langchain 0.3.28 → 0.3.30

package/dist/chains/openai_functions/openapi.cjs

@@ -1,6 +1,8 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.createOpenAPIChain = exports.convertOpenAPISpecToOpenAIFunctions = exports.convertOpenAPISchemaToJSONSchema = void 0;
+exports.convertOpenAPISchemaToJSONSchema = convertOpenAPISchemaToJSONSchema;
+exports.convertOpenAPISpecToOpenAIFunctions = convertOpenAPISpecToOpenAIFunctions;
+exports.createOpenAPIChain = createOpenAPIChain;
 const openai_1 = require("@langchain/openai");
 const prompts_1 = require("@langchain/core/prompts");
 const openapi_js_1 = require("../../util/openapi.cjs");
@@ -158,7 +160,6 @@ function convertOpenAPISchemaToJSONSchema(schema, spec) {
         type: schema.type ?? "string",
     };
 }
-exports.convertOpenAPISchemaToJSONSchema = convertOpenAPISchemaToJSONSchema;
 /**
  * Converts an OpenAPI specification to OpenAI functions.
  * @param spec The OpenAPI specification to convert.
@@ -302,7 +303,6 @@ function convertOpenAPISpecToOpenAIFunctions(spec) {
         },
     };
 }
-exports.convertOpenAPISpecToOpenAIFunctions = convertOpenAPISpecToOpenAIFunctions;
 /**
  * A chain for making simple API requests.
  */
@@ -378,7 +378,7 @@ async function createOpenAPIChain(spec, options = {}) {
     if (defaultExecutionMethod === undefined) {
         throw new Error(`Could not parse any valid operations from the provided spec.`);
     }
-    const { llm = new openai_1.ChatOpenAI({ modelName: "gpt-3.5-turbo-0613" }), prompt = prompts_1.ChatPromptTemplate.fromMessages([
+    const { llm = new openai_1.ChatOpenAI({ model: "gpt-3.5-turbo-0613" }), prompt = prompts_1.ChatPromptTemplate.fromMessages([
         prompts_1.HumanMessagePromptTemplate.fromTemplate("Use the provided API's to respond to this user query:\n\n{query}"),
     ]), requestChain = new SimpleRequestChain({
         requestMethod: async (name, args) => defaultExecutionMethod(name, args, {
@@ -402,4 +402,3 @@ async function createOpenAPIChain(spec, options = {}) {
         ...rest,
     });
 }
-exports.createOpenAPIChain = createOpenAPIChain;

package/dist/chains/openai_functions/openapi.js

@@ -373,7 +373,7 @@ export async function createOpenAPIChain(spec, options = {}) {
     if (defaultExecutionMethod === undefined) {
         throw new Error(`Could not parse any valid operations from the provided spec.`);
     }
-    const { llm = new ChatOpenAI({ modelName: "gpt-3.5-turbo-0613" }), prompt = ChatPromptTemplate.fromMessages([
+    const { llm = new ChatOpenAI({ model: "gpt-3.5-turbo-0613" }), prompt = ChatPromptTemplate.fromMessages([
         HumanMessagePromptTemplate.fromTemplate("Use the provided API's to respond to this user query:\n\n{query}"),
     ]), requestChain = new SimpleRequestChain({
         requestMethod: async (name, args) => defaultExecutionMethod(name, args, {

package/dist/chains/openai_functions/structured_output.cjs

@@ -1,6 +1,8 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.createStructuredOutputChainFromZod = exports.createStructuredOutputChain = exports.FunctionCallStructuredOutputParser = void 0;
+exports.FunctionCallStructuredOutputParser = void 0;
+exports.createStructuredOutputChain = createStructuredOutputChain;
+exports.createStructuredOutputChainFromZod = createStructuredOutputChainFromZod;
 const json_schema_1 = require("@langchain/core/utils/json_schema");
 const openai_1 = require("@langchain/openai");
 const output_parsers_1 = require("@langchain/core/output_parsers");
@@ -109,7 +111,7 @@ exports.FunctionCallStructuredOutputParser = FunctionCallStructuredOutputParser;
  * @returns OpenAPIChain
  */
 function createStructuredOutputChain(input) {
-    const { outputSchema, llm = new openai_1.ChatOpenAI({ modelName: "gpt-3.5-turbo-0613", temperature: 0 }), outputKey = "output", llmKwargs = {}, zodSchema, ...rest } = input;
+    const { outputSchema, llm = new openai_1.ChatOpenAI({ model: "gpt-3.5-turbo-0613", temperature: 0 }), outputKey = "output", llmKwargs = {}, zodSchema, ...rest } = input;
     if (outputSchema === undefined && zodSchema === undefined) {
         throw new Error(`Must provide one of "outputSchema" or "zodSchema".`);
     }
@@ -137,7 +139,6 @@ function createStructuredOutputChain(input) {
         ...rest,
     });
 }
-exports.createStructuredOutputChain = createStructuredOutputChain;
 /** @deprecated Use {@link https://api.js.langchain.com/functions/langchain.chains_openai_functions.createStructuredOutputRunnable.html | createStructuredOutputRunnable} instead */
 function createStructuredOutputChainFromZod(zodSchema, input) {
     return createStructuredOutputChain({
@@ -146,4 +147,3 @@ function createStructuredOutputChainFromZod(zodSchema, input) {
         zodSchema,
     });
 }
-exports.createStructuredOutputChainFromZod = createStructuredOutputChainFromZod;

package/dist/chains/openai_functions/structured_output.js

@@ -105,7 +105,7 @@ export class FunctionCallStructuredOutputParser extends BaseLLMOutputParser {
  * @returns OpenAPIChain
  */
 export function createStructuredOutputChain(input) {
-    const { outputSchema, llm = new ChatOpenAI({ modelName: "gpt-3.5-turbo-0613", temperature: 0 }), outputKey = "output", llmKwargs = {}, zodSchema, ...rest } = input;
+    const { outputSchema, llm = new ChatOpenAI({ model: "gpt-3.5-turbo-0613", temperature: 0 }), outputKey = "output", llmKwargs = {}, zodSchema, ...rest } = input;
     if (outputSchema === undefined && zodSchema === undefined) {
         throw new Error(`Must provide one of "outputSchema" or "zodSchema".`);
     }

package/dist/chains/openai_functions/tagging.cjs

@@ -1,6 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.createTaggingChainFromZod = exports.createTaggingChain = void 0;
+exports.createTaggingChain = createTaggingChain;
+exports.createTaggingChainFromZod = createTaggingChainFromZod;
 const prompts_1 = require("@langchain/core/prompts");
 const json_schema_1 = require("@langchain/core/utils/json_schema");
 const openai_functions_js_1 = require("../../output_parsers/openai_functions.cjs");
@@ -51,7 +52,6 @@ function createTaggingChain(schema, llm, options = {}) {
         ...rest,
     });
 }
-exports.createTaggingChain = createTaggingChain;
 /**
  * Function that creates a tagging chain from a Zod schema. It converts
  * the Zod schema to a JSON schema using the zodToJsonSchema function and
@@ -70,4 +70,3 @@ function createTaggingChainFromZod(
 schema, llm, options) {
     return createTaggingChain((0, json_schema_1.toJsonSchema)(schema), llm, options);
 }
-exports.createTaggingChainFromZod = createTaggingChainFromZod;

package/dist/chains/query_constructor/index.cjs

@@ -1,6 +1,8 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.loadQueryConstructorRunnable = exports.formatAttributeInfo = exports.StructuredQueryOutputParser = exports.EXAMPLE_PROMPT = exports.DEFAULT_SUFFIX = exports.DEFAULT_SCHEMA = exports.DEFAULT_PREFIX = exports.DEFAULT_EXAMPLES = exports.QueryTransformer = exports.AttributeInfo = void 0;
+exports.StructuredQueryOutputParser = exports.EXAMPLE_PROMPT = exports.DEFAULT_SUFFIX = exports.DEFAULT_SCHEMA = exports.DEFAULT_PREFIX = exports.DEFAULT_EXAMPLES = exports.QueryTransformer = exports.AttributeInfo = void 0;
+exports.formatAttributeInfo = formatAttributeInfo;
+exports.loadQueryConstructorRunnable = loadQueryConstructorRunnable;
 const zod_1 = require("zod");
 const prompts_1 = require("@langchain/core/prompts");
 const parser_js_1 = require("./parser.cjs");
@@ -118,7 +120,6 @@ function formatAttributeInfo(info) {
         .replaceAll("{", "{{")
         .replaceAll("}", "}}");
 }
-exports.formatAttributeInfo = formatAttributeInfo;
 const defaultExample = prompt_js_1.DEFAULT_EXAMPLES.map((EXAMPLE) => EXAMPLE);
 function _getPrompt(documentContents, attributeInfo, allowedComparators, allowedOperators, examples = defaultExample) {
     const myAllowedComparators = allowedComparators ?? Object.values(ir_js_1.Comparators);
@@ -151,4 +152,3 @@ function loadQueryConstructorRunnable(opts) {
     const outputParser = StructuredQueryOutputParser.fromComponents(opts.allowedComparators, opts.allowedOperators);
     return prompt.pipe(opts.llm).pipe(outputParser);
 }
-exports.loadQueryConstructorRunnable = loadQueryConstructorRunnable;

package/dist/chains/question_answering/load.cjs

@@ -1,6 +1,9 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.loadQARefineChain = exports.loadQAMapReduceChain = exports.loadQAStuffChain = exports.loadQAChain = void 0;
+exports.loadQAChain = void 0;
+exports.loadQAStuffChain = loadQAStuffChain;
+exports.loadQAMapReduceChain = loadQAMapReduceChain;
+exports.loadQARefineChain = loadQARefineChain;
 const llm_chain_js_1 = require("../llm_chain.cjs");
 const combine_docs_chain_js_1 = require("../combine_docs_chain.cjs");
 const stuff_prompts_js_1 = require("./stuff_prompts.cjs");
@@ -33,7 +36,6 @@ function loadQAStuffChain(llm, params = {}) {
     const chain = new combine_docs_chain_js_1.StuffDocumentsChain({ llmChain, verbose });
     return chain;
 }
-exports.loadQAStuffChain = loadQAStuffChain;
 /**
  * Loads a MapReduceQAChain based on the provided parameters. It takes an
  * LLM instance and MapReduceQAChainParams as parameters.
@@ -62,7 +64,6 @@ function loadQAMapReduceChain(llm, params = {}) {
     });
     return chain;
 }
-exports.loadQAMapReduceChain = loadQAMapReduceChain;
 /**
  * Loads a RefineQAChain based on the provided parameters. It takes an LLM
  * instance and RefineQAChainParams as parameters.
@@ -85,4 +86,3 @@ function loadQARefineChain(llm, params = {}) {
     });
     return chain;
 }
-exports.loadQARefineChain = loadQARefineChain;

package/dist/chains/retrieval.cjs

@@ -1,6 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.createRetrievalChain = void 0;
+exports.createRetrievalChain = createRetrievalChain;
 const runnables_1 = require("@langchain/core/runnables");
 function isBaseRetriever(x) {
     return (!!x &&
@@ -22,7 +22,7 @@ function isBaseRetriever(x) {
  * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
  *
  * const retrievalQAChatPrompt = await pull("langchain-ai/retrieval-qa-chat");
- * const llm = new ChatOpenAI({});
+ * const llm = new ChatOpenAI({ model: "gpt-4o-mini" });
  * const retriever = ...
  * const combineDocsChain = await createStuffDocumentsChain(...);
  * const retrievalChain = await createRetrievalChain({
@@ -57,4 +57,3 @@ async function createRetrievalChain({ retriever, combineDocsChain, }) {
     ]).withConfig({ runName: "retrieval_chain" });
     return retrievalChain;
 }
-exports.createRetrievalChain = createRetrievalChain;

package/dist/chains/retrieval.d.ts

@@ -42,7 +42,7 @@ export type CreateRetrievalChainParams<RunOutput> = {
  * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
  *
  * const retrievalQAChatPrompt = await pull("langchain-ai/retrieval-qa-chat");
- * const llm = new ChatOpenAI({});
+ * const llm = new ChatOpenAI({ model: "gpt-4o-mini" });
  * const retriever = ...
  * const combineDocsChain = await createStuffDocumentsChain(...);
  * const retrievalChain = await createRetrievalChain({

package/dist/chains/retrieval.js

@@ -19,7 +19,7 @@ function isBaseRetriever(x) {
  * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
  *
  * const retrievalQAChatPrompt = await pull("langchain-ai/retrieval-qa-chat");
- * const llm = new ChatOpenAI({});
+ * const llm = new ChatOpenAI({ model: "gpt-4o-mini" });
  * const retriever = ...
  * const combineDocsChain = await createStuffDocumentsChain(...);
  * const retrievalChain = await createRetrievalChain({

package/dist/chains/router/multi_prompt.cjs

@@ -16,19 +16,22 @@ const router_js_1 = require("../../output_parsers/router.cjs");
  * functionality specific to multi-prompt chains.
  * @example
  * ```typescript
- * const multiPromptChain = MultiPromptChain.fromLLMAndPrompts(new ChatOpenAI(), {
- *   promptNames: ["physics", "math", "history"],
- *   promptDescriptions: [
- *     "Good for answering questions about physics",
- *     "Good for answering math questions",
- *     "Good for answering questions about history",
- *   ],
- *   promptTemplates: [
- *     `You are a very smart physics professor. Here is a question:\n{input}\n`,
- *     `You are a very good mathematician. Here is a question:\n{input}\n`,
- *     `You are a very smart history professor. Here is a question:\n{input}\n`,
- *   ],
- * });
+ * const multiPromptChain = MultiPromptChain.fromLLMAndPrompts(
+ *   new ChatOpenAI({ model: "gpt-4o-mini" }),
+ *   {
+ *     promptNames: ["physics", "math", "history"],
+ *     promptDescriptions: [
+ *       "Good for answering questions about physics",
+ *       "Good for answering math questions",
+ *       "Good for answering questions about history",
+ *     ],
+ *     promptTemplates: [
+ *       `You are a very smart physics professor. Here is a question:\n{input}\n`,
+ *       `You are a very good mathematician. Here is a question:\n{input}\n`,
+ *       `You are a very smart history professor. Here is a question:\n{input}\n`,
+ *     ],
+ *   }
+ * );
  * const result = await multiPromptChain.call({
  *   input: "What is the speed of light?",
  * });

package/dist/chains/router/multi_prompt.d.ts

@@ -9,19 +9,22 @@ import { LLMChainInput } from "../../chains/llm_chain.js";
  * functionality specific to multi-prompt chains.
  * @example
  * ```typescript
- * const multiPromptChain = MultiPromptChain.fromLLMAndPrompts(new ChatOpenAI(), {
- *   promptNames: ["physics", "math", "history"],
- *   promptDescriptions: [
- *     "Good for answering questions about physics",
- *     "Good for answering math questions",
- *     "Good for answering questions about history",
- *   ],
- *   promptTemplates: [
- *     `You are a very smart physics professor. Here is a question:\n{input}\n`,
- *     `You are a very good mathematician. Here is a question:\n{input}\n`,
- *     `You are a very smart history professor. Here is a question:\n{input}\n`,
- *   ],
- * });
+ * const multiPromptChain = MultiPromptChain.fromLLMAndPrompts(
+ *   new ChatOpenAI({ model: "gpt-4o-mini" }),
+ *   {
+ *     promptNames: ["physics", "math", "history"],
+ *     promptDescriptions: [
+ *       "Good for answering questions about physics",
+ *       "Good for answering math questions",
+ *       "Good for answering questions about history",
+ *     ],
+ *     promptTemplates: [
+ *       `You are a very smart physics professor. Here is a question:\n{input}\n`,
+ *       `You are a very good mathematician. Here is a question:\n{input}\n`,
+ *       `You are a very smart history professor. Here is a question:\n{input}\n`,
+ *     ],
+ *   }
+ * );
  * const result = await multiPromptChain.call({
  *   input: "What is the speed of light?",
  * });

package/dist/chains/router/multi_prompt.js

@@ -13,19 +13,22 @@ import { RouterOutputParser } from "../../output_parsers/router.js";
  * functionality specific to multi-prompt chains.
  * @example
  * ```typescript
- * const multiPromptChain = MultiPromptChain.fromLLMAndPrompts(new ChatOpenAI(), {
- *   promptNames: ["physics", "math", "history"],
- *   promptDescriptions: [
- *     "Good for answering questions about physics",
- *     "Good for answering math questions",
- *     "Good for answering questions about history",
- *   ],
- *   promptTemplates: [
- *     `You are a very smart physics professor. Here is a question:\n{input}\n`,
- *     `You are a very good mathematician. Here is a question:\n{input}\n`,
- *     `You are a very smart history professor. Here is a question:\n{input}\n`,
- *   ],
- * });
+ * const multiPromptChain = MultiPromptChain.fromLLMAndPrompts(
+ *   new ChatOpenAI({ model: "gpt-4o-mini" }),
+ *   {
+ *     promptNames: ["physics", "math", "history"],
+ *     promptDescriptions: [
+ *       "Good for answering questions about physics",
+ *       "Good for answering math questions",
+ *       "Good for answering questions about history",
+ *     ],
+ *     promptTemplates: [
+ *       `You are a very smart physics professor. Here is a question:\n{input}\n`,
+ *       `You are a very good mathematician. Here is a question:\n{input}\n`,
+ *       `You are a very smart history professor. Here is a question:\n{input}\n`,
+ *     ],
+ *   }
+ * );
  * const result = await multiPromptChain.call({
  *   input: "What is the speed of light?",
  * });

package/dist/chains/router/multi_retrieval_qa.cjs

@@ -18,7 +18,7 @@ const router_js_1 = require("../../output_parsers/router.cjs");
  * @example
  * ```typescript
  * const multiRetrievalQAChain = MultiRetrievalQAChain.fromLLMAndRetrievers(
- *   new ChatOpenAI(),
+ *   new ChatOpenAI({ model: "gpt-4o-mini" }),
  *   {
  *     retrieverNames: ["aqua teen", "mst3k", "animaniacs"],
  *     retrieverDescriptions: [

package/dist/chains/router/multi_retrieval_qa.d.ts

@@ -22,7 +22,7 @@ export type MultiRetrievalDefaults = {
  * @example
  * ```typescript
  * const multiRetrievalQAChain = MultiRetrievalQAChain.fromLLMAndRetrievers(
- *   new ChatOpenAI(),
+ *   new ChatOpenAI({ model: "gpt-4o-mini" }),
  *   {
  *     retrieverNames: ["aqua teen", "mst3k", "animaniacs"],
  *     retrieverDescriptions: [

package/dist/chains/router/multi_retrieval_qa.js

@@ -15,7 +15,7 @@ import { RouterOutputParser } from "../../output_parsers/router.js";
  * @example
  * ```typescript
  * const multiRetrievalQAChain = MultiRetrievalQAChain.fromLLMAndRetrievers(
- *   new ChatOpenAI(),
+ *   new ChatOpenAI({ model: "gpt-4o-mini" }),
  *   {
  *     retrieverNames: ["aqua teen", "mst3k", "animaniacs"],
  *     retrieverDescriptions: [

package/dist/chains/router/utils.cjs

@@ -1,6 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.zipEntries = void 0;
+exports.zipEntries = zipEntries;
 // eslint-disable-next-line @typescript-eslint/no-explicit-any
 function zipEntries(...arrays) {
     // Check for empty input
@@ -31,4 +31,3 @@ function zipEntries(...arrays) {
     }
     return zipped;
 }
-exports.zipEntries = zipEntries;

package/dist/chains/sequential_chain.cjs

@@ -32,12 +32,12 @@ function formatSet(input) {
  * const overallChain = new SequentialChain({
  *   chains: [
  *     new LLMChain({
- *       llm: new ChatOpenAI({ temperature: 0 }),
+ *       llm: new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 }),
  *       prompt: promptTemplate,
  *       outputKey: "synopsis",
  *     }),
  *     new LLMChain({
- *       llm: new OpenAI({ temperature: 0 }),
+ *       llm: new OpenAI({ model: "gpt-4o-mini", temperature: 0 }),
  *       prompt: reviewPromptTemplate,
  *       outputKey: "review",
  *     }),
@@ -275,7 +275,8 @@ class SimpleSequentialChain extends base_js_1.BaseChain {
     /** @ignore */
     _validateChains() {
         for (const chain of this.chains) {
-            if (chain.inputKeys.filter((k) => !chain.memory?.memoryKeys.includes(k) ?? true).length !== 1) {
+            if (chain.inputKeys.filter((k) => !chain.memory?.memoryKeys.includes(k))
+                .length !== 1) {
                 throw new Error(`Chains used in SimpleSequentialChain should all have one input, got ${chain.inputKeys.length} for ${chain._chainType()}.`);
             }
             if (chain.outputKeys.length !== 1) {

package/dist/chains/sequential_chain.d.ts

@@ -43,12 +43,12 @@ export interface SequentialChainInput extends ChainInputs {
  * const overallChain = new SequentialChain({
  *   chains: [
  *     new LLMChain({
- *       llm: new ChatOpenAI({ temperature: 0 }),
+ *       llm: new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 }),
  *       prompt: promptTemplate,
  *       outputKey: "synopsis",
  *     }),
  *     new LLMChain({
- *       llm: new OpenAI({ temperature: 0 }),
+ *       llm: new OpenAI({ model: "gpt-4o-mini", temperature: 0 }),
  *       prompt: reviewPromptTemplate,
  *       outputKey: "review",
  *     }),

package/dist/chains/sequential_chain.js

@@ -29,12 +29,12 @@ function formatSet(input) {
  * const overallChain = new SequentialChain({
  *   chains: [
  *     new LLMChain({
- *       llm: new ChatOpenAI({ temperature: 0 }),
+ *       llm: new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 }),
  *       prompt: promptTemplate,
  *       outputKey: "synopsis",
  *     }),
  *     new LLMChain({
- *       llm: new OpenAI({ temperature: 0 }),
+ *       llm: new OpenAI({ model: "gpt-4o-mini", temperature: 0 }),
  *       prompt: reviewPromptTemplate,
  *       outputKey: "review",
  *     }),
@@ -271,7 +271,8 @@ export class SimpleSequentialChain extends BaseChain {
     /** @ignore */
     _validateChains() {
         for (const chain of this.chains) {
-            if (chain.inputKeys.filter((k) => !chain.memory?.memoryKeys.includes(k) ?? true).length !== 1) {
+            if (chain.inputKeys.filter((k) => !chain.memory?.memoryKeys.includes(k))
+                .length !== 1) {
                 throw new Error(`Chains used in SimpleSequentialChain should all have one input, got ${chain.inputKeys.length} for ${chain._chainType()}.`);
             }
             if (chain.outputKeys.length !== 1) {

package/dist/chains/sql_db/sql_db_chain.cjs

@@ -1,6 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.createSqlQueryChain = exports.SqlDatabaseChain = void 0;
+exports.SqlDatabaseChain = void 0;
+exports.createSqlQueryChain = createSqlQueryChain;
 const base_1 = require("@langchain/core/language_models/base");
 const runnables_1 = require("@langchain/core/runnables");
 const output_parsers_1 = require("@langchain/core/output_parsers");
@@ -217,7 +218,7 @@ const difference = (setA, setB) => new Set([...setA].filter((x) => !setB.has(x))
  * const db = await SqlDatabase.fromDataSourceParams({
  *   appDataSource: datasource,
  * });
- * const llm = new ChatOpenAI({ temperature: 0 });
+ * const llm = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 });
  * const chain = await createSqlQueryChain({
  *   llm,
  *   db,
@@ -267,4 +268,3 @@ async function createSqlQueryChain({ llm, db, prompt, k = 5, dialect, }) {
         strip,
     ]);
 }
-exports.createSqlQueryChain = createSqlQueryChain;

package/dist/chains/sql_db/sql_db_chain.d.ts

@@ -104,7 +104,7 @@ export interface CreateSqlQueryChainFields {
  * const db = await SqlDatabase.fromDataSourceParams({
  *   appDataSource: datasource,
  * });
- * const llm = new ChatOpenAI({ temperature: 0 });
+ * const llm = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 });
  * const chain = await createSqlQueryChain({
  *   llm,
  *   db,

package/dist/chains/sql_db/sql_db_chain.js

@@ -213,7 +213,7 @@ const difference = (setA, setB) => new Set([...setA].filter((x) => !setB.has(x))
  * const db = await SqlDatabase.fromDataSourceParams({
  *   appDataSource: datasource,
  * });
- * const llm = new ChatOpenAI({ temperature: 0 });
+ * const llm = new ChatOpenAI({ model: "gpt-4o-mini", temperature: 0 });
  * const chain = await createSqlQueryChain({
  *   llm,
  *   db,

package/dist/chat_models/universal.cjs

@@ -1,6 +1,41 @@
 "use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.initChatModel = exports.ConfigurableModel = exports._inferModelProvider = void 0;
+exports.ConfigurableModel = void 0;
+exports._inferModelProvider = _inferModelProvider;
+exports.initChatModel = initChatModel;
 const chat_models_1 = require("@langchain/core/language_models/chat_models");
 const runnables_1 = require("@langchain/core/runnables");
 const stream_1 = require("@langchain/core/utils/stream");
@@ -34,83 +69,83 @@ params = {}) {
     try {
         switch (modelProviderCopy) {
             case "openai": {
-                const { ChatOpenAI } = await import("@langchain/openai");
+                const { ChatOpenAI } = await Promise.resolve().then(() => __importStar(require("@langchain/openai")));
                 return new ChatOpenAI({ model, ...passedParams });
             }
             case "anthropic": {
-                const { ChatAnthropic } = await import("@langchain/anthropic");
+                const { ChatAnthropic } = await Promise.resolve().then(() => __importStar(require("@langchain/anthropic")));
                 return new ChatAnthropic({ model, ...passedParams });
             }
             case "azure_openai": {
-                const { AzureChatOpenAI } = await import("@langchain/openai");
+                const { AzureChatOpenAI } = await Promise.resolve().then(() => __importStar(require("@langchain/openai")));
                 return new AzureChatOpenAI({ model, ...passedParams });
             }
             case "cohere": {
-                const { ChatCohere } = await import("@langchain/cohere");
+                const { ChatCohere } = await Promise.resolve().then(() => __importStar(require("@langchain/cohere")));
                 return new ChatCohere({ model, ...passedParams });
             }
             case "google-vertexai": {
-                const { ChatVertexAI } = await import("@langchain/google-vertexai");
+                const { ChatVertexAI } = await Promise.resolve().then(() => __importStar(require("@langchain/google-vertexai")));
                 return new ChatVertexAI({ model, ...passedParams });
             }
             case "google-vertexai-web": {
-                const { ChatVertexAI } = await import("@langchain/google-vertexai-web");
+                const { ChatVertexAI } = await Promise.resolve().then(() => __importStar(require("@langchain/google-vertexai-web")));
                 return new ChatVertexAI({ model, ...passedParams });
             }
             case "google-genai": {
-                const { ChatGoogleGenerativeAI } = await import("@langchain/google-genai");
+                const { ChatGoogleGenerativeAI } = await Promise.resolve().then(() => __importStar(require("@langchain/google-genai")));
                 return new ChatGoogleGenerativeAI({ model, ...passedParams });
             }
             case "ollama": {
-                const { ChatOllama } = await import("@langchain/ollama");
+                const { ChatOllama } = await Promise.resolve().then(() => __importStar(require("@langchain/ollama")));
                 return new ChatOllama({ model, ...passedParams });
             }
             case "mistralai": {
-                const { ChatMistralAI } = await import("@langchain/mistralai");
+                const { ChatMistralAI } = await Promise.resolve().then(() => __importStar(require("@langchain/mistralai")));
                 return new ChatMistralAI({ model, ...passedParams });
             }
             case "groq": {
-                const { ChatGroq } = await import("@langchain/groq");
+                const { ChatGroq } = await Promise.resolve().then(() => __importStar(require("@langchain/groq")));
                 return new ChatGroq({ model, ...passedParams });
             }
             case "cerebras": {
-                const { ChatCerebras } = await import("@langchain/cerebras");
+                const { ChatCerebras } = await Promise.resolve().then(() => __importStar(require("@langchain/cerebras")));
                 return new ChatCerebras({ model, ...passedParams });
             }
             case "bedrock": {
-                const { ChatBedrockConverse } = await import("@langchain/aws");
+                const { ChatBedrockConverse } = await Promise.resolve().then(() => __importStar(require("@langchain/aws")));
                 return new ChatBedrockConverse({ model, ...passedParams });
             }
             case "deepseek": {
-                const { ChatDeepSeek } = await import("@langchain/deepseek");
+                const { ChatDeepSeek } = await Promise.resolve().then(() => __importStar(require("@langchain/deepseek")));
                 return new ChatDeepSeek({ model, ...passedParams });
             }
             case "xai": {
-                const { ChatXAI } = await import("@langchain/xai");
+                const { ChatXAI } = await Promise.resolve().then(() => __importStar(require("@langchain/xai")));
                 return new ChatXAI({ model, ...passedParams });
             }
             case "fireworks": {
                 // eslint-disable-next-line @typescript-eslint/ban-ts-comment
                 // @ts-ignore - Can not install as a proper dependency due to circular dependency
-                const { ChatFireworks } = await import(
+                const { ChatFireworks } = await Promise.resolve().then(() => __importStar(require(
                 // We can not 'expect-error' because if you explicitly build `@langchain/community`
                 // this import will be able to be resolved, thus there will be no error. However
                 // this will never be the case in CI.
                 // eslint-disable-next-line @typescript-eslint/ban-ts-comment
                 // @ts-ignore - Can not install as a proper dependency due to circular dependency
-                "@langchain/community/chat_models/fireworks");
+                "@langchain/community/chat_models/fireworks")));
                 return new ChatFireworks({ model, ...passedParams });
             }
             case "together": {
                 // eslint-disable-next-line @typescript-eslint/ban-ts-comment
                 // @ts-ignore - Can not install as a proper dependency due to circular dependency
-                const { ChatTogetherAI } = await import(
+                const { ChatTogetherAI } = await Promise.resolve().then(() => __importStar(require(
                 // We can not 'expect-error' because if you explicitly build `@langchain/community`
                 // this import will be able to be resolved, thus there will be no error. However
                 // this will never be the case in CI.
                 // eslint-disable-next-line @typescript-eslint/ban-ts-comment
                 // @ts-ignore - Can not install as a proper dependency due to circular dependency
-                "@langchain/community/chat_models/togetherai");
+                "@langchain/community/chat_models/togetherai")));
                 return new ChatTogetherAI({ model, ...passedParams });
             }
             default: {
@@ -169,7 +204,6 @@ function _inferModelProvider(modelName) {
         return undefined;
     }
 }
-exports._inferModelProvider = _inferModelProvider;
 /**
  * Internal class used to create chat models.
  *
@@ -651,4 +685,3 @@ fields) {
         });
     }
 }
-exports.initChatModel = initChatModel;