feat: added invoke method to chat model docs (langchain-ai#2981)

* feat: added invoke method to chat model docs

* nit

* nit: remove install openai dep

docs/docs/modules/model_io/models/chat/index.mdx

@@ -20,24 +20,6 @@ The following sections of documentation are provided:
 
 ### Setup
 
-To start we'll need to install the official OpenAI package:
-
-import Tabs from "@theme/Tabs";
-import TabItem from "@theme/TabItem";
-import CodeBlock from "@theme/CodeBlock";
-
-<Tabs>
-  <TabItem value="npm" label="npm" default>
-    <CodeBlock language="bash">npm install -S openai</CodeBlock>
-  </TabItem>
-  <TabItem value="yarn" label="Yarn">
-    <CodeBlock language="bash">yarn add openai</CodeBlock>
-  </TabItem>
-  <TabItem value="pnpm" label="pnpm">
-    <CodeBlock language="bash">pnpm add openai</CodeBlock>
-  </TabItem>
-</Tabs>
-
 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:
 
 ```bash
@@ -67,6 +49,16 @@ const chat = new ChatOpenAI({});
 The chat model interface is based around messages rather than raw text.
 The types of messages currently supported in LangChain are `AIMessage`, `HumanMessage`, `SystemMessage`, `FunctionMessage`, and `ChatMessage` -- `ChatMessage` takes in an arbitrary role parameter. Most of the time, you'll just be dealing with `HumanMessage`, `AIMessage`, and `SystemMessage`
 
+### `invoke`
+
+#### Generic inputs -> generic outputs
+
+You can generate LLM responses by calling `.invoke` and passing in whatever inputs you defined in the (`Runnable`)[/docs/expression_language/].
+
+import RunnableExample from "@examples/models/chat/runnable_chat_quick_start.ts";
+
+<CodeBlock language="typescript">{RunnableExample}</CodeBlock>
+
 ### `call`
 
 #### Messages in -> message out

examples/src/models/chat/chat_quick_start.ts

@@ -1,7 +1,7 @@
 import { ChatOpenAI } from "langchain/chat_models/openai";
 import { HumanMessage } from "langchain/schema";
 
-const chat = new ChatOpenAI();
+const chat = new ChatOpenAI({});
 // Pass in a list of messages to `call` to start a conversation. In this simple example, we only pass in one message.
 const response = await chat.call([
   new HumanMessage(

examples/src/models/chat/runnable_chat_quick_start.ts

@@ -0,0 +1,14 @@
+import { ChatOpenAI } from "langchain/chat_models/openai";
+import { PromptTemplate } from "langchain/prompts";
+
+const chat = new ChatOpenAI({});
+// Create a prompt to start the conversation.
+const prompt =
+  PromptTemplate.fromTemplate(`You're a dog, good luck with the conversation.
+Question: {question}`);
+// Define your runnable by piping the prompt into the chat model.
+const runnable = prompt.pipe(chat);
+// Call .invoke() and pass in the input defined in the prompt template.
+const response = await runnable.invoke({ question: "Who's a good boy??" });
+console.log(response);
+// AIMessage { content: "Woof woof! Thank you for asking! I believe I'm a good boy! I try my best to be a good dog and make my humans happy. Wagging my tail happily here! How can I make your day better?" }