import { ChatGoogle, ChatGoogleInput } from "@langchain/google-gauth";

//#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.
 *
 * 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_google_vertexai.index.ChatVertexAI.html#constructor.new_ChatVertexAI)
 *
 * ## [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
 * // When calling `.withConfig`, call options should be passed via the first argument
 * const llmWithArgsBound = llm.withConfig({
 *   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 />
 */
declare class ChatVertexAI extends ChatGoogle {
  lc_namespace: string[];
  static lc_name(): string;
  constructor(model: string, params?: Omit<ChatVertexAIInput, "model">);
  constructor(fields?: ChatVertexAIInput);
}
//#endregion
export { ChatVertexAI, ChatVertexAIInput };
//# sourceMappingURL=chat_models.d.ts.map