docs: 0.9 plugin updates

docs/_guides.yaml

@@ -79,8 +79,6 @@ toc:
     path: /docs/genkit/plugins/firebase
   - title: Google Cloud
     path: /docs/genkit/plugins/google-cloud
-  - title: LangChain
-    path: /docs/genkit/plugins/langchain
 
   - break: true
   - title: Connect with us

docs/plugins/chroma.md

@@ -1,6 +1,6 @@
 # Chroma plugin
 
-The Chroma plugin provides indexer and retriever implementatons that use the
+The Chroma plugin provides indexer and retriever implementations that use the
 [Chroma](https://docs.trychroma.com/) vector database in client/server mode.
 
 ## Installation
@@ -11,77 +11,73 @@ npm i --save genkitx-chromadb
 
 ## Configuration
 
-To use this plugin, specify it when you call `configureGenkit()`:
+To use this plugin, specify it when you initialize Genkit:
 
-```js
+```ts
+import { genkit } from 'genkit';
 import { chroma } from 'genkitx-chromadb';
 
-export default configureGenkit({
+const ai = genkit({
   plugins: [
     chroma([
       {
         collectionName: 'bob_collection',
-        embedder: textEmbeddingGecko,
+        embedder: textEmbedding004,
       },
     ]),
   ],
-  // ...
 });
 ```
 
-You must specify a Chroma collection and the embedding model you want to use. In
+You must specify a Chroma collection and the embedding model you want to use. In
 addition, there are two optional parameters:
 
-- `clientParams`: If you're not running your Chroma server on the same machine
-  as your Genkit flow, you need to specify auth options, or you're otherwise not
-  running a default Chroma server configuration, you can specify a Chroma
-  [`ChromaClientParams` object](https://docs.trychroma.com/js_reference/Client)
-  to pass to the Chroma client:
+*    `clientParams`: If you're not running your Chroma server on the same machine as your Genkit flow, you need to specify auth options, or you're otherwise not running a default Chroma server configuration, you can specify a Chroma <code>[ChromaClientParams object]([https://docs.trychroma.com/js_reference/Client](https://docs.trychroma.com/js_reference/Client))</code> to pass to the Chroma client:
 
-  ```js
-  clientParams: {
-    path: "http://192.168.10.42:8000",
-  }
-  ```
+    ```ts
+    clientParams: {
+      path: "http://192.168.10.42:8000",
+    }
+    ```
 
-- `embedderOptions`: Use this parameter to pass options to the embedder:
+*   `embedderOptions`: Use this parameter to pass options to the embedder:
 
-  ```js
-  embedderOptions: { taskType: 'RETRIEVAL_DOCUMENT' },
-  ```
+    ```ts
+    embedderOptions: { taskType: 'RETRIEVAL_DOCUMENT' },
+    ```
 
 ## Usage
 
 Import retriever and indexer references like so:
 
-```js
+```ts
 import { chromaRetrieverRef } from 'genkitx-chromadb';
 import { chromaIndexerRef } from 'genkitx-chromadb';
 ```
 
-Then, pass the references to `retrieve()` and `index()`:
+Then, use the references with `ai.retrieve()` and `ai.index()`:
 
-```js
+```ts
 // To use the index you configured when you loaded the plugin:
-let docs = await retrieve({ retriever: chromaRetrieverRef, query });
+let docs = await ai.retrieve({ retriever: chromaRetrieverRef, query });
 
 // To specify an index:
 export const bobFactsRetriever = chromaRetrieverRef({
   collectionName: 'bob-facts',
 });
-docs = await retrieve({ retriever: bobFactsRetriever, query });
+docs = await ai.retrieve({ retriever: bobFactsRetriever, query });
 ```
 
-```js
+```ts
 // To use the index you configured when you loaded the plugin:
-await index({ indexer: chromaIndexerRef, documents });
+await ai.index({ indexer: chromaIndexerRef, documents });
 
 // To specify an index:
 export const bobFactsIndexer = chromaIndexerRef({
   collectionName: 'bob-facts',
 });
-await index({ indexer: bobFactsIndexer, documents });
+await ai.index({ indexer: bobFactsIndexer, documents });
 ```
 
-See the [Retrieval-augmented generation](../rag.md) page for a general
+See the [Retrieval-augmented generation](../rag) page for a general
 discussion on indexers and retrievers.

docs/plugins/google-genai.md

@@ -11,14 +11,14 @@ npm i --save @genkit-ai/googleai
 
 ## Configuration
 
-To use this plugin, specify it when you call `configureGenkit()`:
+To use this plugin, specify it when you initialize Genkit:
 
-```js
+```ts
+import { genkit } from 'genkit';
 import { googleAI } from '@genkit-ai/googleai';
 
-export default configureGenkit({
+const ai = genkit({
   plugins: [googleAI()],
-  // ...
 });
 ```
 
@@ -27,61 +27,48 @@ The plugin requires an API key for the Gemini API, which you can get from
 
 Configure the plugin to use your API key by doing one of the following:
 
-- Set the `GOOGLE_GENAI_API_KEY` environment variable to your API key.
+*   Set the `GOOGLE_GENAI_API_KEY` environment variable to your API key.
+*   Specify the API key when you initialize the plugin:
 
-- Specify the API key when you initialize the plugin:
+    ```ts
+    googleAI({ apiKey: yourKey });
+    ```
 
-  ```js
-  googleAI({ apiKey: yourKey });
-  ```
-
-  However, don't embed your API key directly in code! Use this feature only
-  in conjunction with a service like Cloud Secret Manager or similar.
-
-Some models (like Gemini 1.5 Pro) are in preview and only aviable via the
-`v1beta` API. You can specify the `apiVersion` to get access to those models:
-
-```js
-configureGenkit({
-  plugins: [googleAI({ apiVersion: 'v1beta' })],
-});
-```
-
-or you can specify multiple versions if you'd like to use different versions of
-models at the same time.
-
-```js
-configureGenkit({
-  plugins: [googleAI({ apiVersion: ['v1', 'v1beta'] })],
-});
-```
+    However, don't embed your API key directly in code! Use this feature only in
+    conjunction with a service like Cloud Secret Manager or similar.
 
 ## Usage
 
 This plugin statically exports references to its supported models:
 
-```js
+```ts
 import {
   gemini15Flash,
   gemini15Pro,
-  textEmbeddingGecko001,
+  textEmbedding004,
 } from '@genkit-ai/googleai';
 ```
 
 You can use these references to specify which model `generate()` uses:
 
-```js
-const llmResponse = await generate({
+```ts
+const ai = genkit({
+  plugins: [googleAI()],
   model: gemini15Flash,
-  prompt: 'Tell me a joke.',
 });
+
+const llmResponse = await ai.generate('Tell me a joke.');
 ```
 
-or use embedders (ex. `textEmbeddingGecko001`) with `embed` or retrievers:
+or use embedders (ex. `textEmbedding004`) with `embed` or retrievers:
 
-```js
-const embedding = await embed({
-  embedder: textEmbeddingGecko001,
+```ts
+const ai = genkit({
+  plugins: [googleAI()],
+});
+
+const embedding = await ai.embed({
+  embedder: textEmbedding004,
   content: input,
 });
 ```
@@ -90,8 +77,14 @@ const embedding = await embed({
 
 You can use files uploaded to the Gemini Files API with Genkit:
 
-```js
+```ts
 import { GoogleAIFileManager } from '@google/generative-ai/server';
+import { genkit } from 'genkit';
+import { googleAI } from '@genkit-ai/googleai';
+
+const ai = genkit({
+  plugins: [googleAI()],
+});
 
 const fileManager = new GoogleAIFileManager(process.env.GOOGLE_GENAI_API_KEY);
 const uploadResult = await fileManager.uploadFile(
@@ -102,7 +95,7 @@ const uploadResult = await fileManager.uploadFile(
   }
 );
 
-const response = await generate({
+const response = await ai.generate({
   model: gemini15Flash,
   prompt: [
     {text: 'Describe this image:'},
@@ -113,18 +106,30 @@ const response = await generate({
 
 ## Fine-tuned models
 
-You can use models fine-tuned with the Google Gemini API.  Follow the instructions from the [Gemini API](https://ai.google.dev/gemini-api/docs/model-tuning/tutorial?lang=python) or fine-tune a model using [AI Studio](https://aistudio.corp.google.com/app/tune).
+You can use models fine-tuned with the Google Gemini API.  Follow the
+instructions from the
+[Gemini API](https://ai.google.dev/gemini-api/docs/model-tuning/tutorial?lang=python)
+or fine-tune a model using
+[AI Studio](https://aistudio.corp.google.com/app/tune).
 
-The tuning process uses a base model—for example, Gemini 1.5 Flash—and your provided examples to create a new tuned model.  Remember the base model you used, and copy the new model's ID.
+The tuning process uses a base model—for example, Gemini 1.5 Flash—and your
+provided examples to create a new tuned model.  Remember the base model you
+used, and copy the new model's ID.
 
-When calling the tuned model in Genkit, use the base model as the `model` parameter, and pass the tuned model's ID as part of the `config` block. For example, if you used Gemini 1.5 Flash as the base model, and got the model ID `tunedModels/my-example-model-apbm8oqbvuv2` you can call it with a block like the following:
+When calling the tuned model in Genkit, use the base model as the `model`
+parameter, and pass the tuned model's ID as part of the `config` block. For
+example, if you used Gemini 1.5 Flash as the base model, and got the model ID
+`tunedModels/my-example-model-apbm8oqbvuv2` you can call it with:
 
-```js
-const llmResponse = await generate({
+```ts
+const ai = genkit({
+  plugins: [googleAI()],
+});
+
+const llmResponse = await ai.generate({
   prompt: `Suggest an item for the menu of fish themed restruant`,
-  model: gemini15Flash,
-  config: {
+  model: gemini15Flash.withConfig({
     version: "tunedModels/my-example-model-apbm8oqbvuv2",
-  },
+  }),
 });
-```
+```