECT)%'
             ollama:
                 host_url: '%env(OLLAMA_HOST_URL)%'
         agent:

src/platform/CHANGELOG.md

@@ -9,7 +9,7 @@ CHANGELOG
  * Add support for 13+ AI providers:
    - OpenAI (GPT-4, GPT-3.5, DALL·E, Whisper)
    - Anthropic (Claude models via native API and AWS Bedrock)
-   - Google (Gemini models with server-side tools support)
+   - Google (VertexAi and Gemini models with server-side tools support)
    - Azure (OpenAI and Meta Llama models)
    - AWS Bedrock (Anthropic Claude, Meta Llama, Amazon Nova)
    - Mistral AI (language models and embeddings)

src/platform/doc/index.rst

@@ -73,13 +73,15 @@ usually defined by the specific models and their documentation.
     * `OpenAI's GPT`_ with `OpenAI`_ and `Azure`_ as Platform
     * `Anthropic's Claude`_ with `Anthropic`_ and `AWS Bedrock`_ as Platform
     * `Meta's Llama`_ with `Azure`_, `Ollama`_, `Replicate`_ and `AWS Bedrock`_ as Platform
-    * `Gemini`_ with `Google`_ and `OpenRouter`_ as Platform
+    * `Gemini`_ with `Google`_, `VertexAi`_ and `OpenRouter`_ as Platform
+    * `VertexAi Gen AI`_ with `VertexAi`_ as Platform
     * `DeepSeek's R1`_ with `OpenRouter`_ as Platform
     * `Amazon's Nova`_ with `AWS Bedrock`_ as Platform
     * `Mistral's Mistral`_ with `Mistral`_ as Platform
     * `Albert API`_ models with `Albert`_ as Platform (French government's sovereign AI gateway)
 * **Embeddings Models**
     * `Gemini Text Embeddings`_ with `Google`_
+    * `VertexAi Text Embeddings`_ with `VertexAi`_
     * `OpenAI's Text Embeddings`_ with `OpenAI`_ and `Azure`_ as Platform
     * `Voyage's Embeddings`_ with `Voyage`_ as Platform
     * `Mistral Embed`_ with `Mistral`_ as Platform
@@ -263,7 +265,8 @@ Server Tools
 
 Some platforms provide built-in server-side tools for enhanced capabilities without custom implementations:
 
-1. **[Gemini](gemini-server-tools.md)** - URL Context, Google Search, Code Execution
+1. **[Gemini](gemini-server-tools.rst)** - URL Context, Google Search, Code Execution
+2. **[VertexAi](vertexai-server-tools.rst)** - URL Context, Google Search, Code Execution
 
 Parallel Platform Calls
 -----------------------
@@ -363,6 +366,7 @@ This allows fast and isolated testing of AI-powered features without relying on
 .. _`Ollama`: https://ollama.com/
 .. _`Replicate`: https://replicate.com/
 .. _`Gemini`: https://gemini.google.com/
+.. _`VertexAi`: https://cloud.google.com/vertex-ai/generative-ai/docs
 .. _`Google`: https://ai.google.dev/
 .. _`OpenRouter`: https://www.openrouter.ai/
 .. _`DeepSeek's R1`: https://www.deepseek.com/
@@ -372,6 +376,8 @@ This allows fast and isolated testing of AI-powered features without relying on
 .. _`Albert`: https://alliance.numerique.gouv.fr/produit/albert/
 .. _`Mistral`: https://www.mistral.ai/
 .. _`Gemini Text Embeddings`: https://ai.google.dev/gemini-api/docs/embeddings
+.. _`VertexAi Gen AI`: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference
+.. _`VertexAi Text Embeddings`: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api
 .. _`OpenAI's Text Embeddings`: https://platform.openai.com/docs/guides/embeddings/embedding-models
 .. _`Voyage's Embeddings`: https://docs.voyageai.com/docs/embeddings
 .. _`Voyage`: https://www.voyageai.com/

src/platform/doc/vertexai-server-tools.rst

@@ -0,0 +1,111 @@
+Vertex AI Server Tools
+======================
+
+Server tools in Vertex AI are built-in capabilities provided by Google's Gemini models that allow the model to perform
+specific actions without requiring custom tool implementations.
+These tools run on Google's infrastructure and provide access to external data sources and execution environments.
+
+Overview
+--------
+
+Vertex AI provides several server-side tools that can be enabled when calling the model:
+
+- **URL Context** - Fetches and analyzes content from URLs
+- **Grounding** - Lets a model output connect to verifiable sources of information.
+- **Code Execution** - Executes code in a sandboxed environment.
+
+Available Server Tools
+----------------------
+
+**URL Context**
+
+The URL Context tool allows the model to fetch and analyze content from specified web pages. This is useful for:
+
+- Analyzing current web content
+- Extracting structured information from pages
+- Providing context from external documents
+- https://cloud.google.com/vertex-ai/generative-ai/docs/url-context
+
+::
+
+    $model = new VertexAi\Gemini\Model('gemini-2.5-pro');
+
+    $content = file_get_contents('https://www.euribor-rates.eu/en/current-euribor-rates/4/euribor-rate-12-months/');
+    $messages = new MessageBag(
+        Message::ofUser("Based on the following page content, what was the 12-month Euribor rate a week ago?\n\n".$content)
+    );
+
+    $result = $platform->invoke($model, $messages);
+
+
+**Grounding with Google Search**
+The Grounding tool allows the model to connect its responses to verifiable sources of information, enhancing the reliability
+of its outputs. More at https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/overview
+Below is an example of grounding a model's responses using Google Search, which uses publicly-available web data.
+
+* Grounding with Google Search *
+
+Ground a model's responses using Google Search, which uses publicly-available web data.
+More info can be found at https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/overview
+
+::
+
+    $model = new VertexAi\Gemini\Model('gemini-2.5-pro', [
+        'tools' => [[
+            'googleSearch' => new \stdClass()
+        ]]
+    ]);
+
+    $messages = new MessageBag(
+        Message::ofUser('What are the top breakthroughs in AI in 2025 so far?')
+    );
+
+    $result = $platform->invoke($model, $messages);
+
+**Code Execution**
+
+Executes code in a Google-managed sandbox environment and returns both the code and its output.
+More info can be found at https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/code-execution
+
+::
+
+    $model = new Gemini('gemini-2.5-pro-preview-03-25', [
+        'tools' => [[
+            'codeExecution' => new \stdClass()
+        ]]
+    ]);
+
+    $messages = new MessageBag(
+        Message::ofUser('Write Python code to calculate the 50th Fibonacci number and run it')
+    );
+
+    $result = $platform->invoke($model, $messages);
+
+
+Using Multiple Server Tools
+---------------------------
+
+You can enable multiple tools in a single request::
+
+    $model = new Gemini('gemini-2.5-pro-preview-03-25', [
+        'tools' => [[
+            'googleSearch' => new \stdClass(),
+            'codeExecution' => new \stdClass()
+        ]]
+    ]);
+
+Example
+-------
+
+See `examples/vertexai/server-tools.php`_ for a complete working example.
+
+Limitations
+-----------
+
+- **Model support:** Not all Vertex AI Gemini model versions support all server tools — check the Vertex AI documentation for the chosen model ID.
+- **Permissions:** The Vertex AI service account and the models must have the required permissions or scopes to use server tools.
+- **Quotas:** Server tools are subject to usage limits and quotas configured in your Google Cloud project.
+- **Latency:** Using multiple tools or fetching from slow external sources can increase response time.
+- **Regional availability:** Ensure you are using a location that supports the selected model and tools.
+
+.. _`examples/vertexai/server-tools.php`: https://github.com/symfony/ai/blob/main/examples/vertexai/server-tools.php