@langchain/google-vertexai-web 0.0.22 → 0.0.26

package/dist/chat_models.cjs

@@ -3,7 +3,289 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.ChatVertexAI = void 0;
 const google_webauth_1 = require("@langchain/google-webauth");
 /**
- * Integration with a chat model.
+ * Integration with Google Vertex AI chat models in web environments.
+ *
+ * Setup:
+ * Install `@langchain/google-vertexai-web` and set your stringified
+ * Vertex AI credentials as an environment variable named `GOOGLE_VERTEX_AI_WEB_CREDENTIALS`.
+ *
+ * ```bash
+ * npm install @langchain/google-vertexai-web
+ * export GOOGLE_VERTEX_AI_WEB_CREDENTIALS={"type":"service_account","project_id":"YOUR_PROJECT-12345",...}
+ * ```
+ *
+ * ## [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-web';
+ *
+ * const llm = new ChatVertexAI({
+ *   model: "gemini-1.5-pro",
+ *   temperature: 0,
+ *   authOptions: {
+ *     credentials: process.env.GOOGLE_VERTEX_AI_WEB_CREDENTIALS,
+ *   },
+ *   // 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_webauth_1.ChatGoogle {
     static lc_name() {

package/dist/chat_models.d.ts

@@ -1,11 +1,293 @@
 import { type ChatGoogleInput, ChatGoogle } from "@langchain/google-webauth";
 /**
- * Input to chat model class.
+ * Input to a Google Vertex AI chat model class.
  */
 export interface ChatVertexAIInput extends ChatGoogleInput {
 }
 /**
- * Integration with a chat model.
+ * Integration with Google Vertex AI chat models in web environments.
+ *
+ * Setup:
+ * Install `@langchain/google-vertexai-web` and set your stringified
+ * Vertex AI credentials as an environment variable named `GOOGLE_VERTEX_AI_WEB_CREDENTIALS`.
+ *
+ * ```bash
+ * npm install @langchain/google-vertexai-web
+ * export GOOGLE_VERTEX_AI_WEB_CREDENTIALS={"type":"service_account","project_id":"YOUR_PROJECT-12345",...}
+ * ```
+ *
+ * ## [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-web';
+ *
+ * const llm = new ChatVertexAI({
+ *   model: "gemini-1.5-pro",
+ *   temperature: 0,
+ *   authOptions: {
+ *     credentials: process.env.GOOGLE_VERTEX_AI_WEB_CREDENTIALS,
+ *   },
+ *   // 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

@@ -1,6 +1,288 @@
 import { ChatGoogle } from "@langchain/google-webauth";
 /**
- * Integration with a chat model.
+ * Integration with Google Vertex AI chat models in web environments.
+ *
+ * Setup:
+ * Install `@langchain/google-vertexai-web` and set your stringified
+ * Vertex AI credentials as an environment variable named `GOOGLE_VERTEX_AI_WEB_CREDENTIALS`.
+ *
+ * ```bash
+ * npm install @langchain/google-vertexai-web
+ * export GOOGLE_VERTEX_AI_WEB_CREDENTIALS={"type":"service_account","project_id":"YOUR_PROJECT-12345",...}
+ * ```
+ *
+ * ## [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-web';
+ *
+ * const llm = new ChatVertexAI({
+ *   model: "gemini-1.5-pro",
+ *   temperature: 0,
+ *   authOptions: {
+ *     credentials: process.env.GOOGLE_VERTEX_AI_WEB_CREDENTIALS,
+ *   },
+ *   // 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/dist/embeddings.cjs

@@ -0,0 +1,20 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.VertexAIEmbeddings = void 0;
+const google_webauth_1 = require("@langchain/google-webauth");
+/**
+ * Integration with a Google Vertex AI embeddings model using
+ * the "@langchain/google-webauth" package for auth.
+ */
+class VertexAIEmbeddings extends google_webauth_1.GoogleEmbeddings {
+    static lc_name() {
+        return "VertexAIEmbeddings";
+    }
+    constructor(fields) {
+        super({
+            ...fields,
+            platformType: "gcp",
+        });
+    }
+}
+exports.VertexAIEmbeddings = VertexAIEmbeddings;

package/dist/embeddings.d.ts

@@ -0,0 +1,14 @@
+import { type GoogleEmbeddingsInput, GoogleEmbeddings } from "@langchain/google-webauth";
+/**
+ * Input to a Google Vertex AI embeddings class.
+ */
+export interface GoogleVertexAIEmbeddingsInput extends GoogleEmbeddingsInput {
+}
+/**
+ * Integration with a Google Vertex AI embeddings model using
+ * the "@langchain/google-webauth" package for auth.
+ */
+export declare class VertexAIEmbeddings extends GoogleEmbeddings {
+    static lc_name(): string;
+    constructor(fields: GoogleVertexAIEmbeddingsInput);
+}

package/dist/embeddings.js

@@ -0,0 +1,16 @@
+import { GoogleEmbeddings, } from "@langchain/google-webauth";
+/**
+ * Integration with a Google Vertex AI embeddings model using
+ * the "@langchain/google-webauth" package for auth.
+ */
+export class VertexAIEmbeddings extends GoogleEmbeddings {
+    static lc_name() {
+        return "VertexAIEmbeddings";
+    }
+    constructor(fields) {
+        super({
+            ...fields,
+            platformType: "gcp",
+        });
+    }
+}

package/dist/index.cjs

@@ -16,3 +16,4 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./chat_models.cjs"), exports);
 __exportStar(require("./llms.cjs"), exports);
+__exportStar(require("./embeddings.cjs"), exports);

package/dist/index.d.ts

@@ -1,2 +1,3 @@
 export * from "./chat_models.js";
 export * from "./llms.js";
+export * from "./embeddings.js";

package/dist/index.js

@@ -1,2 +1,3 @@
 export * from "./chat_models.js";
 export * from "./llms.js";
+export * from "./embeddings.js";

package/dist/llms.cjs

@@ -3,7 +3,8 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.VertexAI = void 0;
 const google_webauth_1 = require("@langchain/google-webauth");
 /**
- * Integration with a LLM model.
+ * Integration with a Google Vertex AI LLM using
+ * the "@langchain/google-webauth" package for auth.
  */
 class VertexAI extends google_webauth_1.GoogleLLM {
     static lc_name() {

package/dist/llms.d.ts

@@ -1,11 +1,12 @@
 import { type GoogleLLMInput, GoogleLLM } from "@langchain/google-webauth";
 /**
- * Input to LLM model class.
+ * Input to a Google Vertex LLM class.
  */
 export interface VertexAIInput extends GoogleLLMInput {
 }
 /**
- * Integration with a LLM model.
+ * Integration with a Google Vertex AI LLM using
+ * the "@langchain/google-webauth" package for auth.
  */
 export declare class VertexAI extends GoogleLLM {
     static lc_name(): string;

package/dist/llms.js

@@ -1,6 +1,7 @@
 import { GoogleLLM } from "@langchain/google-webauth";
 /**
- * Integration with a LLM model.
+ * Integration with a Google Vertex AI LLM using
+ * the "@langchain/google-webauth" package for auth.
  */
 export class VertexAI extends GoogleLLM {
     static lc_name() {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@langchain/google-vertexai-web",
-  "version": "0.0.22",
+  "version": "0.0.26",
   "description": "LangChain.js support for Google Vertex AI Web",
   "type": "module",
   "engines": {
@@ -41,7 +41,7 @@
   "license": "MIT",
   "dependencies": {
     "@langchain/core": ">=0.2.21 <0.3.0",
-    "@langchain/google-webauth": "~0.0.22"
+    "@langchain/google-webauth": "~0.0.26"
   },
   "devDependencies": {
     "@jest/globals": "^29.5.0",