@langchain/google-vertexai-web 2.1.25 → 2.1.26-dev-1773698445534

package/dist/chat_models.cjs

@@ -1,5 +1,4 @@
 let _langchain_google_webauth = require("@langchain/google-webauth");
-
 //#region src/chat_models.ts
 /**
 * Integration with Google Vertex AI chat models in web environments.
@@ -304,10 +303,10 @@ var ChatVertexAI = class extends _langchain_google_webauth.ChatGoogle {
 			...fields,
 			platformType: "gcp"
 		});
-		this._addVersion("@langchain/google-vertexai-web", "2.1.25");
+		this._addVersion("@langchain/google-vertexai-web", "2.1.26-dev-1773698445534");
 	}
 };
-
 //#endregion
 exports.ChatVertexAI = ChatVertexAI;
+
 //# sourceMappingURL=chat_models.cjs.map

package/dist/chat_models.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"chat_models.cjs","names":["ChatGoogle"],"sources":["../src/chat_models.ts"],"sourcesContent":["import { type ChatGoogleInput, ChatGoogle } from \"@langchain/google-webauth\";\n\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 class ChatVertexAI extends ChatGoogle {\n  lc_namespace = [\"langchain\", \"chat_models\", \"vertexai\"];\n\n  static lc_name() {\n    return \"ChatVertexAI\";\n  }\n\n  constructor(model: string, fields?: Omit<ChatVertexAIInput, \"model\">);\n  constructor(fields?: ChatVertexAIInput);\n  constructor(\n    modelOrFields?: string | ChatVertexAIInput,\n    fieldsArg?: Omit<ChatVertexAIInput, \"model\">\n  ) {\n    const fields =\n      typeof modelOrFields === \"string\"\n        ? { ...(fieldsArg ?? {}), model: modelOrFields }\n        : (modelOrFields ?? {});\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAoSA,IAAa,eAAb,cAAkCA,qCAAW;CAC3C,eAAe;EAAC;EAAa;EAAe;EAAW;CAEvD,OAAO,UAAU;AACf,SAAO;;CAKT,YACE,eACA,WACA;EACA,MAAM,SACJ,OAAO,kBAAkB,WACrB;GAAE,GAAI,aAAa,EAAE;GAAG,OAAO;GAAe,GAC7C,iBAAiB,EAAE;AAC1B,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,2CAAkD"}
+{"version":3,"file":"chat_models.cjs","names":["ChatGoogle"],"sources":["../src/chat_models.ts"],"sourcesContent":["import { type ChatGoogleInput, ChatGoogle } from \"@langchain/google-webauth\";\n\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 class ChatVertexAI extends ChatGoogle {\n  lc_namespace = [\"langchain\", \"chat_models\", \"vertexai\"];\n\n  static lc_name() {\n    return \"ChatVertexAI\";\n  }\n\n  constructor(model: string, fields?: Omit<ChatVertexAIInput, \"model\">);\n  constructor(fields?: ChatVertexAIInput);\n  constructor(\n    modelOrFields?: string | ChatVertexAIInput,\n    fieldsArg?: Omit<ChatVertexAIInput, \"model\">\n  ) {\n    const fields =\n      typeof modelOrFields === \"string\"\n        ? { ...(fieldsArg ?? {}), model: modelOrFields }\n        : (modelOrFields ?? {});\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAoSA,IAAa,eAAb,cAAkCA,0BAAAA,WAAW;CAC3C,eAAe;EAAC;EAAa;EAAe;EAAW;CAEvD,OAAO,UAAU;AACf,SAAO;;CAKT,YACE,eACA,WACA;EACA,MAAM,SACJ,OAAO,kBAAkB,WACrB;GAAE,GAAI,aAAa,EAAE;GAAG,OAAO;GAAe,GAC7C,iBAAiB,EAAE;AAC1B,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,kCAAA,2BAAkD"}

package/dist/chat_models.js

@@ -1,5 +1,4 @@
 import { ChatGoogle } from "@langchain/google-webauth";
-
 //#region src/chat_models.ts
 /**
 * Integration with Google Vertex AI chat models in web environments.
@@ -304,10 +303,10 @@ var ChatVertexAI = class extends ChatGoogle {
 			...fields,
 			platformType: "gcp"
 		});
-		this._addVersion("@langchain/google-vertexai-web", "2.1.25");
+		this._addVersion("@langchain/google-vertexai-web", "2.1.26-dev-1773698445534");
 	}
 };
-
 //#endregion
 export { ChatVertexAI };
+
 //# sourceMappingURL=chat_models.js.map

package/dist/chat_models.js.map

@@ -1 +1 @@
-{"version":3,"file":"chat_models.js","names":[],"sources":["../src/chat_models.ts"],"sourcesContent":["import { type ChatGoogleInput, ChatGoogle } from \"@langchain/google-webauth\";\n\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 class ChatVertexAI extends ChatGoogle {\n  lc_namespace = [\"langchain\", \"chat_models\", \"vertexai\"];\n\n  static lc_name() {\n    return \"ChatVertexAI\";\n  }\n\n  constructor(model: string, fields?: Omit<ChatVertexAIInput, \"model\">);\n  constructor(fields?: ChatVertexAIInput);\n  constructor(\n    modelOrFields?: string | ChatVertexAIInput,\n    fieldsArg?: Omit<ChatVertexAIInput, \"model\">\n  ) {\n    const fields =\n      typeof modelOrFields === \"string\"\n        ? { ...(fieldsArg ?? {}), model: modelOrFields }\n        : (modelOrFields ?? {});\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAoSA,IAAa,eAAb,cAAkC,WAAW;CAC3C,eAAe;EAAC;EAAa;EAAe;EAAW;CAEvD,OAAO,UAAU;AACf,SAAO;;CAKT,YACE,eACA,WACA;EACA,MAAM,SACJ,OAAO,kBAAkB,WACrB;GAAE,GAAI,aAAa,EAAE;GAAG,OAAO;GAAe,GAC7C,iBAAiB,EAAE;AAC1B,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,2CAAkD"}
+{"version":3,"file":"chat_models.js","names":[],"sources":["../src/chat_models.ts"],"sourcesContent":["import { type ChatGoogleInput, ChatGoogle } from \"@langchain/google-webauth\";\n\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 class ChatVertexAI extends ChatGoogle {\n  lc_namespace = [\"langchain\", \"chat_models\", \"vertexai\"];\n\n  static lc_name() {\n    return \"ChatVertexAI\";\n  }\n\n  constructor(model: string, fields?: Omit<ChatVertexAIInput, \"model\">);\n  constructor(fields?: ChatVertexAIInput);\n  constructor(\n    modelOrFields?: string | ChatVertexAIInput,\n    fieldsArg?: Omit<ChatVertexAIInput, \"model\">\n  ) {\n    const fields =\n      typeof modelOrFields === \"string\"\n        ? { ...(fieldsArg ?? {}), model: modelOrFields }\n        : (modelOrFields ?? {});\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAoSA,IAAa,eAAb,cAAkC,WAAW;CAC3C,eAAe;EAAC;EAAa;EAAe;EAAW;CAEvD,OAAO,UAAU;AACf,SAAO;;CAKT,YACE,eACA,WACA;EACA,MAAM,SACJ,OAAO,kBAAkB,WACrB;GAAE,GAAI,aAAa,EAAE;GAAG,OAAO;GAAe,GAC7C,iBAAiB,EAAE;AAC1B,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,kCAAA,2BAAkD"}

package/dist/embeddings.cjs

@@ -1,5 +1,4 @@
 let _langchain_google_webauth = require("@langchain/google-webauth");
-
 //#region src/embeddings.ts
 /**
 * Integration with a Google Vertex AI embeddings model using
@@ -16,7 +15,7 @@ var VertexAIEmbeddings = class extends _langchain_google_webauth.GoogleEmbedding
 		});
 	}
 };
-
 //#endregion
 exports.VertexAIEmbeddings = VertexAIEmbeddings;
+
 //# sourceMappingURL=embeddings.cjs.map

package/dist/embeddings.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"embeddings.cjs","names":["GoogleEmbeddings"],"sources":["../src/embeddings.ts"],"sourcesContent":["import {\n  type GoogleEmbeddingsInput,\n  GoogleEmbeddings,\n} from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex AI embeddings class.\n */\nexport interface GoogleVertexAIEmbeddingsInput extends GoogleEmbeddingsInput {}\n\n/**\n * Integration with a Google Vertex AI embeddings model using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAIEmbeddings extends GoogleEmbeddings {\n  static lc_name() {\n    return \"VertexAIEmbeddings\";\n  }\n\n  constructor(fields: GoogleVertexAIEmbeddingsInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n  }\n}\n"],"mappings":";;;;;;;AAcA,IAAa,qBAAb,cAAwCA,2CAAiB;CACvD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAuC;AACjD,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC"}
+{"version":3,"file":"embeddings.cjs","names":["GoogleEmbeddings"],"sources":["../src/embeddings.ts"],"sourcesContent":["import {\n  type GoogleEmbeddingsInput,\n  GoogleEmbeddings,\n} from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex AI embeddings class.\n */\nexport interface GoogleVertexAIEmbeddingsInput extends GoogleEmbeddingsInput {}\n\n/**\n * Integration with a Google Vertex AI embeddings model using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAIEmbeddings extends GoogleEmbeddings {\n  static lc_name() {\n    return \"VertexAIEmbeddings\";\n  }\n\n  constructor(fields: GoogleVertexAIEmbeddingsInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n  }\n}\n"],"mappings":";;;;;;AAcA,IAAa,qBAAb,cAAwCA,0BAAAA,iBAAiB;CACvD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAuC;AACjD,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC"}

package/dist/embeddings.js

@@ -1,5 +1,4 @@
 import { GoogleEmbeddings } from "@langchain/google-webauth";
-
 //#region src/embeddings.ts
 /**
 * Integration with a Google Vertex AI embeddings model using
@@ -16,7 +15,7 @@ var VertexAIEmbeddings = class extends GoogleEmbeddings {
 		});
 	}
 };
-
 //#endregion
 export { VertexAIEmbeddings };
+
 //# sourceMappingURL=embeddings.js.map

package/dist/embeddings.js.map

@@ -1 +1 @@
-{"version":3,"file":"embeddings.js","names":[],"sources":["../src/embeddings.ts"],"sourcesContent":["import {\n  type GoogleEmbeddingsInput,\n  GoogleEmbeddings,\n} from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex AI embeddings class.\n */\nexport interface GoogleVertexAIEmbeddingsInput extends GoogleEmbeddingsInput {}\n\n/**\n * Integration with a Google Vertex AI embeddings model using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAIEmbeddings extends GoogleEmbeddings {\n  static lc_name() {\n    return \"VertexAIEmbeddings\";\n  }\n\n  constructor(fields: GoogleVertexAIEmbeddingsInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n  }\n}\n"],"mappings":";;;;;;;AAcA,IAAa,qBAAb,cAAwC,iBAAiB;CACvD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAuC;AACjD,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC"}
+{"version":3,"file":"embeddings.js","names":[],"sources":["../src/embeddings.ts"],"sourcesContent":["import {\n  type GoogleEmbeddingsInput,\n  GoogleEmbeddings,\n} from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex AI embeddings class.\n */\nexport interface GoogleVertexAIEmbeddingsInput extends GoogleEmbeddingsInput {}\n\n/**\n * Integration with a Google Vertex AI embeddings model using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAIEmbeddings extends GoogleEmbeddings {\n  static lc_name() {\n    return \"VertexAIEmbeddings\";\n  }\n\n  constructor(fields: GoogleVertexAIEmbeddingsInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n  }\n}\n"],"mappings":";;;;;;AAcA,IAAa,qBAAb,cAAwC,iBAAiB;CACvD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAuC;AACjD,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC"}

package/dist/index.cjs

@@ -1,8 +1,7 @@
-Object.defineProperty(exports, Symbol.toStringTag, { value: 'Module' });
-const require_chat_models = require('./chat_models.cjs');
-const require_llms = require('./llms.cjs');
-const require_embeddings = require('./embeddings.cjs');
-
+Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
+const require_chat_models = require("./chat_models.cjs");
+const require_llms = require("./llms.cjs");
+const require_embeddings = require("./embeddings.cjs");
 exports.ChatVertexAI = require_chat_models.ChatVertexAI;
 exports.VertexAI = require_llms.VertexAI;
-exports.VertexAIEmbeddings = require_embeddings.VertexAIEmbeddings;
+exports.VertexAIEmbeddings = require_embeddings.VertexAIEmbeddings;

package/dist/index.js

@@ -1,5 +1,4 @@
 import { ChatVertexAI } from "./chat_models.js";
 import { VertexAI } from "./llms.js";
 import { VertexAIEmbeddings } from "./embeddings.js";
-
-export { ChatVertexAI, VertexAI, VertexAIEmbeddings };
+export { ChatVertexAI, VertexAI, VertexAIEmbeddings };

package/dist/llms.cjs

@@ -1,5 +1,4 @@
 let _langchain_google_webauth = require("@langchain/google-webauth");
-
 //#region src/llms.ts
 /**
 * Integration with a Google Vertex AI LLM using
@@ -19,10 +18,10 @@ var VertexAI = class extends _langchain_google_webauth.GoogleLLM {
 			...fields,
 			platformType: "gcp"
 		});
-		this._addVersion("@langchain/google-vertexai-web", "2.1.25");
+		this._addVersion("@langchain/google-vertexai-web", "2.1.26-dev-1773698445534");
 	}
 };
-
 //#endregion
 exports.VertexAI = VertexAI;
+
 //# sourceMappingURL=llms.cjs.map

package/dist/llms.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"llms.cjs","names":["GoogleLLM"],"sources":["../src/llms.ts"],"sourcesContent":["import { type GoogleLLMInput, GoogleLLM } from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex LLM class.\n */\nexport interface VertexAIInput extends GoogleLLMInput {}\n\n/**\n * Integration with a Google Vertex AI LLM using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAI extends GoogleLLM {\n  lc_namespace = [\"langchain\", \"llms\", \"vertexai\"];\n\n  static lc_name() {\n    return \"VertexAI\";\n  }\n\n  constructor(fields?: VertexAIInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;;AAWA,IAAa,WAAb,cAA8BA,oCAAU;CACtC,eAAe;EAAC;EAAa;EAAQ;EAAW;CAEhD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAwB;AAClC,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,2CAAkD"}
+{"version":3,"file":"llms.cjs","names":["GoogleLLM"],"sources":["../src/llms.ts"],"sourcesContent":["import { type GoogleLLMInput, GoogleLLM } from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex LLM class.\n */\nexport interface VertexAIInput extends GoogleLLMInput {}\n\n/**\n * Integration with a Google Vertex AI LLM using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAI extends GoogleLLM {\n  lc_namespace = [\"langchain\", \"llms\", \"vertexai\"];\n\n  static lc_name() {\n    return \"VertexAI\";\n  }\n\n  constructor(fields?: VertexAIInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;AAWA,IAAa,WAAb,cAA8BA,0BAAAA,UAAU;CACtC,eAAe;EAAC;EAAa;EAAQ;EAAW;CAEhD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAwB;AAClC,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,kCAAA,2BAAkD"}

package/dist/llms.js

@@ -1,5 +1,4 @@
 import { GoogleLLM } from "@langchain/google-webauth";
-
 //#region src/llms.ts
 /**
 * Integration with a Google Vertex AI LLM using
@@ -19,10 +18,10 @@ var VertexAI = class extends GoogleLLM {
 			...fields,
 			platformType: "gcp"
 		});
-		this._addVersion("@langchain/google-vertexai-web", "2.1.25");
+		this._addVersion("@langchain/google-vertexai-web", "2.1.26-dev-1773698445534");
 	}
 };
-
 //#endregion
 export { VertexAI };
+
 //# sourceMappingURL=llms.js.map

package/dist/llms.js.map

@@ -1 +1 @@
-{"version":3,"file":"llms.js","names":[],"sources":["../src/llms.ts"],"sourcesContent":["import { type GoogleLLMInput, GoogleLLM } from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex LLM class.\n */\nexport interface VertexAIInput extends GoogleLLMInput {}\n\n/**\n * Integration with a Google Vertex AI LLM using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAI extends GoogleLLM {\n  lc_namespace = [\"langchain\", \"llms\", \"vertexai\"];\n\n  static lc_name() {\n    return \"VertexAI\";\n  }\n\n  constructor(fields?: VertexAIInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;;AAWA,IAAa,WAAb,cAA8B,UAAU;CACtC,eAAe;EAAC;EAAa;EAAQ;EAAW;CAEhD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAwB;AAClC,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,2CAAkD"}
+{"version":3,"file":"llms.js","names":[],"sources":["../src/llms.ts"],"sourcesContent":["import { type GoogleLLMInput, GoogleLLM } from \"@langchain/google-webauth\";\n\n/**\n * Input to a Google Vertex LLM class.\n */\nexport interface VertexAIInput extends GoogleLLMInput {}\n\n/**\n * Integration with a Google Vertex AI LLM using\n * the \"@langchain/google-webauth\" package for auth.\n */\nexport class VertexAI extends GoogleLLM {\n  lc_namespace = [\"langchain\", \"llms\", \"vertexai\"];\n\n  static lc_name() {\n    return \"VertexAI\";\n  }\n\n  constructor(fields?: VertexAIInput) {\n    super({\n      ...fields,\n      platformType: \"gcp\",\n    });\n    this._addVersion(\"@langchain/google-vertexai-web\", __PKG_VERSION__);\n  }\n}\n"],"mappings":";;;;;;AAWA,IAAa,WAAb,cAA8B,UAAU;CACtC,eAAe;EAAC;EAAa;EAAQ;EAAW;CAEhD,OAAO,UAAU;AACf,SAAO;;CAGT,YAAY,QAAwB;AAClC,QAAM;GACJ,GAAG;GACH,cAAc;GACf,CAAC;AACF,OAAK,YAAY,kCAAA,2BAAkD"}

package/dist/types.cjs

@@ -1,9 +1,9 @@
-
-
 var _langchain_google_webauth_types = require("@langchain/google-webauth/types");
-Object.keys(_langchain_google_webauth_types).forEach(function (k) {
-  if (k !== 'default' && !Object.prototype.hasOwnProperty.call(exports, k)) Object.defineProperty(exports, k, {
-    enumerable: true,
-    get: function () { return _langchain_google_webauth_types[k]; }
-  });
+Object.keys(_langchain_google_webauth_types).forEach(function(k) {
+	if (k !== "default" && !Object.prototype.hasOwnProperty.call(exports, k)) Object.defineProperty(exports, k, {
+		enumerable: true,
+		get: function() {
+			return _langchain_google_webauth_types[k];
+		}
+	});
 });

package/dist/types.js

@@ -1,3 +1,2 @@
-export * from "@langchain/google-webauth/types"
-
-export {  };
+export * from "@langchain/google-webauth/types";
+export {};

package/dist/utils.cjs

@@ -1,9 +1,9 @@
-
-
 var _langchain_google_webauth_utils = require("@langchain/google-webauth/utils");
-Object.keys(_langchain_google_webauth_utils).forEach(function (k) {
-  if (k !== 'default' && !Object.prototype.hasOwnProperty.call(exports, k)) Object.defineProperty(exports, k, {
-    enumerable: true,
-    get: function () { return _langchain_google_webauth_utils[k]; }
-  });
+Object.keys(_langchain_google_webauth_utils).forEach(function(k) {
+	if (k !== "default" && !Object.prototype.hasOwnProperty.call(exports, k)) Object.defineProperty(exports, k, {
+		enumerable: true,
+		get: function() {
+			return _langchain_google_webauth_utils[k];
+		}
+	});
 });

package/dist/utils.js

@@ -1,3 +1,2 @@
-export * from "@langchain/google-webauth/utils"
-
-export {  };
+export * from "@langchain/google-webauth/utils";
+export {};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@langchain/google-vertexai-web",
-  "version": "2.1.25",
+  "version": "2.1.26-dev-1773698445534",
   "description": "LangChain.js support for Google Vertex AI Web",
   "author": "LangChain",
   "license": "MIT",
@@ -14,26 +14,21 @@
   },
   "homepage": "https://github.com/langchain-ai/langchainjs/tree/main/libs/providers/langchain-google-vertexai-web/",
   "dependencies": {
-    "@langchain/google-webauth": "2.1.25"
+    "@langchain/google-webauth": "2.1.26-dev-1773698445534"
   },
   "devDependencies": {
-    "@jest/globals": "^30.2.0",
-    "@swc/core": "^1.15.18",
-    "@swc/jest": "^0.2.29",
     "@tsconfig/recommended": "^1.0.3",
     "dotenv": "^16.3.1",
     "dpdm": "^3.14.0",
     "eslint": "^9.34.0",
-    "jest": "^30.2.0",
-    "jest-environment-node": "^30.2.0",
     "prettier": "^3.5.0",
-    "ts-jest": "^29.4.6",
     "typescript": "~5.8.3",
+    "vitest": "^3.2.4",
     "zod": "^3.25.76",
-    "@langchain/eslint": "0.1.1",
-    "@langchain/google-common": "2.1.25",
     "@langchain/standard-tests": "0.0.23",
-    "@langchain/tsconfig": "0.0.1"
+    "@langchain/tsconfig": "0.0.1",
+    "@langchain/google-common": "2.1.26-dev-1773698445534",
+    "@langchain/eslint": "0.1.1"
   },
   "publishConfig": {
     "access": "public"
@@ -91,10 +86,10 @@
     "lint": "pnpm lint:eslint && pnpm lint:dpdm",
     "lint:fix": "pnpm lint:eslint --fix && pnpm lint:dpdm",
     "clean": "rm -rf .turbo dist/",
-    "test": "NODE_OPTIONS=--experimental-vm-modules jest --testPathIgnorePatterns=\\.int\\.test.ts --testTimeout 30000 --maxWorkers=50%",
-    "test:watch": "NODE_OPTIONS=--experimental-vm-modules jest --watch --testPathIgnorePatterns=\\.int\\.test.ts",
-    "test:single": "NODE_OPTIONS=--experimental-vm-modules pnpm run jest --config jest.config.cjs --testTimeout 100000",
-    "test:int": "NODE_OPTIONS=--experimental-vm-modules jest --testPathPatterns=\\.int\\.test.ts --testTimeout 100000 --maxWorkers=50%",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "test:single": "vitest run",
+    "test:int": "vitest run --mode int",
     "format": "prettier --write \"src\"",
     "format:check": "prettier --check \"src\""
   }