@langchain/google-vertexai-web 0.2.17 → 1.0.0

package/dist/chat_models.d.cts

@@ -0,0 +1,301 @@
+import { ChatGoogle, ChatGoogleInput } from "@langchain/google-webauth";
+
+//#region src/chat_models.d.ts
+
+/**
+ * Input to a Google Vertex AI chat model class.
+ */
+interface ChatVertexAIInput extends ChatGoogleInput {}
+/**
+ * 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_google_vertexai_web.index.ChatVertexAI.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 `.withConfig`, or the second arg in `.bindTools`, like shown in the examples below:
+ *
+ * ```typescript
+ * // If binding tools along with other options, chain `.bindTools` and `.withConfig`
+ * const llmWithArgsBound = llm.bindTools([...]) // tools array
+ *   .withConfig({
+ *     stop: ["\n"], // other call options
+ *   });
+ *
+ * // 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 />
+ */
+declare class ChatVertexAI extends ChatGoogle {
+  lc_namespace: string[];
+  static lc_name(): string;
+  constructor(fields?: ChatVertexAIInput);
+}
+//#endregion
+export { ChatVertexAI, ChatVertexAIInput };
+//# sourceMappingURL=chat_models.d.cts.map

package/dist/chat_models.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"chat_models.d.cts","names":["ChatGoogleInput","ChatGoogle","ChatVertexAIInput","ChatVertexAI"],"sources":["../src/chat_models.d.ts"],"sourcesContent":["import { type ChatGoogleInput, ChatGoogle } from \"@langchain/google-webauth\";\n/**\n * Input to a Google Vertex AI chat model class.\n */\nexport interface ChatVertexAIInput extends ChatGoogleInput {\n}\n/**\n * Integration with Google Vertex AI chat models in web environments.\n *\n * Setup:\n * Install `@langchain/google-vertexai-web` and set your stringified\n * Vertex AI credentials as an environment variable named `GOOGLE_VERTEX_AI_WEB_CREDENTIALS`.\n *\n * ```bash\n * npm install @langchain/google-vertexai-web\n * export GOOGLE_VERTEX_AI_WEB_CREDENTIALS={\"type\":\"service_account\",\"project_id\":\"YOUR_PROJECT-12345\",...}\n * ```\n *\n * ## [Constructor args](https://api.js.langchain.com/classes/_langchain_google_vertexai_web.index.ChatVertexAI.html#constructor)\n *\n * ## [Runtime args](https://api.js.langchain.com/interfaces/langchain_google_common_types.GoogleAIBaseLanguageModelCallOptions.html)\n *\n * Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc.\n * They can also be passed via `.withConfig`, or the second arg in `.bindTools`, like shown in the examples below:\n *\n * ```typescript\n * // If binding tools along with other options, chain `.bindTools` and `.withConfig`\n * const llmWithArgsBound = llm.bindTools([...]) // tools array\n *   .withConfig({\n *     stop: [\"\\n\"], // other call options\n *   });\n *\n * // When calling `.bindTools`, call options should be passed via the second argument\n * const llmWithTools = llm.bindTools(\n *   [...],\n *   {\n *     tool_choice: \"auto\",\n *   }\n * );\n * ```\n *\n * ## Examples\n *\n * <details open>\n * <summary><strong>Instantiate</strong></summary>\n *\n * ```typescript\n * import { ChatVertexAI } from '@langchain/google-vertexai-web';\n *\n * const llm = new ChatVertexAI({\n *   model: \"gemini-1.5-pro\",\n *   temperature: 0,\n *   authOptions: {\n *     credentials: process.env.GOOGLE_VERTEX_AI_WEB_CREDENTIALS,\n *   },\n *   // other params...\n * });\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Invoking</strong></summary>\n *\n * ```typescript\n * const input = `Translate \"I love programming\" into French.`;\n *\n * // Models also accept a list of chat messages or a formatted prompt\n * const result = await llm.invoke(input);\n * console.log(result);\n * ```\n *\n * ```txt\n * AIMessageChunk {\n *   \"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\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": [],\n *   \"usage_metadata\": {\n *     \"input_tokens\": 9,\n *     \"output_tokens\": 63,\n *     \"total_tokens\": 72\n *   }\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Streaming Chunks</strong></summary>\n *\n * ```typescript\n * for await (const chunk of await llm.stream(input)) {\n *   console.log(chunk);\n * }\n * ```\n *\n * ```txt\n * AIMessageChunk {\n *   \"content\": \"\\\"\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": []\n * }\n * AIMessageChunk {\n *   \"content\": \"J'adore programmer\\\" \\n\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": []\n * }\n * AIMessageChunk {\n *   \"content\": \"\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": []\n * }\n * AIMessageChunk {\n *   \"content\": \"\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {\n *     \"finishReason\": \"stop\"\n *   },\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": [],\n *   \"usage_metadata\": {\n *     \"input_tokens\": 9,\n *     \"output_tokens\": 8,\n *     \"total_tokens\": 17\n *   }\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Aggregate Streamed Chunks</strong></summary>\n *\n * ```typescript\n * import { AIMessageChunk } from '@langchain/core/messages';\n * import { concat } from '@langchain/core/utils/stream';\n *\n * const stream = await llm.stream(input);\n * let full: AIMessageChunk | undefined;\n * for await (const chunk of stream) {\n *   full = !full ? chunk : concat(full, chunk);\n * }\n * console.log(full);\n * ```\n *\n * ```txt\n * AIMessageChunk {\n *   \"content\": \"\\\"J'adore programmer\\\" \\n\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {\n *     \"finishReason\": \"stop\"\n *   },\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": [],\n *   \"usage_metadata\": {\n *     \"input_tokens\": 9,\n *     \"output_tokens\": 8,\n *     \"total_tokens\": 17\n *   }\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Bind tools</strong></summary>\n *\n * ```typescript\n * import { z } from 'zod';\n *\n * const GetWeather = {\n *   name: \"GetWeather\",\n *   description: \"Get the current weather in a given location\",\n *   schema: z.object({\n *     location: z.string().describe(\"The city and state, e.g. San Francisco, CA\")\n *   }),\n * }\n *\n * const GetPopulation = {\n *   name: \"GetPopulation\",\n *   description: \"Get the current population in a given location\",\n *   schema: z.object({\n *     location: z.string().describe(\"The city and state, e.g. San Francisco, CA\")\n *   }),\n * }\n *\n * const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);\n * const aiMsg = await llmWithTools.invoke(\n *   \"Which city is hotter today and which is bigger: LA or NY?\"\n * );\n * console.log(aiMsg.tool_calls);\n * ```\n *\n * ```txt\n * [\n *   {\n *     name: 'GetPopulation',\n *     args: { location: 'New York City, NY' },\n *     id: '33c1c1f47e2f492799c77d2800a43912',\n *     type: 'tool_call'\n *   }\n * ]\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Structured Output</strong></summary>\n *\n * ```typescript\n * import { z } from 'zod';\n *\n * const Joke = z.object({\n *   setup: z.string().describe(\"The setup of the joke\"),\n *   punchline: z.string().describe(\"The punchline to the joke\"),\n *   rating: z.number().optional().describe(\"How funny the joke is, from 1 to 10\")\n * }).describe('Joke to tell user.');\n *\n * const structuredLlm = llm.withStructuredOutput(Joke, { name: \"Joke\" });\n * const jokeResult = await structuredLlm.invoke(\"Tell me a joke about cats\");\n * console.log(jokeResult);\n * ```\n *\n * ```txt\n * {\n *   setup: 'What do you call a cat that loves to bowl?',\n *   punchline: 'An alley cat!'\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Usage Metadata</strong></summary>\n *\n * ```typescript\n * const aiMsgForMetadata = await llm.invoke(input);\n * console.log(aiMsgForMetadata.usage_metadata);\n * ```\n *\n * ```txt\n * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Stream Usage Metadata</strong></summary>\n *\n * ```typescript\n * const streamForMetadata = await llm.stream(\n *   input,\n *   {\n *     streamUsage: true\n *   }\n * );\n * let fullForMetadata: AIMessageChunk | undefined;\n * for await (const chunk of streamForMetadata) {\n *   fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);\n * }\n * console.log(fullForMetadata?.usage_metadata);\n * ```\n *\n * ```txt\n * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }\n * ```\n * </details>\n *\n * <br />\n */\nexport declare class ChatVertexAI extends ChatGoogle {\n    lc_namespace: string[];\n    static lc_name(): string;\n    constructor(fields?: ChatVertexAIInput);\n}\n"],"mappings":";;;;;;AAIA;AA+RqBG,UA/RJD,iBAAAA,SAA0BF,eA+RV,CAAA;;;AAAmB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cAA/BG,YAAAA,SAAqBF,UAAAA;;;uBAGjBC"}

package/dist/chat_models.d.ts

@@ -1,9 +1,11 @@
-import { type ChatGoogleInput, ChatGoogle } from "@langchain/google-webauth";
+import { ChatGoogle, ChatGoogleInput } from "@langchain/google-webauth";
+
+//#region src/chat_models.d.ts
+
 /**
  * Input to a Google Vertex AI chat model class.
  */
-export interface ChatVertexAIInput extends ChatGoogleInput {
-}
+interface ChatVertexAIInput extends ChatGoogleInput {}
 /**
  * Integration with Google Vertex AI chat models in web environments.
  *
@@ -289,8 +291,11 @@ export interface ChatVertexAIInput extends ChatGoogleInput {
  *
  * <br />
  */
-export declare class ChatVertexAI extends ChatGoogle {
-    lc_namespace: string[];
-    static lc_name(): string;
-    constructor(fields?: ChatVertexAIInput);
+declare class ChatVertexAI extends ChatGoogle {
+  lc_namespace: string[];
+  static lc_name(): string;
+  constructor(fields?: ChatVertexAIInput);
 }
+//#endregion
+export { ChatVertexAI, ChatVertexAIInput };
+//# sourceMappingURL=chat_models.d.ts.map

package/dist/chat_models.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"chat_models.d.ts","names":["ChatGoogleInput","ChatGoogle","ChatVertexAIInput","ChatVertexAI"],"sources":["../src/chat_models.d.ts"],"sourcesContent":["import { type ChatGoogleInput, ChatGoogle } from \"@langchain/google-webauth\";\n/**\n * Input to a Google Vertex AI chat model class.\n */\nexport interface ChatVertexAIInput extends ChatGoogleInput {\n}\n/**\n * Integration with Google Vertex AI chat models in web environments.\n *\n * Setup:\n * Install `@langchain/google-vertexai-web` and set your stringified\n * Vertex AI credentials as an environment variable named `GOOGLE_VERTEX_AI_WEB_CREDENTIALS`.\n *\n * ```bash\n * npm install @langchain/google-vertexai-web\n * export GOOGLE_VERTEX_AI_WEB_CREDENTIALS={\"type\":\"service_account\",\"project_id\":\"YOUR_PROJECT-12345\",...}\n * ```\n *\n * ## [Constructor args](https://api.js.langchain.com/classes/_langchain_google_vertexai_web.index.ChatVertexAI.html#constructor)\n *\n * ## [Runtime args](https://api.js.langchain.com/interfaces/langchain_google_common_types.GoogleAIBaseLanguageModelCallOptions.html)\n *\n * Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc.\n * They can also be passed via `.withConfig`, or the second arg in `.bindTools`, like shown in the examples below:\n *\n * ```typescript\n * // If binding tools along with other options, chain `.bindTools` and `.withConfig`\n * const llmWithArgsBound = llm.bindTools([...]) // tools array\n *   .withConfig({\n *     stop: [\"\\n\"], // other call options\n *   });\n *\n * // When calling `.bindTools`, call options should be passed via the second argument\n * const llmWithTools = llm.bindTools(\n *   [...],\n *   {\n *     tool_choice: \"auto\",\n *   }\n * );\n * ```\n *\n * ## Examples\n *\n * <details open>\n * <summary><strong>Instantiate</strong></summary>\n *\n * ```typescript\n * import { ChatVertexAI } from '@langchain/google-vertexai-web';\n *\n * const llm = new ChatVertexAI({\n *   model: \"gemini-1.5-pro\",\n *   temperature: 0,\n *   authOptions: {\n *     credentials: process.env.GOOGLE_VERTEX_AI_WEB_CREDENTIALS,\n *   },\n *   // other params...\n * });\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Invoking</strong></summary>\n *\n * ```typescript\n * const input = `Translate \"I love programming\" into French.`;\n *\n * // Models also accept a list of chat messages or a formatted prompt\n * const result = await llm.invoke(input);\n * console.log(result);\n * ```\n *\n * ```txt\n * AIMessageChunk {\n *   \"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\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": [],\n *   \"usage_metadata\": {\n *     \"input_tokens\": 9,\n *     \"output_tokens\": 63,\n *     \"total_tokens\": 72\n *   }\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Streaming Chunks</strong></summary>\n *\n * ```typescript\n * for await (const chunk of await llm.stream(input)) {\n *   console.log(chunk);\n * }\n * ```\n *\n * ```txt\n * AIMessageChunk {\n *   \"content\": \"\\\"\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": []\n * }\n * AIMessageChunk {\n *   \"content\": \"J'adore programmer\\\" \\n\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": []\n * }\n * AIMessageChunk {\n *   \"content\": \"\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {},\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": []\n * }\n * AIMessageChunk {\n *   \"content\": \"\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {\n *     \"finishReason\": \"stop\"\n *   },\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": [],\n *   \"usage_metadata\": {\n *     \"input_tokens\": 9,\n *     \"output_tokens\": 8,\n *     \"total_tokens\": 17\n *   }\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Aggregate Streamed Chunks</strong></summary>\n *\n * ```typescript\n * import { AIMessageChunk } from '@langchain/core/messages';\n * import { concat } from '@langchain/core/utils/stream';\n *\n * const stream = await llm.stream(input);\n * let full: AIMessageChunk | undefined;\n * for await (const chunk of stream) {\n *   full = !full ? chunk : concat(full, chunk);\n * }\n * console.log(full);\n * ```\n *\n * ```txt\n * AIMessageChunk {\n *   \"content\": \"\\\"J'adore programmer\\\" \\n\",\n *   \"additional_kwargs\": {},\n *   \"response_metadata\": {\n *     \"finishReason\": \"stop\"\n *   },\n *   \"tool_calls\": [],\n *   \"tool_call_chunks\": [],\n *   \"invalid_tool_calls\": [],\n *   \"usage_metadata\": {\n *     \"input_tokens\": 9,\n *     \"output_tokens\": 8,\n *     \"total_tokens\": 17\n *   }\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Bind tools</strong></summary>\n *\n * ```typescript\n * import { z } from 'zod';\n *\n * const GetWeather = {\n *   name: \"GetWeather\",\n *   description: \"Get the current weather in a given location\",\n *   schema: z.object({\n *     location: z.string().describe(\"The city and state, e.g. San Francisco, CA\")\n *   }),\n * }\n *\n * const GetPopulation = {\n *   name: \"GetPopulation\",\n *   description: \"Get the current population in a given location\",\n *   schema: z.object({\n *     location: z.string().describe(\"The city and state, e.g. San Francisco, CA\")\n *   }),\n * }\n *\n * const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);\n * const aiMsg = await llmWithTools.invoke(\n *   \"Which city is hotter today and which is bigger: LA or NY?\"\n * );\n * console.log(aiMsg.tool_calls);\n * ```\n *\n * ```txt\n * [\n *   {\n *     name: 'GetPopulation',\n *     args: { location: 'New York City, NY' },\n *     id: '33c1c1f47e2f492799c77d2800a43912',\n *     type: 'tool_call'\n *   }\n * ]\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Structured Output</strong></summary>\n *\n * ```typescript\n * import { z } from 'zod';\n *\n * const Joke = z.object({\n *   setup: z.string().describe(\"The setup of the joke\"),\n *   punchline: z.string().describe(\"The punchline to the joke\"),\n *   rating: z.number().optional().describe(\"How funny the joke is, from 1 to 10\")\n * }).describe('Joke to tell user.');\n *\n * const structuredLlm = llm.withStructuredOutput(Joke, { name: \"Joke\" });\n * const jokeResult = await structuredLlm.invoke(\"Tell me a joke about cats\");\n * console.log(jokeResult);\n * ```\n *\n * ```txt\n * {\n *   setup: 'What do you call a cat that loves to bowl?',\n *   punchline: 'An alley cat!'\n * }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Usage Metadata</strong></summary>\n *\n * ```typescript\n * const aiMsgForMetadata = await llm.invoke(input);\n * console.log(aiMsgForMetadata.usage_metadata);\n * ```\n *\n * ```txt\n * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }\n * ```\n * </details>\n *\n * <br />\n *\n * <details>\n * <summary><strong>Stream Usage Metadata</strong></summary>\n *\n * ```typescript\n * const streamForMetadata = await llm.stream(\n *   input,\n *   {\n *     streamUsage: true\n *   }\n * );\n * let fullForMetadata: AIMessageChunk | undefined;\n * for await (const chunk of streamForMetadata) {\n *   fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);\n * }\n * console.log(fullForMetadata?.usage_metadata);\n * ```\n *\n * ```txt\n * { input_tokens: 9, output_tokens: 8, total_tokens: 17 }\n * ```\n * </details>\n *\n * <br />\n */\nexport declare class ChatVertexAI extends ChatGoogle {\n    lc_namespace: string[];\n    static lc_name(): string;\n    constructor(fields?: ChatVertexAIInput);\n}\n"],"mappings":";;;;;;AAIA;AA+RqBG,UA/RJD,iBAAAA,SAA0BF,eA+RV,CAAA;;;AAAmB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cAA/BG,YAAAA,SAAqBF,UAAAA;;;uBAGjBC"}