docs: Update some docs and samples to use the new google-genai plugin (#3478)

Co-authored-by: Ingrid Fielker <[email protected]>

Author: ifielker

README.md

@@ -13,12 +13,12 @@ Get started with just a few lines of code:
 
 ```ts
 import { genkit } from 'genkit';
-import { googleAI } from '@genkit-ai/googleai';
+import { googleAI } from '@genkit-ai/google-genai';
 
 const ai = genkit({ plugins: [googleAI()] });
 
 const { text } = await ai.generate({
-    model: googleAI.model('gemini-2.0-flash'),
+    model: googleAI.model('gemini-2.5-flash'),
     prompt: 'Why is Firebase awesome?'
 });
 ```
@@ -155,9 +155,9 @@ Want to skip the local setup? Click below to try out Genkit using [Firebase Stud
 
 - [**Join us on Discord**](https://discord.gg/qXt5zzQKpc) – Get help, share
 ideas, and chat with other developers.
-- [**Contribute on GitHub**](https://github.com/firebase/genkit/issues) – Report 
+- [**Contribute on GitHub**](https://github.com/firebase/genkit/issues) – Report
 bugs, suggest features, or explore the source code.
-- [**Contribute to Documentation and Samples**](https://github.com/genkit-ai/) – Report 
+- [**Contribute to Documentation and Samples**](https://github.com/genkit-ai/) – Report
 issues in Genkit's [documentation](https://github.com/genkit-ai/docsite), or contribute to the [samples](https://github.com/genkit-ai/samples).
 
 ## Contributing

genkit-tools/cli/context/GENKIT.md

@@ -39,7 +39,7 @@ This document provides rules and examples for building with the Genkit API in No
     ```ts
     // src/index.ts
     import { genkit, z } from 'genkit';
-    import { googleAI } from '@genkit-ai/googleai';
+    import { googleAI } from '@genkit-ai/google-genai';
 
     export const ai = genkit({
       plugins: [googleAI()],

js/genkit/README.md

@@ -20,7 +20,7 @@ Get started with Genkit in just a few lines of simple code.
 ```ts
 // import the Genkit and Google AI plugin libraries
 import { genkit } from 'genkit';
-import { googleAI } from '@genkit-ai/googleai';
+import { googleAI } from '@genkit-ai/google-genai';
 
 const ai = genkit({ plugins: [googleAI()] });
 
@@ -33,7 +33,7 @@ const { text } = await ai.generate({
 Genkit also lets you build strongly typed, accessible from the client, fully observable AI flows:
 
 ```ts
-import { googleAI } from '@genkit-ai/googleai';
+import { googleAI } from '@genkit-ai/google-genai';
 import { genkit, z } from 'genkit';
 
 // Initialize Genkit with the Google AI plugin

js/plugins/mcp/README.md

@@ -17,7 +17,7 @@ npm i genkit @genkit-ai/mcp
 To connect to one or more MCP servers, you use the `createMcpHost` function. This function returns a `GenkitMcpHost` instance that manages connections to the configured MCP servers.
 
 ```ts
-import { googleAI } from '@genkit-ai/googleai';
+import { googleAI } from '@genkit-ai/google-genai';
 import { createMcpHost } from '@genkit-ai/mcp';
 import { genkit } from 'genkit';
 
@@ -63,7 +63,7 @@ The `createMcpHost` function initializes a `GenkitMcpHost` instance, which handl
 -   **`version`**: (optional, string) The version of the MCP host plugin. Defaults to "1.0.0".
 -   **`rawToolResponses`**: (optional, boolean) When `true`, tool responses are returned in their raw MCP format; otherwise, they are processed for Genkit compatibility. Defaults to `false`.
 -   **`mcpServers`**: (required, object) An object where each key is a client-side name (namespace) for an MCP server, and the value is the configuration for that server.
-    
+
     Each server configuration object can include:
     -   **`disabled`**: (optional, boolean) If `true`, this server connection will not be attempted. Defaults to `false`.
     -   One of the following server connection configurations:
@@ -80,7 +80,7 @@ The `createMcpHost` function initializes a `GenkitMcpHost` instance, which handl
 For scenarios where you only need to connect to a single MCP server, or prefer to manage client instances individually, you can use `createMcpClient`.
 
 ```ts
-import { googleAI } from '@genkit-ai/googleai';
+import { googleAI } from '@genkit-ai/google-genai';
 import { createMcpClient } from '@genkit-ai/mcp';
 import { genkit } from 'genkit';
 
@@ -146,7 +146,7 @@ MCP tools return a `content` array as opposed to a structured response like most
 You can also expose all of the tools and prompts from a Genkit instance as an MCP server using the `createMcpServer` function.
 
 ```ts
-import { googleAI } from '@genkit-ai/googleai';
+import { googleAI } from '@genkit-ai/google-genai';
 import { createMcpServer } from '@genkit-ai/mcp';
 import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
 import { genkit, z } from 'genkit/beta';

samples/js-angular/README.md

@@ -45,4 +45,4 @@ Then access the application at [http://localhost:4200/](http://localhost:4200/)
 The application is built with:
 - Angular for the frontend framework
 - Genkit for AI integration
-- Gemini 2.0 Flash for the AI model
+- Gemini 2.5 Flash for the AI model