@langchain/google-vertexai 0.0.25 → 0.0.27

package/dist/chat_models.cjs

@@ -3,8 +3,286 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.ChatVertexAI = void 0;
 const google_gauth_1 = require("@langchain/google-gauth");
 /**
- * Integration with a Google Vertex AI chat model using
- * the "@langchain/google-gauth" package for auth.
+ * Integration with Google Vertex AI chat models.
+ *
+ * Setup:
+ * Install `@langchain/google-vertexai` and set your stringified
+ * Vertex AI credentials as an environment variable named `GOOGLE_APPLICATION_CREDENTIALS`.
+ *
+ * ```bash
+ * npm install @langchain/google-vertexai
+ * export GOOGLE_APPLICATION_CREDENTIALS="path/to/credentials"
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/langchain_community_chat_models_googlevertexai_web.ChatGoogleVertexAI.html#constructor)
+ *
+ * ## [Runtime args](https://api.js.langchain.com/interfaces/langchain_google_common_types.GoogleAIBaseLanguageModelCallOptions.html)
+ *
+ * Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc.
+ * They can also be passed via `.bind`, or the second arg in `.bindTools`, like shown in the examples below:
+ *
+ * ```typescript
+ * // When calling `.bind`, call options should be passed via the first argument
+ * const llmWithArgsBound = llm.bind({
+ *   stop: ["\n"],
+ *   tools: [...],
+ * });
+ *
+ * // When calling `.bindTools`, call options should be passed via the second argument
+ * const llmWithTools = llm.bindTools(
+ *   [...],
+ *   {
+ *     tool_choice: "auto",
+ *   }
+ * );
+ * ```
+ *
+ * ## Examples
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { ChatVertexAI } from '@langchain/google-vertexai';
+ *
+ * const llm = new ChatVertexAI({
+ *   model: "gemini-1.5-pro",
+ *   temperature: 0,
+ *   // other params...
+ * });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Invoking</strong></summary>
+ *
+ * ```typescript
+ * const input = `Translate "I love programming" into French.`;
+ *
+ * // Models also accept a list of chat messages or a formatted prompt
+ * const result = await llm.invoke(input);
+ * console.log(result);
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"J'adore programmer\" \n\nHere's why this is the best translation:\n\n* **J'adore** means \"I love\" and conveys a strong passion.\n* **Programmer** is the French verb for \"to program.\"\n\nThis translation is natural and idiomatic in French. \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 63,
+ *     "total_tokens": 72
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Streaming Chunks</strong></summary>
+ *
+ * ```typescript
+ * for await (const chunk of await llm.stream(input)) {
+ *   console.log(chunk);
+ * }
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "J'adore programmer\" \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {
+ *     "finishReason": "stop"
+ *   },
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 8,
+ *     "total_tokens": 17
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Aggregate Streamed Chunks</strong></summary>
+ *
+ * ```typescript
+ * import { AIMessageChunk } from '@langchain/core/messages';
+ * import { concat } from '@langchain/core/utils/stream';
+ *
+ * const stream = await llm.stream(input);
+ * let full: AIMessageChunk | undefined;
+ * for await (const chunk of stream) {
+ *   full = !full ? chunk : concat(full, chunk);
+ * }
+ * console.log(full);
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"J'adore programmer\" \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {
+ *     "finishReason": "stop"
+ *   },
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 8,
+ *     "total_tokens": 17
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Bind tools</strong></summary>
+ *
+ * ```typescript
+ * import { z } from 'zod';
+ *
+ * const GetWeather = {
+ *   name: "GetWeather",
+ *   description: "Get the current weather in a given location",
+ *   schema: z.object({
+ *     location: z.string().describe("The city and state, e.g. San Francisco, CA")
+ *   }),
+ * }
+ *
+ * const GetPopulation = {
+ *   name: "GetPopulation",
+ *   description: "Get the current population in a given location",
+ *   schema: z.object({
+ *     location: z.string().describe("The city and state, e.g. San Francisco, CA")
+ *   }),
+ * }
+ *
+ * const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);
+ * const aiMsg = await llmWithTools.invoke(
+ *   "Which city is hotter today and which is bigger: LA or NY?"
+ * );
+ * console.log(aiMsg.tool_calls);
+ * ```
+ *
+ * ```txt
+ * [
+ *   {
+ *     name: 'GetPopulation',
+ *     args: { location: 'New York City, NY' },
+ *     id: '33c1c1f47e2f492799c77d2800a43912',
+ *     type: 'tool_call'
+ *   }
+ * ]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Structured Output</strong></summary>
+ *
+ * ```typescript
+ * import { z } from 'zod';
+ *
+ * const Joke = z.object({
+ *   setup: z.string().describe("The setup of the joke"),
+ *   punchline: z.string().describe("The punchline to the joke"),
+ *   rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
+ * }).describe('Joke to tell user.');
+ *
+ * const structuredLlm = llm.withStructuredOutput(Joke, { name: "Joke" });
+ * const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
+ * console.log(jokeResult);
+ * ```
+ *
+ * ```txt
+ * {
+ *   setup: 'What do you call a cat that loves to bowl?',
+ *   punchline: 'An alley cat!'
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Usage Metadata</strong></summary>
+ *
+ * ```typescript
+ * const aiMsgForMetadata = await llm.invoke(input);
+ * console.log(aiMsgForMetadata.usage_metadata);
+ * ```
+ *
+ * ```txt
+ * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Stream Usage Metadata</strong></summary>
+ *
+ * ```typescript
+ * const streamForMetadata = await llm.stream(
+ *   input,
+ *   {
+ *     streamUsage: true
+ *   }
+ * );
+ * let fullForMetadata: AIMessageChunk | undefined;
+ * for await (const chunk of streamForMetadata) {
+ *   fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);
+ * }
+ * console.log(fullForMetadata?.usage_metadata);
+ * ```
+ *
+ * ```txt
+ * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }
+ * ```
+ * </details>
+ *
+ * <br />
  */
 class ChatVertexAI extends google_gauth_1.ChatGoogle {
     static lc_name() {

package/dist/chat_models.d.ts

@@ -5,8 +5,286 @@ import { type ChatGoogleInput, ChatGoogle } from "@langchain/google-gauth";
 export interface ChatVertexAIInput extends ChatGoogleInput {
 }
 /**
- * Integration with a Google Vertex AI chat model using
- * the "@langchain/google-gauth" package for auth.
+ * Integration with Google Vertex AI chat models.
+ *
+ * Setup:
+ * Install `@langchain/google-vertexai` and set your stringified
+ * Vertex AI credentials as an environment variable named `GOOGLE_APPLICATION_CREDENTIALS`.
+ *
+ * ```bash
+ * npm install @langchain/google-vertexai
+ * export GOOGLE_APPLICATION_CREDENTIALS="path/to/credentials"
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/langchain_community_chat_models_googlevertexai_web.ChatGoogleVertexAI.html#constructor)
+ *
+ * ## [Runtime args](https://api.js.langchain.com/interfaces/langchain_google_common_types.GoogleAIBaseLanguageModelCallOptions.html)
+ *
+ * Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc.
+ * They can also be passed via `.bind`, or the second arg in `.bindTools`, like shown in the examples below:
+ *
+ * ```typescript
+ * // When calling `.bind`, call options should be passed via the first argument
+ * const llmWithArgsBound = llm.bind({
+ *   stop: ["\n"],
+ *   tools: [...],
+ * });
+ *
+ * // When calling `.bindTools`, call options should be passed via the second argument
+ * const llmWithTools = llm.bindTools(
+ *   [...],
+ *   {
+ *     tool_choice: "auto",
+ *   }
+ * );
+ * ```
+ *
+ * ## Examples
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { ChatVertexAI } from '@langchain/google-vertexai';
+ *
+ * const llm = new ChatVertexAI({
+ *   model: "gemini-1.5-pro",
+ *   temperature: 0,
+ *   // other params...
+ * });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Invoking</strong></summary>
+ *
+ * ```typescript
+ * const input = `Translate "I love programming" into French.`;
+ *
+ * // Models also accept a list of chat messages or a formatted prompt
+ * const result = await llm.invoke(input);
+ * console.log(result);
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"J'adore programmer\" \n\nHere's why this is the best translation:\n\n* **J'adore** means \"I love\" and conveys a strong passion.\n* **Programmer** is the French verb for \"to program.\"\n\nThis translation is natural and idiomatic in French. \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 63,
+ *     "total_tokens": 72
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Streaming Chunks</strong></summary>
+ *
+ * ```typescript
+ * for await (const chunk of await llm.stream(input)) {
+ *   console.log(chunk);
+ * }
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "J'adore programmer\" \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {
+ *     "finishReason": "stop"
+ *   },
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 8,
+ *     "total_tokens": 17
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Aggregate Streamed Chunks</strong></summary>
+ *
+ * ```typescript
+ * import { AIMessageChunk } from '@langchain/core/messages';
+ * import { concat } from '@langchain/core/utils/stream';
+ *
+ * const stream = await llm.stream(input);
+ * let full: AIMessageChunk | undefined;
+ * for await (const chunk of stream) {
+ *   full = !full ? chunk : concat(full, chunk);
+ * }
+ * console.log(full);
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"J'adore programmer\" \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {
+ *     "finishReason": "stop"
+ *   },
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 8,
+ *     "total_tokens": 17
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Bind tools</strong></summary>
+ *
+ * ```typescript
+ * import { z } from 'zod';
+ *
+ * const GetWeather = {
+ *   name: "GetWeather",
+ *   description: "Get the current weather in a given location",
+ *   schema: z.object({
+ *     location: z.string().describe("The city and state, e.g. San Francisco, CA")
+ *   }),
+ * }
+ *
+ * const GetPopulation = {
+ *   name: "GetPopulation",
+ *   description: "Get the current population in a given location",
+ *   schema: z.object({
+ *     location: z.string().describe("The city and state, e.g. San Francisco, CA")
+ *   }),
+ * }
+ *
+ * const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);
+ * const aiMsg = await llmWithTools.invoke(
+ *   "Which city is hotter today and which is bigger: LA or NY?"
+ * );
+ * console.log(aiMsg.tool_calls);
+ * ```
+ *
+ * ```txt
+ * [
+ *   {
+ *     name: 'GetPopulation',
+ *     args: { location: 'New York City, NY' },
+ *     id: '33c1c1f47e2f492799c77d2800a43912',
+ *     type: 'tool_call'
+ *   }
+ * ]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Structured Output</strong></summary>
+ *
+ * ```typescript
+ * import { z } from 'zod';
+ *
+ * const Joke = z.object({
+ *   setup: z.string().describe("The setup of the joke"),
+ *   punchline: z.string().describe("The punchline to the joke"),
+ *   rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
+ * }).describe('Joke to tell user.');
+ *
+ * const structuredLlm = llm.withStructuredOutput(Joke, { name: "Joke" });
+ * const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
+ * console.log(jokeResult);
+ * ```
+ *
+ * ```txt
+ * {
+ *   setup: 'What do you call a cat that loves to bowl?',
+ *   punchline: 'An alley cat!'
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Usage Metadata</strong></summary>
+ *
+ * ```typescript
+ * const aiMsgForMetadata = await llm.invoke(input);
+ * console.log(aiMsgForMetadata.usage_metadata);
+ * ```
+ *
+ * ```txt
+ * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Stream Usage Metadata</strong></summary>
+ *
+ * ```typescript
+ * const streamForMetadata = await llm.stream(
+ *   input,
+ *   {
+ *     streamUsage: true
+ *   }
+ * );
+ * let fullForMetadata: AIMessageChunk | undefined;
+ * for await (const chunk of streamForMetadata) {
+ *   fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);
+ * }
+ * console.log(fullForMetadata?.usage_metadata);
+ * ```
+ *
+ * ```txt
+ * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }
+ * ```
+ * </details>
+ *
+ * <br />
  */
 export declare class ChatVertexAI extends ChatGoogle {
     static lc_name(): string;

package/dist/chat_models.js

@@ -1,7 +1,285 @@
 import { ChatGoogle } from "@langchain/google-gauth";
 /**
- * Integration with a Google Vertex AI chat model using
- * the "@langchain/google-gauth" package for auth.
+ * Integration with Google Vertex AI chat models.
+ *
+ * Setup:
+ * Install `@langchain/google-vertexai` and set your stringified
+ * Vertex AI credentials as an environment variable named `GOOGLE_APPLICATION_CREDENTIALS`.
+ *
+ * ```bash
+ * npm install @langchain/google-vertexai
+ * export GOOGLE_APPLICATION_CREDENTIALS="path/to/credentials"
+ * ```
+ *
+ * ## [Constructor args](https://api.js.langchain.com/classes/langchain_community_chat_models_googlevertexai_web.ChatGoogleVertexAI.html#constructor)
+ *
+ * ## [Runtime args](https://api.js.langchain.com/interfaces/langchain_google_common_types.GoogleAIBaseLanguageModelCallOptions.html)
+ *
+ * Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc.
+ * They can also be passed via `.bind`, or the second arg in `.bindTools`, like shown in the examples below:
+ *
+ * ```typescript
+ * // When calling `.bind`, call options should be passed via the first argument
+ * const llmWithArgsBound = llm.bind({
+ *   stop: ["\n"],
+ *   tools: [...],
+ * });
+ *
+ * // When calling `.bindTools`, call options should be passed via the second argument
+ * const llmWithTools = llm.bindTools(
+ *   [...],
+ *   {
+ *     tool_choice: "auto",
+ *   }
+ * );
+ * ```
+ *
+ * ## Examples
+ *
+ * <details open>
+ * <summary><strong>Instantiate</strong></summary>
+ *
+ * ```typescript
+ * import { ChatVertexAI } from '@langchain/google-vertexai';
+ *
+ * const llm = new ChatVertexAI({
+ *   model: "gemini-1.5-pro",
+ *   temperature: 0,
+ *   // other params...
+ * });
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Invoking</strong></summary>
+ *
+ * ```typescript
+ * const input = `Translate "I love programming" into French.`;
+ *
+ * // Models also accept a list of chat messages or a formatted prompt
+ * const result = await llm.invoke(input);
+ * console.log(result);
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"J'adore programmer\" \n\nHere's why this is the best translation:\n\n* **J'adore** means \"I love\" and conveys a strong passion.\n* **Programmer** is the French verb for \"to program.\"\n\nThis translation is natural and idiomatic in French. \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 63,
+ *     "total_tokens": 72
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Streaming Chunks</strong></summary>
+ *
+ * ```typescript
+ * for await (const chunk of await llm.stream(input)) {
+ *   console.log(chunk);
+ * }
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "J'adore programmer\" \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {},
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": []
+ * }
+ * AIMessageChunk {
+ *   "content": "",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {
+ *     "finishReason": "stop"
+ *   },
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 8,
+ *     "total_tokens": 17
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Aggregate Streamed Chunks</strong></summary>
+ *
+ * ```typescript
+ * import { AIMessageChunk } from '@langchain/core/messages';
+ * import { concat } from '@langchain/core/utils/stream';
+ *
+ * const stream = await llm.stream(input);
+ * let full: AIMessageChunk | undefined;
+ * for await (const chunk of stream) {
+ *   full = !full ? chunk : concat(full, chunk);
+ * }
+ * console.log(full);
+ * ```
+ *
+ * ```txt
+ * AIMessageChunk {
+ *   "content": "\"J'adore programmer\" \n",
+ *   "additional_kwargs": {},
+ *   "response_metadata": {
+ *     "finishReason": "stop"
+ *   },
+ *   "tool_calls": [],
+ *   "tool_call_chunks": [],
+ *   "invalid_tool_calls": [],
+ *   "usage_metadata": {
+ *     "input_tokens": 9,
+ *     "output_tokens": 8,
+ *     "total_tokens": 17
+ *   }
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Bind tools</strong></summary>
+ *
+ * ```typescript
+ * import { z } from 'zod';
+ *
+ * const GetWeather = {
+ *   name: "GetWeather",
+ *   description: "Get the current weather in a given location",
+ *   schema: z.object({
+ *     location: z.string().describe("The city and state, e.g. San Francisco, CA")
+ *   }),
+ * }
+ *
+ * const GetPopulation = {
+ *   name: "GetPopulation",
+ *   description: "Get the current population in a given location",
+ *   schema: z.object({
+ *     location: z.string().describe("The city and state, e.g. San Francisco, CA")
+ *   }),
+ * }
+ *
+ * const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);
+ * const aiMsg = await llmWithTools.invoke(
+ *   "Which city is hotter today and which is bigger: LA or NY?"
+ * );
+ * console.log(aiMsg.tool_calls);
+ * ```
+ *
+ * ```txt
+ * [
+ *   {
+ *     name: 'GetPopulation',
+ *     args: { location: 'New York City, NY' },
+ *     id: '33c1c1f47e2f492799c77d2800a43912',
+ *     type: 'tool_call'
+ *   }
+ * ]
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Structured Output</strong></summary>
+ *
+ * ```typescript
+ * import { z } from 'zod';
+ *
+ * const Joke = z.object({
+ *   setup: z.string().describe("The setup of the joke"),
+ *   punchline: z.string().describe("The punchline to the joke"),
+ *   rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
+ * }).describe('Joke to tell user.');
+ *
+ * const structuredLlm = llm.withStructuredOutput(Joke, { name: "Joke" });
+ * const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
+ * console.log(jokeResult);
+ * ```
+ *
+ * ```txt
+ * {
+ *   setup: 'What do you call a cat that loves to bowl?',
+ *   punchline: 'An alley cat!'
+ * }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Usage Metadata</strong></summary>
+ *
+ * ```typescript
+ * const aiMsgForMetadata = await llm.invoke(input);
+ * console.log(aiMsgForMetadata.usage_metadata);
+ * ```
+ *
+ * ```txt
+ * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }
+ * ```
+ * </details>
+ *
+ * <br />
+ *
+ * <details>
+ * <summary><strong>Stream Usage Metadata</strong></summary>
+ *
+ * ```typescript
+ * const streamForMetadata = await llm.stream(
+ *   input,
+ *   {
+ *     streamUsage: true
+ *   }
+ * );
+ * let fullForMetadata: AIMessageChunk | undefined;
+ * for await (const chunk of streamForMetadata) {
+ *   fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);
+ * }
+ * console.log(fullForMetadata?.usage_metadata);
+ * ```
+ *
+ * ```txt
+ * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }
+ * ```
+ * </details>
+ *
+ * <br />
  */
 export class ChatVertexAI extends ChatGoogle {
     static lc_name() {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@langchain/google-vertexai",
-  "version": "0.0.25",
+  "version": "0.0.27",
   "description": "LangChain.js support for Google Vertex AI",
   "type": "module",
   "engines": {
@@ -15,12 +15,7 @@
   "homepage": "https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-google-vertexai/",
   "scripts": {
     "build": "yarn turbo:command build:internal --filter=@langchain/google-vertexai",
-    "build:internal": "yarn lc_build_v2 --create-entrypoints --pre --tree-shaking",
-    "build:deps": "yarn run turbo:command build --filter=@langchain/google-gauth",
-    "build:esm": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist/ && rm -rf dist/tests dist/**/tests",
-    "build:cjs": "NODE_OPTIONS=--max-old-space-size=4096 tsc --outDir dist-cjs/ -p tsconfig.cjs.json && yarn move-cjs-to-dist && rm -rf dist-cjs",
-    "build:watch": "yarn create-entrypoints && tsc --outDir dist/ --watch",
-    "build:scripts": "yarn create-entrypoints && yarn check-tree-shaking",
+    "build:internal": "yarn lc_build --create-entrypoints --pre --tree-shaking",
     "lint:eslint": "NODE_OPTIONS=--max-old-space-size=4096 eslint --cache --ext .ts,.js src/",
     "lint:dpdm": "dpdm --exit-code circular:1 --no-warning --no-tree src/*.ts src/**/*.ts",
     "lint": "yarn lint:eslint && yarn lint:dpdm",
@@ -31,25 +26,19 @@
     "test:watch": "NODE_OPTIONS=--experimental-vm-modules jest --watch --testPathIgnorePatterns=\\.int\\.test.ts",
     "test:single": "NODE_OPTIONS=--experimental-vm-modules yarn run jest --config jest.config.cjs --testTimeout 100000",
     "test:int": "NODE_OPTIONS=--experimental-vm-modules jest --testPathPattern=\\.int\\.test.ts --testTimeout 100000 --maxWorkers=50%",
-    "test:standard:unit": "NODE_OPTIONS=--experimental-vm-modules jest --testPathPattern=\\.standard\\.test.ts --testTimeout 100000 --maxWorkers=50%",
-    "test:standard:int": "NODE_OPTIONS=--experimental-vm-modules jest --testPathPattern=\\.standard\\.int\\.test.ts --testTimeout 100000 --maxWorkers=50%",
-    "test:standard": "yarn test:standard:unit && yarn test:standard:int",
     "format": "prettier --config .prettierrc --write \"src\"",
-    "format:check": "prettier --config .prettierrc --check \"src\"",
-    "move-cjs-to-dist": "yarn lc-build --config ./langchain.config.js --move-cjs-dist",
-    "create-entrypoints": "yarn lc-build --config ./langchain.config.js --create-entrypoints",
-    "check-tree-shaking": "yarn lc-build --config ./langchain.config.js --tree-shaking"
+    "format:check": "prettier --config .prettierrc --check \"src\""
   },
   "author": "LangChain",
   "license": "MIT",
   "dependencies": {
     "@langchain/core": ">=0.2.21 <0.3.0",
-    "@langchain/google-gauth": "~0.0.25"
+    "@langchain/google-gauth": "~0.0.27"
   },
   "devDependencies": {
     "@jest/globals": "^29.5.0",
-    "@langchain/google-common": "~0.0",
-    "@langchain/scripts": "~0.0.20",
+    "@langchain/google-common": "^0.0.27",
+    "@langchain/scripts": ">=0.1.0 <0.2.0",
     "@langchain/standard-tests": "0.0.0",
     "@swc/core": "^1.3.90",
     "@swc/jest": "^0.2.29",