@librechat/agents 2.4.43 → 2.4.44

package/dist/cjs/llm/providers.cjs

@@ -3,12 +3,12 @@
 var ollama = require('@langchain/ollama');
 var mistralai = require('@langchain/mistralai');
 var aws = require('@langchain/aws');
-var googleVertexai = require('@langchain/google-vertexai');
 var web = require('@langchain/community/chat_models/bedrock/web');
+var index$3 = require('./openai/index.cjs');
 var index = require('./google/index.cjs');
 var index$2 = require('./anthropic/index.cjs');
 var index$1 = require('./openrouter/index.cjs');
-var index$3 = require('./openai/index.cjs');
+var index$4 = require('./vertexai/index.cjs');
 var _enum = require('../common/enum.cjs');
 
 // src/llm/providers.ts
@@ -17,7 +17,7 @@ const llmProviders = {
     [_enum.Providers.OPENAI]: index$3.ChatOpenAI,
     [_enum.Providers.OLLAMA]: ollama.ChatOllama,
     [_enum.Providers.AZURE]: index$3.AzureChatOpenAI,
-    [_enum.Providers.VERTEXAI]: googleVertexai.ChatVertexAI,
+    [_enum.Providers.VERTEXAI]: index$4.ChatVertexAI,
     [_enum.Providers.DEEPSEEK]: index$3.ChatDeepSeek,
     [_enum.Providers.MISTRALAI]: mistralai.ChatMistralAI,
     [_enum.Providers.MISTRAL]: mistralai.ChatMistralAI,

package/dist/cjs/llm/providers.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"providers.cjs","sources":["../../../src/llm/providers.ts"],"sourcesContent":["// src/llm/providers.ts\nimport { ChatOllama } from '@langchain/ollama';\nimport { ChatMistralAI } from '@langchain/mistralai';\nimport { ChatBedrockConverse } from '@langchain/aws';\n// import { ChatAnthropic } from '@langchain/anthropic';\nimport { ChatVertexAI } from '@langchain/google-vertexai';\nimport { BedrockChat } from '@langchain/community/chat_models/bedrock/web';\nimport type {\n  ChatModelConstructorMap,\n  ProviderOptionsMap,\n  ChatModelMap,\n} from '@/types';\nimport { CustomChatGoogleGenerativeAI } from '@/llm/google';\nimport { CustomAnthropic } from '@/llm/anthropic';\nimport { ChatOpenRouter } from '@/llm/openrouter';\nimport {\n  ChatXAI,\n  ChatOpenAI,\n  ChatDeepSeek,\n  AzureChatOpenAI,\n} from '@/llm/openai';\nimport { Providers } from '@/common';\n\nexport const llmProviders: Partial<ChatModelConstructorMap> = {\n  [Providers.XAI]: ChatXAI,\n  [Providers.OPENAI]: ChatOpenAI,\n  [Providers.OLLAMA]: ChatOllama,\n  [Providers.AZURE]: AzureChatOpenAI,\n  [Providers.VERTEXAI]: ChatVertexAI,\n  [Providers.DEEPSEEK]: ChatDeepSeek,\n  [Providers.MISTRALAI]: ChatMistralAI,\n  [Providers.MISTRAL]: ChatMistralAI,\n  [Providers.ANTHROPIC]: CustomAnthropic,\n  [Providers.OPENROUTER]: ChatOpenRouter,\n  [Providers.BEDROCK_LEGACY]: BedrockChat,\n  [Providers.BEDROCK]: ChatBedrockConverse,\n  // [Providers.ANTHROPIC]: ChatAnthropic,\n  [Providers.GOOGLE]: CustomChatGoogleGenerativeAI,\n};\n\nexport const manualToolStreamProviders = new Set<Providers | string>([\n  Providers.ANTHROPIC,\n  Providers.BEDROCK,\n  Providers.OLLAMA,\n]);\n\nexport const getChatModelClass = <P extends Providers>(\n  provider: P\n): new (config: ProviderOptionsMap[P]) => ChatModelMap[P] => {\n  const ChatModelClass = llmProviders[provider];\n  if (!ChatModelClass) {\n    throw new Error(`Unsupported LLM provider: ${provider}`);\n  }\n\n  return ChatModelClass;\n};\n"],"names":["Providers","ChatXAI","ChatOpenAI","ChatOllama","AzureChatOpenAI","ChatVertexAI","ChatDeepSeek","ChatMistralAI","CustomAnthropic","ChatOpenRouter","BedrockChat","ChatBedrockConverse","CustomChatGoogleGenerativeAI"],"mappings":";;;;;;;;;;;;;AAAA;AAuBa,MAAA,YAAY,GAAqC;AAC5D,IAAA,CAACA,eAAS,CAAC,GAAG,GAAGC,eAAO;AACxB,IAAA,CAACD,eAAS,CAAC,MAAM,GAAGE,kBAAU;AAC9B,IAAA,CAACF,eAAS,CAAC,MAAM,GAAGG,iBAAU;AAC9B,IAAA,CAACH,eAAS,CAAC,KAAK,GAAGI,uBAAe;AAClC,IAAA,CAACJ,eAAS,CAAC,QAAQ,GAAGK,2BAAY;AAClC,IAAA,CAACL,eAAS,CAAC,QAAQ,GAAGM,oBAAY;AAClC,IAAA,CAACN,eAAS,CAAC,SAAS,GAAGO,uBAAa;AACpC,IAAA,CAACP,eAAS,CAAC,OAAO,GAAGO,uBAAa;AAClC,IAAA,CAACP,eAAS,CAAC,SAAS,GAAGQ,uBAAe;AACtC,IAAA,CAACR,eAAS,CAAC,UAAU,GAAGS,sBAAc;AACtC,IAAA,CAACT,eAAS,CAAC,cAAc,GAAGU,eAAW;AACvC,IAAA,CAACV,eAAS,CAAC,OAAO,GAAGW,uBAAmB;;AAExC,IAAA,CAACX,eAAS,CAAC,MAAM,GAAGY,kCAA4B;;AAGrC,MAAA,yBAAyB,GAAG,IAAI,GAAG,CAAqB;AACnE,IAAAZ,eAAS,CAAC,SAAS;AACnB,IAAAA,eAAS,CAAC,OAAO;AACjB,IAAAA,eAAS,CAAC,MAAM;AACjB,CAAA;AAEY,MAAA,iBAAiB,GAAG,CAC/B,QAAW,KAC+C;AAC1D,IAAA,MAAM,cAAc,GAAG,YAAY,CAAC,QAAQ,CAAC;IAC7C,IAAI,CAAC,cAAc,EAAE;AACnB,QAAA,MAAM,IAAI,KAAK,CAAC,6BAA6B,QAAQ,CAAA,CAAE,CAAC;;AAG1D,IAAA,OAAO,cAAc;AACvB;;;;;;"}
+{"version":3,"file":"providers.cjs","sources":["../../../src/llm/providers.ts"],"sourcesContent":["// src/llm/providers.ts\nimport { ChatOllama } from '@langchain/ollama';\nimport { ChatMistralAI } from '@langchain/mistralai';\nimport { ChatBedrockConverse } from '@langchain/aws';\n// import { ChatAnthropic } from '@langchain/anthropic';\n// import { ChatVertexAI } from '@langchain/google-vertexai';\nimport { BedrockChat } from '@langchain/community/chat_models/bedrock/web';\nimport type {\n  ChatModelConstructorMap,\n  ProviderOptionsMap,\n  ChatModelMap,\n} from '@/types';\nimport {\n  AzureChatOpenAI,\n  ChatDeepSeek,\n  ChatOpenAI,\n  ChatXAI,\n} from '@/llm/openai';\nimport { CustomChatGoogleGenerativeAI } from '@/llm/google';\nimport { CustomAnthropic } from '@/llm/anthropic';\nimport { ChatOpenRouter } from '@/llm/openrouter';\nimport { ChatVertexAI } from '@/llm/vertexai';\nimport { Providers } from '@/common';\n\nexport const llmProviders: Partial<ChatModelConstructorMap> = {\n  [Providers.XAI]: ChatXAI,\n  [Providers.OPENAI]: ChatOpenAI,\n  [Providers.OLLAMA]: ChatOllama,\n  [Providers.AZURE]: AzureChatOpenAI,\n  [Providers.VERTEXAI]: ChatVertexAI,\n  [Providers.DEEPSEEK]: ChatDeepSeek,\n  [Providers.MISTRALAI]: ChatMistralAI,\n  [Providers.MISTRAL]: ChatMistralAI,\n  [Providers.ANTHROPIC]: CustomAnthropic,\n  [Providers.OPENROUTER]: ChatOpenRouter,\n  [Providers.BEDROCK_LEGACY]: BedrockChat,\n  [Providers.BEDROCK]: ChatBedrockConverse,\n  // [Providers.ANTHROPIC]: ChatAnthropic,\n  [Providers.GOOGLE]: CustomChatGoogleGenerativeAI,\n};\n\nexport const manualToolStreamProviders = new Set<Providers | string>([\n  Providers.ANTHROPIC,\n  Providers.BEDROCK,\n  Providers.OLLAMA,\n]);\n\nexport const getChatModelClass = <P extends Providers>(\n  provider: P\n): new (config: ProviderOptionsMap[P]) => ChatModelMap[P] => {\n  const ChatModelClass = llmProviders[provider];\n  if (!ChatModelClass) {\n    throw new Error(`Unsupported LLM provider: ${provider}`);\n  }\n\n  return ChatModelClass;\n};\n"],"names":["Providers","ChatXAI","ChatOpenAI","ChatOllama","AzureChatOpenAI","ChatVertexAI","ChatDeepSeek","ChatMistralAI","CustomAnthropic","ChatOpenRouter","BedrockChat","ChatBedrockConverse","CustomChatGoogleGenerativeAI"],"mappings":";;;;;;;;;;;;;AAAA;AAwBa,MAAA,YAAY,GAAqC;AAC5D,IAAA,CAACA,eAAS,CAAC,GAAG,GAAGC,eAAO;AACxB,IAAA,CAACD,eAAS,CAAC,MAAM,GAAGE,kBAAU;AAC9B,IAAA,CAACF,eAAS,CAAC,MAAM,GAAGG,iBAAU;AAC9B,IAAA,CAACH,eAAS,CAAC,KAAK,GAAGI,uBAAe;AAClC,IAAA,CAACJ,eAAS,CAAC,QAAQ,GAAGK,oBAAY;AAClC,IAAA,CAACL,eAAS,CAAC,QAAQ,GAAGM,oBAAY;AAClC,IAAA,CAACN,eAAS,CAAC,SAAS,GAAGO,uBAAa;AACpC,IAAA,CAACP,eAAS,CAAC,OAAO,GAAGO,uBAAa;AAClC,IAAA,CAACP,eAAS,CAAC,SAAS,GAAGQ,uBAAe;AACtC,IAAA,CAACR,eAAS,CAAC,UAAU,GAAGS,sBAAc;AACtC,IAAA,CAACT,eAAS,CAAC,cAAc,GAAGU,eAAW;AACvC,IAAA,CAACV,eAAS,CAAC,OAAO,GAAGW,uBAAmB;;AAExC,IAAA,CAACX,eAAS,CAAC,MAAM,GAAGY,kCAA4B;;AAGrC,MAAA,yBAAyB,GAAG,IAAI,GAAG,CAAqB;AACnE,IAAAZ,eAAS,CAAC,SAAS;AACnB,IAAAA,eAAS,CAAC,OAAO;AACjB,IAAAA,eAAS,CAAC,MAAM;AACjB,CAAA;AAEY,MAAA,iBAAiB,GAAG,CAC/B,QAAW,KAC+C;AAC1D,IAAA,MAAM,cAAc,GAAG,YAAY,CAAC,QAAQ,CAAC;IAC7C,IAAI,CAAC,cAAc,EAAE;AACnB,QAAA,MAAM,IAAI,KAAK,CAAC,6BAA6B,QAAQ,CAAA,CAAE,CAAC;;AAG1D,IAAA,OAAO,cAAc;AACvB;;;;;;"}

package/dist/cjs/llm/vertexai/index.cjs

@@ -0,0 +1,330 @@
+'use strict';
+
+var googleGauth = require('@langchain/google-gauth');
+var googleCommon = require('@langchain/google-common');
+
+class CustomChatConnection extends googleCommon.ChatConnection {
+    async formatData(input, parameters) {
+        const formattedData = (await super.formatData(input, parameters));
+        if (formattedData.generationConfig?.thinkingConfig?.thinkingBudget === -1 &&
+            formattedData.generationConfig.thinkingConfig.includeThoughts === false) {
+            formattedData.generationConfig.thinkingConfig.includeThoughts = true;
+        }
+        return formattedData;
+    }
+}
+/**
+ * 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 />
+ */
+class ChatVertexAI extends googleGauth.ChatGoogle {
+    lc_namespace = ['langchain', 'chat_models', 'vertexai'];
+    dynamicThinkingBudget = false;
+    static lc_name() {
+        return 'ChatVertexAI';
+    }
+    constructor(fields) {
+        let dynamicThinkingBudget = false;
+        if (fields?.thinkingBudget === -1) {
+            dynamicThinkingBudget = true;
+            fields.thinkingBudget = 1;
+        }
+        super({
+            ...fields,
+            platformType: 'gcp',
+        });
+        this.dynamicThinkingBudget = dynamicThinkingBudget;
+    }
+    invocationParams(options) {
+        const params = super.invocationParams(options);
+        if (this.dynamicThinkingBudget) {
+            params.maxReasoningTokens = -1;
+        }
+        return params;
+    }
+    buildConnection(fields, client) {
+        this.connection = new CustomChatConnection({ ...fields, ...this }, this.caller, client, false);
+        this.streamedConnection = new CustomChatConnection({ ...fields, ...this }, this.caller, client, true);
+    }
+}
+
+exports.ChatVertexAI = ChatVertexAI;
+//# sourceMappingURL=index.cjs.map

package/dist/cjs/llm/vertexai/index.cjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.cjs","sources":["../../../../src/llm/vertexai/index.ts"],"sourcesContent":["import { ChatGoogle } from '@langchain/google-gauth';\nimport { ChatConnection } from '@langchain/google-common';\nimport type {\n  GeminiRequest,\n  GoogleAIModelRequestParams,\n  GoogleAbstractedClient,\n} from '@langchain/google-common';\nimport type { BaseMessage } from '@langchain/core/messages';\nimport type { VertexAIClientOptions } from '@/types';\n\nclass CustomChatConnection extends ChatConnection<VertexAIClientOptions> {\n  async formatData(\n    input: BaseMessage[],\n    parameters: GoogleAIModelRequestParams\n  ): Promise<unknown> {\n    const formattedData = (await super.formatData(\n      input,\n      parameters\n    )) as GeminiRequest;\n    if (\n      formattedData.generationConfig?.thinkingConfig?.thinkingBudget === -1 &&\n      formattedData.generationConfig.thinkingConfig.includeThoughts === false\n    ) {\n      formattedData.generationConfig.thinkingConfig.includeThoughts = true;\n    }\n    return formattedData;\n  }\n}\n\n/**\n * Integration with Google Vertex AI chat models.\n *\n * Setup:\n * Install `@langchain/google-vertexai` and set your stringified\n * Vertex AI credentials as an environment variable named `GOOGLE_APPLICATION_CREDENTIALS`.\n *\n * ```bash\n * npm install @langchain/google-vertexai\n * export GOOGLE_APPLICATION_CREDENTIALS=\"path/to/credentials\"\n * ```\n *\n * ## [Constructor args](https://api.js.langchain.com/classes/_langchain_google_vertexai.index.ChatVertexAI.html#constructor.new_ChatVertexAI)\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 * // When calling `.withConfig`, call options should be passed via the first argument\n * const llmWithArgsBound = llm.withConfig({\n *   stop: [\"\\n\"],\n *   tools: [...],\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';\n *\n * const llm = new ChatVertexAI({\n *   model: \"gemini-1.5-pro\",\n *   temperature: 0,\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  dynamicThinkingBudget = false;\n\n  static lc_name(): 'ChatVertexAI' {\n    return 'ChatVertexAI';\n  }\n\n  constructor(fields?: VertexAIClientOptions) {\n    let dynamicThinkingBudget = false;\n    if (fields?.thinkingBudget === -1) {\n      dynamicThinkingBudget = true;\n      fields.thinkingBudget = 1;\n    }\n    super({\n      ...fields,\n      platformType: 'gcp',\n    });\n    this.dynamicThinkingBudget = dynamicThinkingBudget;\n  }\n  invocationParams(\n    options?: this['ParsedCallOptions'] | undefined\n  ): GoogleAIModelRequestParams {\n    const params = super.invocationParams(options);\n    if (this.dynamicThinkingBudget) {\n      params.maxReasoningTokens = -1;\n    }\n    return params;\n  }\n\n  buildConnection(\n    fields: VertexAIClientOptions,\n    client: GoogleAbstractedClient\n  ): void {\n    this.connection = new CustomChatConnection(\n      { ...fields, ...this },\n      this.caller,\n      client,\n      false\n    );\n\n    this.streamedConnection = new CustomChatConnection(\n      { ...fields, ...this },\n      this.caller,\n      client,\n      true\n    );\n  }\n}\n"],"names":["ChatConnection","ChatGoogle"],"mappings":";;;;;AAUA,MAAM,oBAAqB,SAAQA,2BAAqC,CAAA;AACtE,IAAA,MAAM,UAAU,CACd,KAAoB,EACpB,UAAsC,EAAA;AAEtC,QAAA,MAAM,aAAa,IAAI,MAAM,KAAK,CAAC,UAAU,CAC3C,KAAK,EACL,UAAU,CACX,CAAkB;QACnB,IACE,aAAa,CAAC,gBAAgB,EAAE,cAAc,EAAE,cAAc,KAAK,EAAE;YACrE,aAAa,CAAC,gBAAgB,CAAC,cAAc,CAAC,eAAe,KAAK,KAAK,EACvE;YACA,aAAa,CAAC,gBAAgB,CAAC,cAAc,CAAC,eAAe,GAAG,IAAI;;AAEtE,QAAA,OAAO,aAAa;;AAEvB;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAyRG;AACG,MAAO,YAAa,SAAQC,sBAAU,CAAA;IAC1C,YAAY,GAAG,CAAC,WAAW,EAAE,aAAa,EAAE,UAAU,CAAC;IACvD,qBAAqB,GAAG,KAAK;AAE7B,IAAA,OAAO,OAAO,GAAA;AACZ,QAAA,OAAO,cAAc;;AAGvB,IAAA,WAAA,CAAY,MAA8B,EAAA;QACxC,IAAI,qBAAqB,GAAG,KAAK;AACjC,QAAA,IAAI,MAAM,EAAE,cAAc,KAAK,EAAE,EAAE;YACjC,qBAAqB,GAAG,IAAI;AAC5B,YAAA,MAAM,CAAC,cAAc,GAAG,CAAC;;AAE3B,QAAA,KAAK,CAAC;AACJ,YAAA,GAAG,MAAM;AACT,YAAA,YAAY,EAAE,KAAK;AACpB,SAAA,CAAC;AACF,QAAA,IAAI,CAAC,qBAAqB,GAAG,qBAAqB;;AAEpD,IAAA,gBAAgB,CACd,OAA+C,EAAA;QAE/C,MAAM,MAAM,GAAG,KAAK,CAAC,gBAAgB,CAAC,OAAO,CAAC;AAC9C,QAAA,IAAI,IAAI,CAAC,qBAAqB,EAAE;AAC9B,YAAA,MAAM,CAAC,kBAAkB,GAAG,EAAE;;AAEhC,QAAA,OAAO,MAAM;;IAGf,eAAe,CACb,MAA6B,EAC7B,MAA8B,EAAA;QAE9B,IAAI,CAAC,UAAU,GAAG,IAAI,oBAAoB,CACxC,EAAE,GAAG,MAAM,EAAE,GAAG,IAAI,EAAE,EACtB,IAAI,CAAC,MAAM,EACX,MAAM,EACN,KAAK,CACN;QAED,IAAI,CAAC,kBAAkB,GAAG,IAAI,oBAAoB,CAChD,EAAE,GAAG,MAAM,EAAE,GAAG,IAAI,EAAE,EACtB,IAAI,CAAC,MAAM,EACX,MAAM,EACN,IAAI,CACL;;AAEJ;;;;"}

package/dist/esm/llm/providers.mjs

@@ -1,12 +1,12 @@
 import { ChatOllama } from '@langchain/ollama';
 import { ChatMistralAI } from '@langchain/mistralai';
 import { ChatBedrockConverse } from '@langchain/aws';
-import { ChatVertexAI } from '@langchain/google-vertexai';
 import { BedrockChat } from '@langchain/community/chat_models/bedrock/web';
+import { ChatDeepSeek, AzureChatOpenAI, ChatOpenAI, ChatXAI } from './openai/index.mjs';
 import { CustomChatGoogleGenerativeAI } from './google/index.mjs';
 import { CustomAnthropic } from './anthropic/index.mjs';
 import { ChatOpenRouter } from './openrouter/index.mjs';
-import { ChatDeepSeek, AzureChatOpenAI, ChatOpenAI, ChatXAI } from './openai/index.mjs';
+import { ChatVertexAI } from './vertexai/index.mjs';
 import { Providers } from '../common/enum.mjs';
 
 // src/llm/providers.ts

package/dist/esm/llm/providers.mjs.map

@@ -1 +1 @@
-{"version":3,"file":"providers.mjs","sources":["../../../src/llm/providers.ts"],"sourcesContent":["// src/llm/providers.ts\nimport { ChatOllama } from '@langchain/ollama';\nimport { ChatMistralAI } from '@langchain/mistralai';\nimport { ChatBedrockConverse } from '@langchain/aws';\n// import { ChatAnthropic } from '@langchain/anthropic';\nimport { ChatVertexAI } from '@langchain/google-vertexai';\nimport { BedrockChat } from '@langchain/community/chat_models/bedrock/web';\nimport type {\n  ChatModelConstructorMap,\n  ProviderOptionsMap,\n  ChatModelMap,\n} from '@/types';\nimport { CustomChatGoogleGenerativeAI } from '@/llm/google';\nimport { CustomAnthropic } from '@/llm/anthropic';\nimport { ChatOpenRouter } from '@/llm/openrouter';\nimport {\n  ChatXAI,\n  ChatOpenAI,\n  ChatDeepSeek,\n  AzureChatOpenAI,\n} from '@/llm/openai';\nimport { Providers } from '@/common';\n\nexport const llmProviders: Partial<ChatModelConstructorMap> = {\n  [Providers.XAI]: ChatXAI,\n  [Providers.OPENAI]: ChatOpenAI,\n  [Providers.OLLAMA]: ChatOllama,\n  [Providers.AZURE]: AzureChatOpenAI,\n  [Providers.VERTEXAI]: ChatVertexAI,\n  [Providers.DEEPSEEK]: ChatDeepSeek,\n  [Providers.MISTRALAI]: ChatMistralAI,\n  [Providers.MISTRAL]: ChatMistralAI,\n  [Providers.ANTHROPIC]: CustomAnthropic,\n  [Providers.OPENROUTER]: ChatOpenRouter,\n  [Providers.BEDROCK_LEGACY]: BedrockChat,\n  [Providers.BEDROCK]: ChatBedrockConverse,\n  // [Providers.ANTHROPIC]: ChatAnthropic,\n  [Providers.GOOGLE]: CustomChatGoogleGenerativeAI,\n};\n\nexport const manualToolStreamProviders = new Set<Providers | string>([\n  Providers.ANTHROPIC,\n  Providers.BEDROCK,\n  Providers.OLLAMA,\n]);\n\nexport const getChatModelClass = <P extends Providers>(\n  provider: P\n): new (config: ProviderOptionsMap[P]) => ChatModelMap[P] => {\n  const ChatModelClass = llmProviders[provider];\n  if (!ChatModelClass) {\n    throw new Error(`Unsupported LLM provider: ${provider}`);\n  }\n\n  return ChatModelClass;\n};\n"],"names":[],"mappings":";;;;;;;;;;;AAAA;AAuBa,MAAA,YAAY,GAAqC;AAC5D,IAAA,CAAC,SAAS,CAAC,GAAG,GAAG,OAAO;AACxB,IAAA,CAAC,SAAS,CAAC,MAAM,GAAG,UAAU;AAC9B,IAAA,CAAC,SAAS,CAAC,MAAM,GAAG,UAAU;AAC9B,IAAA,CAAC,SAAS,CAAC,KAAK,GAAG,eAAe;AAClC,IAAA,CAAC,SAAS,CAAC,QAAQ,GAAG,YAAY;AAClC,IAAA,CAAC,SAAS,CAAC,QAAQ,GAAG,YAAY;AAClC,IAAA,CAAC,SAAS,CAAC,SAAS,GAAG,aAAa;AACpC,IAAA,CAAC,SAAS,CAAC,OAAO,GAAG,aAAa;AAClC,IAAA,CAAC,SAAS,CAAC,SAAS,GAAG,eAAe;AACtC,IAAA,CAAC,SAAS,CAAC,UAAU,GAAG,cAAc;AACtC,IAAA,CAAC,SAAS,CAAC,cAAc,GAAG,WAAW;AACvC,IAAA,CAAC,SAAS,CAAC,OAAO,GAAG,mBAAmB;;AAExC,IAAA,CAAC,SAAS,CAAC,MAAM,GAAG,4BAA4B;;AAGrC,MAAA,yBAAyB,GAAG,IAAI,GAAG,CAAqB;AACnE,IAAA,SAAS,CAAC,SAAS;AACnB,IAAA,SAAS,CAAC,OAAO;AACjB,IAAA,SAAS,CAAC,MAAM;AACjB,CAAA;AAEY,MAAA,iBAAiB,GAAG,CAC/B,QAAW,KAC+C;AAC1D,IAAA,MAAM,cAAc,GAAG,YAAY,CAAC,QAAQ,CAAC;IAC7C,IAAI,CAAC,cAAc,EAAE;AACnB,QAAA,MAAM,IAAI,KAAK,CAAC,6BAA6B,QAAQ,CAAA,CAAE,CAAC;;AAG1D,IAAA,OAAO,cAAc;AACvB;;;;"}
+{"version":3,"file":"providers.mjs","sources":["../../../src/llm/providers.ts"],"sourcesContent":["// src/llm/providers.ts\nimport { ChatOllama } from '@langchain/ollama';\nimport { ChatMistralAI } from '@langchain/mistralai';\nimport { ChatBedrockConverse } from '@langchain/aws';\n// import { ChatAnthropic } from '@langchain/anthropic';\n// import { ChatVertexAI } from '@langchain/google-vertexai';\nimport { BedrockChat } from '@langchain/community/chat_models/bedrock/web';\nimport type {\n  ChatModelConstructorMap,\n  ProviderOptionsMap,\n  ChatModelMap,\n} from '@/types';\nimport {\n  AzureChatOpenAI,\n  ChatDeepSeek,\n  ChatOpenAI,\n  ChatXAI,\n} from '@/llm/openai';\nimport { CustomChatGoogleGenerativeAI } from '@/llm/google';\nimport { CustomAnthropic } from '@/llm/anthropic';\nimport { ChatOpenRouter } from '@/llm/openrouter';\nimport { ChatVertexAI } from '@/llm/vertexai';\nimport { Providers } from '@/common';\n\nexport const llmProviders: Partial<ChatModelConstructorMap> = {\n  [Providers.XAI]: ChatXAI,\n  [Providers.OPENAI]: ChatOpenAI,\n  [Providers.OLLAMA]: ChatOllama,\n  [Providers.AZURE]: AzureChatOpenAI,\n  [Providers.VERTEXAI]: ChatVertexAI,\n  [Providers.DEEPSEEK]: ChatDeepSeek,\n  [Providers.MISTRALAI]: ChatMistralAI,\n  [Providers.MISTRAL]: ChatMistralAI,\n  [Providers.ANTHROPIC]: CustomAnthropic,\n  [Providers.OPENROUTER]: ChatOpenRouter,\n  [Providers.BEDROCK_LEGACY]: BedrockChat,\n  [Providers.BEDROCK]: ChatBedrockConverse,\n  // [Providers.ANTHROPIC]: ChatAnthropic,\n  [Providers.GOOGLE]: CustomChatGoogleGenerativeAI,\n};\n\nexport const manualToolStreamProviders = new Set<Providers | string>([\n  Providers.ANTHROPIC,\n  Providers.BEDROCK,\n  Providers.OLLAMA,\n]);\n\nexport const getChatModelClass = <P extends Providers>(\n  provider: P\n): new (config: ProviderOptionsMap[P]) => ChatModelMap[P] => {\n  const ChatModelClass = llmProviders[provider];\n  if (!ChatModelClass) {\n    throw new Error(`Unsupported LLM provider: ${provider}`);\n  }\n\n  return ChatModelClass;\n};\n"],"names":[],"mappings":";;;;;;;;;;;AAAA;AAwBa,MAAA,YAAY,GAAqC;AAC5D,IAAA,CAAC,SAAS,CAAC,GAAG,GAAG,OAAO;AACxB,IAAA,CAAC,SAAS,CAAC,MAAM,GAAG,UAAU;AAC9B,IAAA,CAAC,SAAS,CAAC,MAAM,GAAG,UAAU;AAC9B,IAAA,CAAC,SAAS,CAAC,KAAK,GAAG,eAAe;AAClC,IAAA,CAAC,SAAS,CAAC,QAAQ,GAAG,YAAY;AAClC,IAAA,CAAC,SAAS,CAAC,QAAQ,GAAG,YAAY;AAClC,IAAA,CAAC,SAAS,CAAC,SAAS,GAAG,aAAa;AACpC,IAAA,CAAC,SAAS,CAAC,OAAO,GAAG,aAAa;AAClC,IAAA,CAAC,SAAS,CAAC,SAAS,GAAG,eAAe;AACtC,IAAA,CAAC,SAAS,CAAC,UAAU,GAAG,cAAc;AACtC,IAAA,CAAC,SAAS,CAAC,cAAc,GAAG,WAAW;AACvC,IAAA,CAAC,SAAS,CAAC,OAAO,GAAG,mBAAmB;;AAExC,IAAA,CAAC,SAAS,CAAC,MAAM,GAAG,4BAA4B;;AAGrC,MAAA,yBAAyB,GAAG,IAAI,GAAG,CAAqB;AACnE,IAAA,SAAS,CAAC,SAAS;AACnB,IAAA,SAAS,CAAC,OAAO;AACjB,IAAA,SAAS,CAAC,MAAM;AACjB,CAAA;AAEY,MAAA,iBAAiB,GAAG,CAC/B,QAAW,KAC+C;AAC1D,IAAA,MAAM,cAAc,GAAG,YAAY,CAAC,QAAQ,CAAC;IAC7C,IAAI,CAAC,cAAc,EAAE;AACnB,QAAA,MAAM,IAAI,KAAK,CAAC,6BAA6B,QAAQ,CAAA,CAAE,CAAC;;AAG1D,IAAA,OAAO,cAAc;AACvB;;;;"}