Add Anthropic to examples (#4609)

docs/core_docs/docs/get_started/quickstart.mdx

@@ -52,25 +52,23 @@ We will cover these at a high level, but keep in mind there is a lot more to eac
 
 ## LLM Chain
 
-For this getting started guide, we will provide two options: using OpenAI (available via API) or using a local open source model.
+import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
 
-<Tabs>
+<Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>
 
 First we'll need to install the LangChain OpenAI integration package:
 
-import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
-
 <IntegrationInstallTooltip></IntegrationInstallTooltip>
 
 ```bash npm2yarn
 npm install @langchain/openai
 ```
 
-Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable by running:
+Accessing the API requires an API key, which you can get by creating an account [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable:
 
 ```bash
-export OPENAI_API_KEY="..."
+OPENAI_API_KEY="..."
 ```
 
 If you'd prefer not to set an environment variable you can pass the key in directly via the `openAIApiKey` named parameter when initiating the OpenAI Chat Model class:
@@ -92,7 +90,7 @@ const chatModel = new ChatOpenAI({});
 ```
 
   </TabItem>
-  <TabItem value="local" label="Local">
+  <TabItem value="local" label="Local (using Ollama)">
 
 [Ollama](https://ollama.ai/) allows you to run open-source large language models, such as Llama 2 and Mistral, locally.
 
@@ -118,6 +116,41 @@ const chatModel = new ChatOllama({
   baseUrl: "http://localhost:11434", // Default value
   model: "mistral",
 });
+```
+
+  </TabItem>
+  <TabItem value="anthropic" label="Anthropic">
+
+First we'll need to install the LangChain Anthropic integration package:
+
+<IntegrationInstallTooltip></IntegrationInstallTooltip>
+
+```bash npm2yarn
+npm install @langchain/anthropic
+```
+
+Accessing the API requires an API key, which you can get by creating an account [here](https://www.anthropic.com/). Once we have a key we'll want to set it as an environment variable:
+
+```bash
+ANTHROPIC_API_KEY="..."
+```
+
+If you'd prefer not to set an environment variable you can pass the key in directly via the `anthropicApiKey` named parameter when initiating the Anthropic Chat Model class:
+
+```typescript
+import { ChatAnthropic } from "@langchain/anthropic";
+
+const chatModel = new ChatAnthropic({
+  anthropicApiKey: "...",
+});
+```
+
+Otherwise you can initialize without any params:
+
+```typescript
+import { ChatAnthropic } from "@langchain/anthropic";
+
+const chatModel = new ChatAnthropic({});
 ```
 
   </TabItem>
@@ -253,7 +286,7 @@ Note that the size of the loaded document is large and may exceed the maximum am
 We can split the document into more manageable chunks to get around this limitation and to reduce the amount of distraction
 to the model using a [text splitter](/docs/modules/data_connection/document_transformers/):
 
-```
+```ts
 import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";
 
 const splitter = new RecursiveCharacterTextSplitter();
@@ -274,7 +307,7 @@ This requires a few components, namely an [embedding model](/docs/modules/data_c
 
 There are many options for both components. Here are some examples for accessing via OpenAI and via local models:
 
-<Tabs>
+<Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>
 
 Make sure you have the `@langchain/openai` package installed and the appropriate environment variables set (these are the same as needed for the model above).
@@ -286,15 +319,15 @@ const embeddings = new OpenAIEmbeddings();
 ```
 
   </TabItem>
-  <TabItem value="local" label="Local">
+  <TabItem value="local" label="Local (using Ollama)">
 
 Make sure you have Ollama running (same set up as with the model).
 
 ```ts
 import { OllamaEmbeddings } from "@langchain/community/embeddings/ollama";
 
 const embeddings = new OllamaEmbeddings({
-  model: "mistral",
+  model: "nomic-embed-text",
   maxConcurrency: 5,
 });
 ```

docs/core_docs/docs/modules/model_io/chat/quick_start.mdx

@@ -12,24 +12,23 @@ Rather than using a "text in, text out" API, they use an interface where "chat m
 
 import Tabs from "@theme/Tabs";
 import TabItem from "@theme/TabItem";
+import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
 
-<Tabs>
+<Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>
 
 First we'll need to install the LangChain OpenAI integration package:
 
-import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
-
 <IntegrationInstallTooltip></IntegrationInstallTooltip>
 
 ```bash npm2yarn
 npm install @langchain/openai
 ```
 
-Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable by running:
+Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable:
 
 ```bash
-export OPENAI_API_KEY="..."
+OPENAI_API_KEY="..."
 ```
 
 If you'd prefer not to set an environment variable you can pass the key in directly via the `openAIApiKey` named parameter when initiating the OpenAI Chat Model class:
@@ -51,7 +50,7 @@ const chatModel = new ChatOpenAI();
 ```
 
   </TabItem>
-  <TabItem value="local" label="Local">
+  <TabItem value="local" label="Local (using Ollama)">
 
 [Ollama](https://ollama.ai/) allows you to run open-source large language models, such as Llama 2 and Mistral, locally.
 
@@ -77,6 +76,41 @@ const chatModel = new ChatOllama({
   baseUrl: "http://localhost:11434", // Default value
   model: "mistral",
 });
+```
+
+  </TabItem>
+  <TabItem value="anthropic" label="Anthropic" default>
+
+First we'll need to install the LangChain Anthropic integration package:
+
+<IntegrationInstallTooltip></IntegrationInstallTooltip>
+
+```bash npm2yarn
+npm install @langchain/anthropic
+```
+
+Accessing the API requires an API key, which you can get by creating an account [here](https://www.anthropic.com/). Once we have a key we'll want to set it as an environment variable:
+
+```bash
+ANTHROPIC_API_KEY="..."
+```
+
+If you'd prefer not to set an environment variable you can pass the key in directly via the `anthropicApiKey` named parameter when initiating the `ChatAnthropic` class:
+
+```typescript
+import { ChatAnthropic } from "@langchain/anthropic";
+
+const chatModel = new ChatAnthropic({
+  anthropicApiKey: "...",
+});
+```
+
+Otherwise you can initialize without any params:
+
+```typescript
+import { ChatAnthropic } from "@langchain/anthropic";
+
+const chatModel = new ChatAnthropic();
 ```
 
   </TabItem>

docs/core_docs/docs/modules/model_io/llms/quick_start.mdx

@@ -55,7 +55,7 @@ const llm = new OpenAI({});
 ```
 
   </TabItem>
-  <TabItem value="local" label="Local">
+  <TabItem value="local" label="Local (using Ollama)">
 
 [Ollama](https://ollama.ai/) allows you to run open-source large language models, such as Llama 2 and Mistral, locally.
 

docs/core_docs/docs/modules/model_io/quick_start.mdx

@@ -11,29 +11,26 @@ For a deeper conceptual guide into these topics - please see [this page](/docs/m
 
 ## Models
 
-For this getting started guide, we will provide two options: using OpenAI (a popular model available via API) or using a locally running open source model.
-
 import Tabs from "@theme/Tabs";
 import TabItem from "@theme/TabItem";
 import CodeBlock from "@theme/CodeBlock";
+import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
 
-<Tabs>
+<Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>
 
 First we'll need to install the LangChain OpenAI integration package:
 
-import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
-
 <IntegrationInstallTooltip></IntegrationInstallTooltip>
 
 ```bash npm2yarn
 npm install @langchain/openai
 ```
 
-Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable by running:
+Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable:
 
 ```shell
-export OPENAI_API_KEY="..."
+OPENAI_API_KEY="..."
 ```
 
 We can then initialize the model:
@@ -58,7 +55,7 @@ const model = new ChatOpenAI({
 ```
 
   </TabItem>
-  <TabItem value="local" label="Local">
+  <TabItem value="local" label="Local (using Ollama)">
 
 [Ollama](https://ollama.ai/) allows you to run open-source large language models, such as Llama 2 and Mistral, locally.
 
@@ -89,12 +86,47 @@ const chatModel = new ChatOllama({
   baseUrl: "http://localhost:11434", // Default value
   model: "mistral",
 });
+```
+
+  </TabItem>
+  <TabItem value="anthropic" label="Anthropic" default>
+
+First we'll need to install the LangChain Anthropic integration package:
+
+<IntegrationInstallTooltip></IntegrationInstallTooltip>
+
+```bash npm2yarn
+npm install @langchain/anthropic
+```
+
+Accessing the API requires an API key, which you can get by creating an account [here](https://www.anthropic.com/). Once we have a key we'll want to set it as an environment variable:
+
+```bash
+ANTHROPIC_API_KEY="..."
+```
+
+We can then initialize the model:
+
+```typescript
+import { ChatAnthropic } from "@langchain/anthropic";
+
+const chatModel = new ChatAnthropic({
+  modelName: "claude-2.1",
+});
+```
+
+If you can't or would prefer not to set an environment variable, you can pass the key in directly via the `anthropicApiKey` named parameter when initiating the ChatAnthropic class:
+
+```typescript
+const model = new ChatAnthropic({
+  anthropicApiKey: "<your key here>",
+});
 ```
 
   </TabItem>
 </Tabs>
 
-Both `llm` and `chatModel` are objects that represent configuration for a particular model.
+These classes represent configuration for a particular model.
 You can initialize them with parameters like `temperature` and others, and pass them around.
 The main difference between them is their input and output schemas.
 

docs/core_docs/src/theme/Npm2Yarn.js

@@ -7,7 +7,7 @@ import CodeBlock from "@theme-original/CodeBlock";
 // parsing built-in npm2yarn markdown blocks
 export default function Npm2Yarn({ children }) {
   return (
-    <Tabs>
+    <Tabs groupId="npm2yarn">
       <TabItem value="npm" label="npm">
         <CodeBlock language="bash">npm i {children}</CodeBlock>
       </TabItem>