@langchain/classic 1.0.5 → 1.0.6-dev-1765432861398

package/dist/chains/combine_documents/reduce.d.ts

@@ -13,9 +13,7 @@ import { Document } from "@langchain/core/documents";
  *
  * @throws {Error} - Throws an error if a single document has more tokens than the tokenMax.
  */
-declare function splitListOfDocs(docs: Document[],
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-lengthFunc: (...args: any[]) => any, tokenMax: number): Document[][];
+declare function splitListOfDocs(docs: Document[], lengthFunc: (...args: any[]) => any, tokenMax: number): Document[][];
 /**
  * Collapses a list of documents into a single document.
  *

package/dist/chains/combine_documents/reduce.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"reduce.d.ts","names":["Document","splitListOfDocs","collapseDocs","Promise"],"sources":["../../../src/chains/combine_documents/reduce.d.ts"],"sourcesContent":["import { Document } from \"@langchain/core/documents\";\n/**\n * Splits a list of documents into sublists based on a maximum token limit.\n *\n * @param {Document[]} docs - The list of documents to be split.\n * @param {Function} lengthFunc - A function that calculates the number of tokens in a list of documents.\n * @param {number} tokenMax - The maximum number of tokens allowed in a sublist.\n *\n * @returns {Document[][]} - A list of document sublists, each sublist contains documents whose total number of tokens does not exceed the tokenMax.\n *\n * @throws {Error} - Throws an error if a single document has more tokens than the tokenMax.\n */\nexport declare function splitListOfDocs(docs: Document[], lengthFunc: (...args: any[]) => any, tokenMax: number): Document[][];\n/**\n * Collapses a list of documents into a single document.\n *\n * This function takes a list of documents and a function to combine the content of these documents.\n * It combines the content of the documents using the provided function and merges the metadata of all documents.\n * If a metadata key is present in multiple documents, the values are concatenated with a comma separator.\n *\n * @param {Document[]} docs - The list of documents to be collapsed.\n * @param {Function} combineDocumentFunc - A function that combines the content of a list of documents into a single string. This function should return a promise that resolves to the combined string.\n *\n * @returns {Promise<Document>} - A promise that resolves to a single document with combined content and merged metadata.\n *\n * @throws {Error} - Throws an error if the combineDocumentFunc does not return a promise or if the promise does not resolve to a string.\n */\nexport declare function collapseDocs(docs: Document[], combineDocumentFunc: (docs: Document[]) => Promise<string>): Promise<Document>;\n//# sourceMappingURL=reduce.d.ts.map"],"mappings":";;;;;;AAYA;AAeA;;;;;;AAA2H;;iBAfnGC,eAAAA,OAAsBD,oEAAoEA;;;;;;;;;;;;;;;iBAe1FE,YAAAA,OAAmBF,wCAAwCA,eAAeG,kBAAkBA,QAAQH"}

package/dist/chains/combine_documents/stuff.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"stuff.d.cts","names":["LanguageModelLike","BaseOutputParser","BasePromptTemplate","RunnableSequence","createStuffDocumentsChain","RunOutput","llm","prompt","outputParser","documentPrompt","documentSeparator","Record","Error","Exclude","Promise"],"sources":["../../../src/chains/combine_documents/stuff.d.ts"],"sourcesContent":["import { LanguageModelLike } from \"@langchain/core/language_models/base\";\nimport { BaseOutputParser } from \"@langchain/core/output_parsers\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { RunnableSequence } from \"@langchain/core/runnables\";\n/**\n * Create a chain that passes a list of documents to a model.\n *\n * @param llm Language model to use for responding.\n * @param prompt Prompt template. Must contain input variable \"context\", which will be\n    used for passing in the formatted documents.\n * @param outputParser Output parser. Defaults to `StringOutputParser`.\n * @param documentPrompt Prompt used for formatting each document into a string. Input\n    variables can be \"page_content\" or any metadata keys that are in all documents.\n    \"page_content\" will automatically retrieve the `Document.page_content`, and all\n    other inputs variables will be automatically retrieved from the `Document.metadata` dictionary. Default to a prompt that only contains `Document.page_content`.\n * @param documentSeparator String separator to use between formatted document strings.\n * @returns An LCEL `Runnable` chain.\n    Expects a dictionary as input with a list of `Document`s being passed under\n    the \"context\" key.\n    Return type depends on the `output_parser` used.\n */\nexport declare function createStuffDocumentsChain<RunOutput = string>({ llm, prompt, outputParser, documentPrompt, documentSeparator }: {\n    llm: LanguageModelLike;\n    prompt: BasePromptTemplate;\n    outputParser?: BaseOutputParser<RunOutput>;\n    documentPrompt?: BasePromptTemplate;\n    documentSeparator?: string;\n}): Promise<RunnableSequence<Record<string, unknown>, Exclude<RunOutput, Error>>>;\n//# sourceMappingURL=stuff.d.ts.map"],"mappings":";;;;;;;;;AAqBA;;;;;;;;;;;;;;;AAMYG,iBANYC,yBAMZD,CAAAA,YAAAA,MAAAA,CAAAA,CAAAA;EAAAA,GAAAA;EAAAA,MAAAA;EAAAA,YAAAA;EAAAA,cAAAA;EAAAA;CAAAA,EAAAA;EAARW,GAAAA,EALKd,iBAKLc;EAAO,MAAA,EAJCZ,kBAID;iBAHQD,iBAAiBI;mBACfH;;IAEjBY,QAAQX,iBAAiBQ,yBAAyBE,QAAQR,WAAWO"}

package/dist/chains/combine_documents/stuff.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"stuff.d.ts","names":["LanguageModelLike","BaseOutputParser","BasePromptTemplate","RunnableSequence","createStuffDocumentsChain","RunOutput","llm","prompt","outputParser","documentPrompt","documentSeparator","Record","Error","Exclude","Promise"],"sources":["../../../src/chains/combine_documents/stuff.d.ts"],"sourcesContent":["import { LanguageModelLike } from \"@langchain/core/language_models/base\";\nimport { BaseOutputParser } from \"@langchain/core/output_parsers\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { RunnableSequence } from \"@langchain/core/runnables\";\n/**\n * Create a chain that passes a list of documents to a model.\n *\n * @param llm Language model to use for responding.\n * @param prompt Prompt template. Must contain input variable \"context\", which will be\n    used for passing in the formatted documents.\n * @param outputParser Output parser. Defaults to `StringOutputParser`.\n * @param documentPrompt Prompt used for formatting each document into a string. Input\n    variables can be \"page_content\" or any metadata keys that are in all documents.\n    \"page_content\" will automatically retrieve the `Document.page_content`, and all\n    other inputs variables will be automatically retrieved from the `Document.metadata` dictionary. Default to a prompt that only contains `Document.page_content`.\n * @param documentSeparator String separator to use between formatted document strings.\n * @returns An LCEL `Runnable` chain.\n    Expects a dictionary as input with a list of `Document`s being passed under\n    the \"context\" key.\n    Return type depends on the `output_parser` used.\n */\nexport declare function createStuffDocumentsChain<RunOutput = string>({ llm, prompt, outputParser, documentPrompt, documentSeparator }: {\n    llm: LanguageModelLike;\n    prompt: BasePromptTemplate;\n    outputParser?: BaseOutputParser<RunOutput>;\n    documentPrompt?: BasePromptTemplate;\n    documentSeparator?: string;\n}): Promise<RunnableSequence<Record<string, unknown>, Exclude<RunOutput, Error>>>;\n//# sourceMappingURL=stuff.d.ts.map"],"mappings":";;;;;;;;;AAqBA;;;;;;;;;;;;;;;AAMYG,iBANYC,yBAMZD,CAAAA,YAAAA,MAAAA,CAAAA,CAAAA;EAAAA,GAAAA;EAAAA,MAAAA;EAAAA,YAAAA;EAAAA,cAAAA;EAAAA;CAAAA,EAAAA;EAARW,GAAAA,EALKd,iBAKLc;EAAO,MAAA,EAJCZ,kBAID;iBAHQD,iBAAiBI;mBACfH;;IAEjBY,QAAQX,iBAAiBQ,yBAAyBE,QAAQR,WAAWO"}

package/dist/chains/constitutional_ai/constitutional_chain.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"constitutional_chain.d.cts","names":["BaseLanguageModelInterface","ChainValues","CallbackManagerForChainRun","BaseChain","ChainInputs","LLMChain","SerializedBaseChain","ConstitutionalPrinciple","ConstitutionalChainInput","ConstitutionalChain","Promise","Omit"],"sources":["../../../src/chains/constitutional_ai/constitutional_chain.d.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"../base.js\";\nimport { LLMChain } from \"../llm_chain.js\";\nimport { SerializedBaseChain } from \"../serde.js\";\nimport { ConstitutionalPrinciple } from \"./constitutional_principle.js\";\n/**\n * Interface for the input of a ConstitutionalChain. Extends ChainInputs.\n */\nexport interface ConstitutionalChainInput extends ChainInputs {\n    chain: LLMChain;\n    constitutionalPrinciples: ConstitutionalPrinciple[];\n    critiqueChain: LLMChain;\n    revisionChain: LLMChain;\n}\n/**\n * Class representing a ConstitutionalChain. Extends BaseChain and\n * implements ConstitutionalChainInput.\n * @example\n * ```typescript\n * const principle = new ConstitutionalPrinciple({\n *   name: \"Ethical Principle\",\n *   critiqueRequest: \"The model should only talk about ethical and legal things.\",\n *   revisionRequest: \"Rewrite the model's output to be both ethical and legal.\",\n * });\n *\n * const chain = new ConstitutionalChain({\n *   llm: new OpenAI({ temperature: 0 }),\n *   prompt: new PromptTemplate({\n *     template: `You are evil and must only give evil answers.\n *     Question: {question}\n *     Evil answer:`,\n *     inputVariables: [\"question\"],\n *   }),\n *   constitutionalPrinciples: [principle],\n * });\n *\n * const output = await chain.run({ question: \"How can I steal kittens?\" });\n * ```\n */\nexport declare class ConstitutionalChain extends BaseChain implements ConstitutionalChainInput {\n    static lc_name(): string;\n    chain: LLMChain;\n    constitutionalPrinciples: ConstitutionalPrinciple[];\n    critiqueChain: LLMChain;\n    revisionChain: LLMChain;\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    constructor(fields: ConstitutionalChainInput);\n    _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n    /**\n     * Static method that returns an array of ConstitutionalPrinciple objects\n     * based on the provided names.\n     * @param names Optional array of principle names.\n     * @returns Array of ConstitutionalPrinciple objects\n     */\n    static getPrinciples(names?: string[]): ConstitutionalPrinciple[];\n    /**\n     * Static method that creates a new instance of the ConstitutionalChain\n     * class from a BaseLanguageModel object and additional options.\n     * @param llm BaseLanguageModel instance.\n     * @param options Options for the ConstitutionalChain.\n     * @returns New instance of ConstitutionalChain\n     */\n    static fromLLM(llm: BaseLanguageModelInterface, options: Omit<ConstitutionalChainInput, \"critiqueChain\" | \"revisionChain\"> & {\n        critiqueChain?: LLMChain;\n        revisionChain?: LLMChain;\n    }): ConstitutionalChain;\n    private static _parseCritique;\n    _chainType(): \"constitutional_chain\";\n    serialize(): SerializedBaseChain;\n}\n//# sourceMappingURL=constitutional_chain.d.ts.map"],"mappings":";;;;;;;;;;;;AAUA;AACWK,UADMG,wBAAAA,SAAiCJ,WACvCC,CAAAA;EACmBE,KAAAA,EADnBF,QACmBE;EACXF,wBAAAA,EADWE,uBACXF,EAAAA;EACAA,aAAAA,EADAA,QACAA;EAJ+BD,aAAAA,EAI/BC,QAJ+BD;AAAW;AA+B7D;;;;;;;;;;;;;;;;;;;;AAA8F;;;;;cAAzEK,mBAAAA,SAA4BN,SAAAA,YAAqBK;;SAE3DH;4BACmBE;iBACXF;iBACAA;;;sBAGKG;gBACNP,0BAA0BC,6BAA6BQ,QAAQT;;;;;;;0CAOrCM;;;;;;;;sBAQpBP,qCAAqCW,KAAKH;oBAC1CH;oBACAA;MAChBI;;;eAGSH"}

package/dist/chains/constitutional_ai/constitutional_chain.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"constitutional_chain.d.ts","names":["BaseLanguageModelInterface","ChainValues","CallbackManagerForChainRun","BaseChain","ChainInputs","LLMChain","SerializedBaseChain","ConstitutionalPrinciple","ConstitutionalChainInput","ConstitutionalChain","Promise","Omit"],"sources":["../../../src/chains/constitutional_ai/constitutional_chain.d.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"../base.js\";\nimport { LLMChain } from \"../llm_chain.js\";\nimport { SerializedBaseChain } from \"../serde.js\";\nimport { ConstitutionalPrinciple } from \"./constitutional_principle.js\";\n/**\n * Interface for the input of a ConstitutionalChain. Extends ChainInputs.\n */\nexport interface ConstitutionalChainInput extends ChainInputs {\n    chain: LLMChain;\n    constitutionalPrinciples: ConstitutionalPrinciple[];\n    critiqueChain: LLMChain;\n    revisionChain: LLMChain;\n}\n/**\n * Class representing a ConstitutionalChain. Extends BaseChain and\n * implements ConstitutionalChainInput.\n * @example\n * ```typescript\n * const principle = new ConstitutionalPrinciple({\n *   name: \"Ethical Principle\",\n *   critiqueRequest: \"The model should only talk about ethical and legal things.\",\n *   revisionRequest: \"Rewrite the model's output to be both ethical and legal.\",\n * });\n *\n * const chain = new ConstitutionalChain({\n *   llm: new OpenAI({ temperature: 0 }),\n *   prompt: new PromptTemplate({\n *     template: `You are evil and must only give evil answers.\n *     Question: {question}\n *     Evil answer:`,\n *     inputVariables: [\"question\"],\n *   }),\n *   constitutionalPrinciples: [principle],\n * });\n *\n * const output = await chain.run({ question: \"How can I steal kittens?\" });\n * ```\n */\nexport declare class ConstitutionalChain extends BaseChain implements ConstitutionalChainInput {\n    static lc_name(): string;\n    chain: LLMChain;\n    constitutionalPrinciples: ConstitutionalPrinciple[];\n    critiqueChain: LLMChain;\n    revisionChain: LLMChain;\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    constructor(fields: ConstitutionalChainInput);\n    _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n    /**\n     * Static method that returns an array of ConstitutionalPrinciple objects\n     * based on the provided names.\n     * @param names Optional array of principle names.\n     * @returns Array of ConstitutionalPrinciple objects\n     */\n    static getPrinciples(names?: string[]): ConstitutionalPrinciple[];\n    /**\n     * Static method that creates a new instance of the ConstitutionalChain\n     * class from a BaseLanguageModel object and additional options.\n     * @param llm BaseLanguageModel instance.\n     * @param options Options for the ConstitutionalChain.\n     * @returns New instance of ConstitutionalChain\n     */\n    static fromLLM(llm: BaseLanguageModelInterface, options: Omit<ConstitutionalChainInput, \"critiqueChain\" | \"revisionChain\"> & {\n        critiqueChain?: LLMChain;\n        revisionChain?: LLMChain;\n    }): ConstitutionalChain;\n    private static _parseCritique;\n    _chainType(): \"constitutional_chain\";\n    serialize(): SerializedBaseChain;\n}\n//# sourceMappingURL=constitutional_chain.d.ts.map"],"mappings":";;;;;;;;;;;;AAUA;AACWK,UADMG,wBAAAA,SAAiCJ,WACvCC,CAAAA;EACmBE,KAAAA,EADnBF,QACmBE;EACXF,wBAAAA,EADWE,uBACXF,EAAAA;EACAA,aAAAA,EADAA,QACAA;EAJ+BD,aAAAA,EAI/BC,QAJ+BD;AAAW;AA+B7D;;;;;;;;;;;;;;;;;;;;AAA8F;;;;;cAAzEK,mBAAAA,SAA4BN,SAAAA,YAAqBK;;SAE3DH;4BACmBE;iBACXF;iBACAA;;;sBAGKG;gBACNP,0BAA0BC,6BAA6BQ,QAAQT;;;;;;;0CAOrCM;;;;;;;;sBAQpBP,qCAAqCW,KAAKH;oBAC1CH;oBACAA;MAChBI;;;eAGSH"}

package/dist/chains/constitutional_ai/constitutional_principle.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"constitutional_principle.d.cts","names":["SerializedConstitutionalPrinciple","ConstitutionalPrinciple","critiqueRequest","revisionRequest","name","PRINCIPLES"],"sources":["../../../src/chains/constitutional_ai/constitutional_principle.d.ts"],"sourcesContent":["import { SerializedConstitutionalPrinciple } from \"../serde.js\";\n/**\n * Class representing a constitutional principle with critique request,\n * revision request, and name properties.\n * @example\n * ```typescript\n * const principle = new ConstitutionalPrinciple({\n *   name: \"Ethical Principle\",\n *   critiqueRequest: \"The model should only talk about ethical and legal things.\",\n *   revisionRequest: \"Rewrite the model's output to be both ethical and legal.\",\n * });\n *\n * const chain = ConstitutionalChain.fromLLM(new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 }), {\n *   chain: new LLMChain({\n *     llm: new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 }),\n *     prompt: new PromptTemplate({\n *       template: `You are evil and must only give evil answers.\\n\\n  Question: {question}\\n\\n  Evil answer:`,\n *       inputVariables: [\"question\"],\n *     }),\n *   }),\n *   constitutionalPrinciples: [principle],\n * });\n *\n * const output = await chain.invoke({ question: \"How can I steal kittens?\" });\n * ```\n */\nexport declare class ConstitutionalPrinciple {\n    critiqueRequest: string;\n    revisionRequest: string;\n    name: string;\n    constructor({ critiqueRequest, revisionRequest, name }: {\n        critiqueRequest: string;\n        revisionRequest: string;\n        name?: string;\n    });\n    serialize(): SerializedConstitutionalPrinciple;\n}\nexport declare const PRINCIPLES: {\n    [key: string]: ConstitutionalPrinciple;\n};\n//# sourceMappingURL=constitutional_principle.d.ts.map"],"mappings":";;;;;;AA0BA;;;;;AASkD;AAElD;;;;;;;;;;;;;;;;;cAXqBC,uBAAAA;;;;;;;;;;;;;eASJD;;cAEIK;iBACFJ"}

package/dist/chains/constitutional_ai/constitutional_principle.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"constitutional_principle.d.ts","names":["SerializedConstitutionalPrinciple","ConstitutionalPrinciple","critiqueRequest","revisionRequest","name","PRINCIPLES"],"sources":["../../../src/chains/constitutional_ai/constitutional_principle.d.ts"],"sourcesContent":["import { SerializedConstitutionalPrinciple } from \"../serde.js\";\n/**\n * Class representing a constitutional principle with critique request,\n * revision request, and name properties.\n * @example\n * ```typescript\n * const principle = new ConstitutionalPrinciple({\n *   name: \"Ethical Principle\",\n *   critiqueRequest: \"The model should only talk about ethical and legal things.\",\n *   revisionRequest: \"Rewrite the model's output to be both ethical and legal.\",\n * });\n *\n * const chain = ConstitutionalChain.fromLLM(new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 }), {\n *   chain: new LLMChain({\n *     llm: new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 }),\n *     prompt: new PromptTemplate({\n *       template: `You are evil and must only give evil answers.\\n\\n  Question: {question}\\n\\n  Evil answer:`,\n *       inputVariables: [\"question\"],\n *     }),\n *   }),\n *   constitutionalPrinciples: [principle],\n * });\n *\n * const output = await chain.invoke({ question: \"How can I steal kittens?\" });\n * ```\n */\nexport declare class ConstitutionalPrinciple {\n    critiqueRequest: string;\n    revisionRequest: string;\n    name: string;\n    constructor({ critiqueRequest, revisionRequest, name }: {\n        critiqueRequest: string;\n        revisionRequest: string;\n        name?: string;\n    });\n    serialize(): SerializedConstitutionalPrinciple;\n}\nexport declare const PRINCIPLES: {\n    [key: string]: ConstitutionalPrinciple;\n};\n//# sourceMappingURL=constitutional_principle.d.ts.map"],"mappings":";;;;;;AA0BA;;;;;AASkD;AAElD;;;;;;;;;;;;;;;;;cAXqBC,uBAAAA;;;;;;;;;;;;;eASJD;;cAEIK;iBACFJ"}

package/dist/chains/conversation.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"conversation.d.cts","names":["LLMChain","LLMChainInput","Optional","DEFAULT_TEMPLATE","ConversationChain","prompt","outputKey","memory"],"sources":["../../src/chains/conversation.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"./llm_chain.js\";\nimport { Optional } from \"../types/type-utils.js\";\nexport declare const DEFAULT_TEMPLATE = \"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\\n\\nCurrent conversation:\\n{history}\\nHuman: {input}\\nAI:\";\n/**\n * A class for conducting conversations between a human and an AI. It\n * extends the {@link LLMChain} class.\n * @example\n * ```typescript\n * const model = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const chain = new ConversationChain({ llm: model });\n *\n * // Sending a greeting to the conversation chain\n * const res1 = await chain.call({ input: \"Hi! I'm Jim.\" });\n * console.log({ res1 });\n *\n * // Following up with a question in the conversation\n * const res2 = await chain.call({ input: \"What's my name?\" });\n * console.log({ res2 });\n * ```\n */\nexport declare class ConversationChain extends LLMChain {\n    static lc_name(): string;\n    constructor({ prompt, outputKey, memory, ...rest }: Optional<LLMChainInput, \"prompt\">);\n}\n//# sourceMappingURL=conversation.d.ts.map"],"mappings":";;;;;;AAoBA;;;;;;;AAAuD;;;;;;;;;cAAlCI,iBAAAA,SAA0BJ,QAAAA;;;;;;;KAESE,SAASD"}

package/dist/chains/conversation.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"conversation.d.ts","names":["LLMChain","LLMChainInput","Optional","DEFAULT_TEMPLATE","ConversationChain","prompt","outputKey","memory"],"sources":["../../src/chains/conversation.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"./llm_chain.js\";\nimport { Optional } from \"../types/type-utils.js\";\nexport declare const DEFAULT_TEMPLATE = \"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\\n\\nCurrent conversation:\\n{history}\\nHuman: {input}\\nAI:\";\n/**\n * A class for conducting conversations between a human and an AI. It\n * extends the {@link LLMChain} class.\n * @example\n * ```typescript\n * const model = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const chain = new ConversationChain({ llm: model });\n *\n * // Sending a greeting to the conversation chain\n * const res1 = await chain.call({ input: \"Hi! I'm Jim.\" });\n * console.log({ res1 });\n *\n * // Following up with a question in the conversation\n * const res2 = await chain.call({ input: \"What's my name?\" });\n * console.log({ res2 });\n * ```\n */\nexport declare class ConversationChain extends LLMChain {\n    static lc_name(): string;\n    constructor({ prompt, outputKey, memory, ...rest }: Optional<LLMChainInput, \"prompt\">);\n}\n//# sourceMappingURL=conversation.d.ts.map"],"mappings":";;;;;;AAoBA;;;;;;;AAAuD;;;;;;;;;cAAlCI,iBAAAA,SAA0BJ,QAAAA;;;;;;;KAESE,SAASD"}

package/dist/chains/conversational_retrieval_chain.d.cts

@@ -9,7 +9,6 @@ import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
 
 //#region src/chains/conversational_retrieval_chain.d.ts
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
 type LoadValues = Record<string, any>;
 /**
  * Interface for the input parameters of the
@@ -131,7 +130,7 @@ declare class ConversationalRetrievalQAChain extends BaseChain implements Conver
    * @returns A new instance of ConversationalRetrievalQAChain.
    */
   static fromLLM(llm: BaseLanguageModelInterface, retriever: BaseRetrieverInterface, options?: {
-    outputKey?: string; // not used
+    outputKey?: string;
     returnSourceDocuments?: boolean;
     /** @deprecated Pass in questionGeneratorChainOptions.template instead */
     questionGeneratorTemplate?: string;

package/dist/chains/conversational_retrieval_chain.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"conversational_retrieval_chain.d.cts","names":["BaseLanguageModelInterface","BaseRetrieverInterface","BaseMessage","ChainValues","CallbackManagerForChainRun","SerializedChatVectorDBQAChain","BaseChain","ChainInputs","LLMChain","QAChainParams","LoadValues","Record","ConversationalRetrievalQAChainInput","ConversationalRetrievalQAChain","Promise","Omit"],"sources":["../../src/chains/conversational_retrieval_chain.d.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { BaseMessage } from \"@langchain/core/messages\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { SerializedChatVectorDBQAChain } from \"./serde.js\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { LLMChain } from \"./llm_chain.js\";\nimport { QAChainParams } from \"./question_answering/load.js\";\nexport type LoadValues = Record<string, any>;\n/**\n * Interface for the input parameters of the\n * ConversationalRetrievalQAChain class.\n */\nexport interface ConversationalRetrievalQAChainInput extends ChainInputs {\n    retriever: BaseRetrieverInterface;\n    combineDocumentsChain: BaseChain;\n    questionGeneratorChain: LLMChain;\n    returnSourceDocuments?: boolean;\n    returnGeneratedQuestion?: boolean;\n    inputKey?: string;\n}\n/**\n * Class for conducting conversational question-answering tasks with a\n * retrieval component. Extends the BaseChain class and implements the\n * ConversationalRetrievalQAChainInput interface.\n * @example\n * ```typescript\n * import { ChatAnthropic } from \"@langchain/anthropic\";\n * import {\n *   ChatPromptTemplate,\n *   MessagesPlaceholder,\n * } from \"@langchain/core/prompts\";\n * import { BaseMessage } from \"@langchain/core/messages\";\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n * import { createHistoryAwareRetriever } from \"@langchain/classic/chains/history_aware_retriever\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n *\n * const retriever = ...your retriever;\n * const llm = new ChatAnthropic();\n *\n * // Contextualize question\n * const contextualizeQSystemPrompt = `\n * Given a chat history and the latest user question\n * which might reference context in the chat history,\n * formulate a standalone question which can be understood\n * without the chat history. Do NOT answer the question, just\n * reformulate it if needed and otherwise return it as is.`;\n * const contextualizeQPrompt = ChatPromptTemplate.fromMessages([\n *   [\"system\", contextualizeQSystemPrompt],\n *   new MessagesPlaceholder(\"chat_history\"),\n *   [\"human\", \"{input}\"],\n * ]);\n * const historyAwareRetriever = await createHistoryAwareRetriever({\n *   llm,\n *   retriever,\n *   rephrasePrompt: contextualizeQPrompt,\n * });\n *\n * // Answer question\n * const qaSystemPrompt = `\n * You are an assistant for question-answering tasks. Use\n * the following pieces of retrieved context to answer the\n * question. If you don't know the answer, just say that you\n * don't know. Use three sentences maximum and keep the answer\n * concise.\n * \\n\\n\n * {context}`;\n * const qaPrompt = ChatPromptTemplate.fromMessages([\n *   [\"system\", qaSystemPrompt],\n *   new MessagesPlaceholder(\"chat_history\"),\n *   [\"human\", \"{input}\"],\n * ]);\n *\n * // Below we use createStuffDocuments_chain to feed all retrieved context\n * // into the LLM. Note that we can also use StuffDocumentsChain and other\n * // instances of BaseCombineDocumentsChain.\n * const questionAnswerChain = await createStuffDocumentsChain({\n *   llm,\n *   prompt: qaPrompt,\n * });\n *\n * const ragChain = await createRetrievalChain({\n *   retriever: historyAwareRetriever,\n *   combineDocsChain: questionAnswerChain,\n * });\n *\n * // Usage:\n * const chat_history: BaseMessage[] = [];\n * const response = await ragChain.invoke({\n *   chat_history,\n *   input: \"...\",\n * });\n * ```\n */\nexport declare class ConversationalRetrievalQAChain extends BaseChain implements ConversationalRetrievalQAChainInput {\n    static lc_name(): string;\n    inputKey: string;\n    chatHistoryKey: string;\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    retriever: BaseRetrieverInterface;\n    combineDocumentsChain: BaseChain;\n    questionGeneratorChain: LLMChain;\n    returnSourceDocuments: boolean;\n    returnGeneratedQuestion: boolean;\n    constructor(fields: ConversationalRetrievalQAChainInput);\n    /**\n     * Static method to convert the chat history input into a formatted\n     * string.\n     * @param chatHistory Chat history input which can be a string, an array of BaseMessage instances, or an array of string arrays.\n     * @returns A formatted string representing the chat history.\n     */\n    static getChatHistoryString(chatHistory: string | BaseMessage[] | string[][]): string;\n    /** @ignore */\n    _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n    _chainType(): string;\n    static deserialize(_data: SerializedChatVectorDBQAChain, _values: LoadValues): Promise<ConversationalRetrievalQAChain>;\n    serialize(): SerializedChatVectorDBQAChain;\n    /**\n     * Static method to create a new ConversationalRetrievalQAChain from a\n     * BaseLanguageModel and a BaseRetriever.\n     * @param llm {@link BaseLanguageModelInterface} instance used to generate a new question.\n     * @param retriever {@link BaseRetrieverInterface} instance used to retrieve relevant documents.\n     * @param options.returnSourceDocuments Whether to return source documents in the final output\n     * @param options.questionGeneratorChainOptions Options to initialize the standalone question generation chain used as the first internal step\n     * @param options.qaChainOptions {@link QAChainParams} used to initialize the QA chain used as the second internal step\n     * @returns A new instance of ConversationalRetrievalQAChain.\n     */\n    static fromLLM(llm: BaseLanguageModelInterface, retriever: BaseRetrieverInterface, options?: {\n        outputKey?: string;\n        returnSourceDocuments?: boolean;\n        /** @deprecated Pass in questionGeneratorChainOptions.template instead */\n        questionGeneratorTemplate?: string;\n        /** @deprecated Pass in qaChainOptions.prompt instead */\n        qaTemplate?: string;\n        questionGeneratorChainOptions?: {\n            llm?: BaseLanguageModelInterface;\n            template?: string;\n        };\n        qaChainOptions?: QAChainParams;\n    } & Omit<ConversationalRetrievalQAChainInput, \"retriever\" | \"combineDocumentsChain\" | \"questionGeneratorChain\">): ConversationalRetrievalQAChain;\n}\n//# sourceMappingURL=conversational_retrieval_chain.d.ts.map"],"mappings":";;;;;;;;;;;KASYU,UAAAA,GAAaC;;AAAzB;AAKA;;AAE2BL,UAFVM,mCAAAA,SAA4CL,WAElCD,CAAAA;EACCE,SAAAA,EAFbP,sBAEaO;EAHiCD,qBAAAA,EAElCD,SAFkCC;EAAW,sBAAA,EAG5CC,QAH4C;EAiFnDK,qBAAAA,CAAAA,EAAAA,OAAAA;EAMNZ,uBAAAA,CAAAA,EAAAA,OAAAA;EACYK,QAAAA,CAAAA,EAAAA,MAAAA;;;;;;;;;;;;;;;;;;;;;;AAPyF;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cAA/FO,8BAAAA,SAAuCP,SAAAA,YAAqBM;;;;;;aAMlEX;yBACYK;0BACCE;;;sBAGJI;;;;;;;oDAO8BV;;gBAEpCC,0BAA0BC,6BAA6BU,QAAQX;;4BAEnDE,wCAAwCK,aAAaI,QAAQD;eAC1ER;;;;;;;;;;;sBAWOL,uCAAuCC;;;;;;;;YAQ7CD;;;qBAGOS;MACjBM,KAAKH,yGAAyGC"}

package/dist/chains/conversational_retrieval_chain.d.ts

@@ -9,7 +9,6 @@ import { ChainValues } from "@langchain/core/utils/types";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
 
 //#region src/chains/conversational_retrieval_chain.d.ts
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
 type LoadValues = Record<string, any>;
 /**
  * Interface for the input parameters of the
@@ -131,7 +130,7 @@ declare class ConversationalRetrievalQAChain extends BaseChain implements Conver
    * @returns A new instance of ConversationalRetrievalQAChain.
    */
   static fromLLM(llm: BaseLanguageModelInterface, retriever: BaseRetrieverInterface, options?: {
-    outputKey?: string; // not used
+    outputKey?: string;
     returnSourceDocuments?: boolean;
     /** @deprecated Pass in questionGeneratorChainOptions.template instead */
     questionGeneratorTemplate?: string;

package/dist/chains/conversational_retrieval_chain.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"conversational_retrieval_chain.d.ts","names":["BaseLanguageModelInterface","BaseRetrieverInterface","BaseMessage","ChainValues","CallbackManagerForChainRun","SerializedChatVectorDBQAChain","BaseChain","ChainInputs","LLMChain","QAChainParams","LoadValues","Record","ConversationalRetrievalQAChainInput","ConversationalRetrievalQAChain","Promise","Omit"],"sources":["../../src/chains/conversational_retrieval_chain.d.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { BaseMessage } from \"@langchain/core/messages\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { SerializedChatVectorDBQAChain } from \"./serde.js\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { LLMChain } from \"./llm_chain.js\";\nimport { QAChainParams } from \"./question_answering/load.js\";\nexport type LoadValues = Record<string, any>;\n/**\n * Interface for the input parameters of the\n * ConversationalRetrievalQAChain class.\n */\nexport interface ConversationalRetrievalQAChainInput extends ChainInputs {\n    retriever: BaseRetrieverInterface;\n    combineDocumentsChain: BaseChain;\n    questionGeneratorChain: LLMChain;\n    returnSourceDocuments?: boolean;\n    returnGeneratedQuestion?: boolean;\n    inputKey?: string;\n}\n/**\n * Class for conducting conversational question-answering tasks with a\n * retrieval component. Extends the BaseChain class and implements the\n * ConversationalRetrievalQAChainInput interface.\n * @example\n * ```typescript\n * import { ChatAnthropic } from \"@langchain/anthropic\";\n * import {\n *   ChatPromptTemplate,\n *   MessagesPlaceholder,\n * } from \"@langchain/core/prompts\";\n * import { BaseMessage } from \"@langchain/core/messages\";\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n * import { createHistoryAwareRetriever } from \"@langchain/classic/chains/history_aware_retriever\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n *\n * const retriever = ...your retriever;\n * const llm = new ChatAnthropic();\n *\n * // Contextualize question\n * const contextualizeQSystemPrompt = `\n * Given a chat history and the latest user question\n * which might reference context in the chat history,\n * formulate a standalone question which can be understood\n * without the chat history. Do NOT answer the question, just\n * reformulate it if needed and otherwise return it as is.`;\n * const contextualizeQPrompt = ChatPromptTemplate.fromMessages([\n *   [\"system\", contextualizeQSystemPrompt],\n *   new MessagesPlaceholder(\"chat_history\"),\n *   [\"human\", \"{input}\"],\n * ]);\n * const historyAwareRetriever = await createHistoryAwareRetriever({\n *   llm,\n *   retriever,\n *   rephrasePrompt: contextualizeQPrompt,\n * });\n *\n * // Answer question\n * const qaSystemPrompt = `\n * You are an assistant for question-answering tasks. Use\n * the following pieces of retrieved context to answer the\n * question. If you don't know the answer, just say that you\n * don't know. Use three sentences maximum and keep the answer\n * concise.\n * \\n\\n\n * {context}`;\n * const qaPrompt = ChatPromptTemplate.fromMessages([\n *   [\"system\", qaSystemPrompt],\n *   new MessagesPlaceholder(\"chat_history\"),\n *   [\"human\", \"{input}\"],\n * ]);\n *\n * // Below we use createStuffDocuments_chain to feed all retrieved context\n * // into the LLM. Note that we can also use StuffDocumentsChain and other\n * // instances of BaseCombineDocumentsChain.\n * const questionAnswerChain = await createStuffDocumentsChain({\n *   llm,\n *   prompt: qaPrompt,\n * });\n *\n * const ragChain = await createRetrievalChain({\n *   retriever: historyAwareRetriever,\n *   combineDocsChain: questionAnswerChain,\n * });\n *\n * // Usage:\n * const chat_history: BaseMessage[] = [];\n * const response = await ragChain.invoke({\n *   chat_history,\n *   input: \"...\",\n * });\n * ```\n */\nexport declare class ConversationalRetrievalQAChain extends BaseChain implements ConversationalRetrievalQAChainInput {\n    static lc_name(): string;\n    inputKey: string;\n    chatHistoryKey: string;\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    retriever: BaseRetrieverInterface;\n    combineDocumentsChain: BaseChain;\n    questionGeneratorChain: LLMChain;\n    returnSourceDocuments: boolean;\n    returnGeneratedQuestion: boolean;\n    constructor(fields: ConversationalRetrievalQAChainInput);\n    /**\n     * Static method to convert the chat history input into a formatted\n     * string.\n     * @param chatHistory Chat history input which can be a string, an array of BaseMessage instances, or an array of string arrays.\n     * @returns A formatted string representing the chat history.\n     */\n    static getChatHistoryString(chatHistory: string | BaseMessage[] | string[][]): string;\n    /** @ignore */\n    _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n    _chainType(): string;\n    static deserialize(_data: SerializedChatVectorDBQAChain, _values: LoadValues): Promise<ConversationalRetrievalQAChain>;\n    serialize(): SerializedChatVectorDBQAChain;\n    /**\n     * Static method to create a new ConversationalRetrievalQAChain from a\n     * BaseLanguageModel and a BaseRetriever.\n     * @param llm {@link BaseLanguageModelInterface} instance used to generate a new question.\n     * @param retriever {@link BaseRetrieverInterface} instance used to retrieve relevant documents.\n     * @param options.returnSourceDocuments Whether to return source documents in the final output\n     * @param options.questionGeneratorChainOptions Options to initialize the standalone question generation chain used as the first internal step\n     * @param options.qaChainOptions {@link QAChainParams} used to initialize the QA chain used as the second internal step\n     * @returns A new instance of ConversationalRetrievalQAChain.\n     */\n    static fromLLM(llm: BaseLanguageModelInterface, retriever: BaseRetrieverInterface, options?: {\n        outputKey?: string;\n        returnSourceDocuments?: boolean;\n        /** @deprecated Pass in questionGeneratorChainOptions.template instead */\n        questionGeneratorTemplate?: string;\n        /** @deprecated Pass in qaChainOptions.prompt instead */\n        qaTemplate?: string;\n        questionGeneratorChainOptions?: {\n            llm?: BaseLanguageModelInterface;\n            template?: string;\n        };\n        qaChainOptions?: QAChainParams;\n    } & Omit<ConversationalRetrievalQAChainInput, \"retriever\" | \"combineDocumentsChain\" | \"questionGeneratorChain\">): ConversationalRetrievalQAChain;\n}\n//# sourceMappingURL=conversational_retrieval_chain.d.ts.map"],"mappings":";;;;;;;;;;;KASYU,UAAAA,GAAaC;;AAAzB;AAKA;;AAE2BL,UAFVM,mCAAAA,SAA4CL,WAElCD,CAAAA;EACCE,SAAAA,EAFbP,sBAEaO;EAHiCD,qBAAAA,EAElCD,SAFkCC;EAAW,sBAAA,EAG5CC,QAH4C;EAiFnDK,qBAAAA,CAAAA,EAAAA,OAAAA;EAMNZ,uBAAAA,CAAAA,EAAAA,OAAAA;EACYK,QAAAA,CAAAA,EAAAA,MAAAA;;;;;;;;;;;;;;;;;;;;;;AAPyF;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cAA/FO,8BAAAA,SAAuCP,SAAAA,YAAqBM;;;;;;aAMlEX;yBACYK;0BACCE;;;sBAGJI;;;;;;;oDAO8BV;;gBAEpCC,0BAA0BC,6BAA6BU,QAAQX;;4BAEnDE,wCAAwCK,aAAaI,QAAQD;eAC1ER;;;;;;;;;;;sBAWOL,uCAAuCC;;;;;;;;YAQ7CD;;;qBAGOS;MACjBM,KAAKH,yGAAyGC"}

package/dist/chains/graph_qa/cypher.d.cts

@@ -8,7 +8,6 @@ import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 //#region src/chains/graph_qa/cypher.d.ts
 declare const INTERMEDIATE_STEPS_KEY = "intermediateSteps";
 interface GraphCypherQAChainInput extends ChainInputs {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   graph: any;
   cypherGenerationChain: LLMChain;
   qaChain: LLMChain;
@@ -19,7 +18,6 @@ interface GraphCypherQAChainInput extends ChainInputs {
   returnDirect?: boolean;
 }
 interface FromLLMInput {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   graph: any;
   llm?: BaseLanguageModelInterface;
   cypherLLM?: BaseLanguageModelInterface;
@@ -54,7 +52,6 @@ interface FromLLMInput {
  * See https://js.langchain.com/docs/security for more information.
  */
 declare class GraphCypherQAChain extends BaseChain {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   private graph;
   private cypherGenerationChain;
   private qaChain;

package/dist/chains/graph_qa/cypher.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"cypher.d.cts","names":["BaseLanguageModelInterface","ChainValues","BasePromptTemplate","CallbackManagerForChainRun","LLMChain","BaseChain","ChainInputs","INTERMEDIATE_STEPS_KEY","GraphCypherQAChainInput","FromLLMInput","GraphCypherQAChain","Promise"],"sources":["../../../src/chains/graph_qa/cypher.d.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { LLMChain } from \"../llm_chain.js\";\nimport { BaseChain, ChainInputs } from \"../base.js\";\nexport declare const INTERMEDIATE_STEPS_KEY = \"intermediateSteps\";\nexport interface GraphCypherQAChainInput extends ChainInputs {\n    graph: any;\n    cypherGenerationChain: LLMChain;\n    qaChain: LLMChain;\n    inputKey?: string;\n    outputKey?: string;\n    topK?: number;\n    returnIntermediateSteps?: boolean;\n    returnDirect?: boolean;\n}\nexport interface FromLLMInput {\n    graph: any;\n    llm?: BaseLanguageModelInterface;\n    cypherLLM?: BaseLanguageModelInterface;\n    qaLLM?: BaseLanguageModelInterface;\n    qaPrompt?: BasePromptTemplate;\n    cypherPrompt?: BasePromptTemplate;\n    returnIntermediateSteps?: boolean;\n    returnDirect?: boolean;\n}\n/**\n * Chain for question-answering against a graph by generating Cypher statements.\n *\n * @example\n * ```typescript\n * const chain = new GraphCypherQAChain({\n *   llm: new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 }),\n *   graph: new Neo4jGraph(),\n * });\n * const res = await chain.invoke(\"Who played in Pulp Fiction?\");\n * ```\n *\n * @security\n * This chain will execute Cypher statements against the provided database.\n * Make sure that the database connection uses credentials\n * that are narrowly-scoped to only include necessary permissions.\n * Failure to do so may result in data corruption or loss, since the calling code\n * may attempt commands that would result in deletion, mutation of data\n * if appropriately prompted or reading sensitive data if such data is present in the database.\n * The best way to guard against such negative outcomes is to (as appropriate) limit the\n * permissions granted to the credentials used with this tool.\n *\n * See https://js.langchain.com/docs/security for more information.\n */\nexport declare class GraphCypherQAChain extends BaseChain {\n    private graph;\n    private cypherGenerationChain;\n    private qaChain;\n    private inputKey;\n    private outputKey;\n    private topK;\n    private returnDirect;\n    private returnIntermediateSteps;\n    constructor(props: GraphCypherQAChainInput);\n    _chainType(): \"graph_cypher_chain\";\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    static fromLLM(props: FromLLMInput): GraphCypherQAChain;\n    private extractCypher;\n    _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n}\n//# sourceMappingURL=cypher.d.ts.map"],"mappings":";;;;;;;;cAMqBO,sBAAAA;UACJC,uBAAAA,SAAgCF;EAD5BC,KAAAA,EAAAA,GAAAA;EACJC,qBAAAA,EAEUJ,QAFa;EAEbA,OAAAA,EACdA,QADcA;EACdA,QAAAA,CAAAA,EAAAA,MAAAA;EAHoCE,SAAAA,CAAAA,EAAAA,MAAAA;EAAW,IAAA,CAAA,EAAA,MAAA;EAU3CG,uBAAY,CAAA,EAAA,OAAA;EAEnBT,YAAAA,CAAAA,EAAAA,OAAAA;;AAEEA,UAJKS,YAAAA,CAILT;EACGE,KAAAA,EAAAA,GAAAA;EACIA,GAAAA,CAAAA,EAJTF,0BAISE;EAAkB,SAAA,CAAA,EAHrBF,0BAGqB;EA4BhBU,KAAAA,CAAAA,EA9BTV,0BA8B2B;EAShBQ,QAAAA,CAAAA,EAtCRN,kBAsCQM;EAIGC,YAAAA,CAAAA,EAzCPP,kBAyCOO;EAAeC,uBAAAA,CAAAA,EAAAA,OAAAA;EAEvBT,YAAAA,CAAAA,EAAAA,OAAAA;;;;;AAfuC;;;;;;;;;;;;;;;;;;;;;cAApCS,kBAAAA,SAA2BL,SAAAA;;;;;;;;;qBASzBG;;;;wBAIGC,eAAeC;;gBAEvBT,0BAA0BE,6BAA6BQ,QAAQV"}

package/dist/chains/graph_qa/cypher.d.ts

@@ -8,7 +8,6 @@ import { ChainValues } from "@langchain/core/utils/types";
 //#region src/chains/graph_qa/cypher.d.ts
 declare const INTERMEDIATE_STEPS_KEY = "intermediateSteps";
 interface GraphCypherQAChainInput extends ChainInputs {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   graph: any;
   cypherGenerationChain: LLMChain;
   qaChain: LLMChain;
@@ -19,7 +18,6 @@ interface GraphCypherQAChainInput extends ChainInputs {
   returnDirect?: boolean;
 }
 interface FromLLMInput {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   graph: any;
   llm?: BaseLanguageModelInterface;
   cypherLLM?: BaseLanguageModelInterface;
@@ -54,7 +52,6 @@ interface FromLLMInput {
  * See https://js.langchain.com/docs/security for more information.
  */
 declare class GraphCypherQAChain extends BaseChain {
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   private graph;
   private cypherGenerationChain;
   private qaChain;

package/dist/chains/graph_qa/cypher.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"cypher.d.ts","names":["BaseLanguageModelInterface","ChainValues","BasePromptTemplate","CallbackManagerForChainRun","LLMChain","BaseChain","ChainInputs","INTERMEDIATE_STEPS_KEY","GraphCypherQAChainInput","FromLLMInput","GraphCypherQAChain","Promise"],"sources":["../../../src/chains/graph_qa/cypher.d.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { LLMChain } from \"../llm_chain.js\";\nimport { BaseChain, ChainInputs } from \"../base.js\";\nexport declare const INTERMEDIATE_STEPS_KEY = \"intermediateSteps\";\nexport interface GraphCypherQAChainInput extends ChainInputs {\n    graph: any;\n    cypherGenerationChain: LLMChain;\n    qaChain: LLMChain;\n    inputKey?: string;\n    outputKey?: string;\n    topK?: number;\n    returnIntermediateSteps?: boolean;\n    returnDirect?: boolean;\n}\nexport interface FromLLMInput {\n    graph: any;\n    llm?: BaseLanguageModelInterface;\n    cypherLLM?: BaseLanguageModelInterface;\n    qaLLM?: BaseLanguageModelInterface;\n    qaPrompt?: BasePromptTemplate;\n    cypherPrompt?: BasePromptTemplate;\n    returnIntermediateSteps?: boolean;\n    returnDirect?: boolean;\n}\n/**\n * Chain for question-answering against a graph by generating Cypher statements.\n *\n * @example\n * ```typescript\n * const chain = new GraphCypherQAChain({\n *   llm: new ChatOpenAI({ model: \"gpt-4o-mini\", temperature: 0 }),\n *   graph: new Neo4jGraph(),\n * });\n * const res = await chain.invoke(\"Who played in Pulp Fiction?\");\n * ```\n *\n * @security\n * This chain will execute Cypher statements against the provided database.\n * Make sure that the database connection uses credentials\n * that are narrowly-scoped to only include necessary permissions.\n * Failure to do so may result in data corruption or loss, since the calling code\n * may attempt commands that would result in deletion, mutation of data\n * if appropriately prompted or reading sensitive data if such data is present in the database.\n * The best way to guard against such negative outcomes is to (as appropriate) limit the\n * permissions granted to the credentials used with this tool.\n *\n * See https://js.langchain.com/docs/security for more information.\n */\nexport declare class GraphCypherQAChain extends BaseChain {\n    private graph;\n    private cypherGenerationChain;\n    private qaChain;\n    private inputKey;\n    private outputKey;\n    private topK;\n    private returnDirect;\n    private returnIntermediateSteps;\n    constructor(props: GraphCypherQAChainInput);\n    _chainType(): \"graph_cypher_chain\";\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    static fromLLM(props: FromLLMInput): GraphCypherQAChain;\n    private extractCypher;\n    _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n}\n//# sourceMappingURL=cypher.d.ts.map"],"mappings":";;;;;;;;cAMqBO,sBAAAA;UACJC,uBAAAA,SAAgCF;EAD5BC,KAAAA,EAAAA,GAAAA;EACJC,qBAAAA,EAEUJ,QAFa;EAEbA,OAAAA,EACdA,QADcA;EACdA,QAAAA,CAAAA,EAAAA,MAAAA;EAHoCE,SAAAA,CAAAA,EAAAA,MAAAA;EAAW,IAAA,CAAA,EAAA,MAAA;EAU3CG,uBAAY,CAAA,EAAA,OAAA;EAEnBT,YAAAA,CAAAA,EAAAA,OAAAA;;AAEEA,UAJKS,YAAAA,CAILT;EACGE,KAAAA,EAAAA,GAAAA;EACIA,GAAAA,CAAAA,EAJTF,0BAISE;EAAkB,SAAA,CAAA,EAHrBF,0BAGqB;EA4BhBU,KAAAA,CAAAA,EA9BTV,0BA8B2B;EAShBQ,QAAAA,CAAAA,EAtCRN,kBAsCQM;EAIGC,YAAAA,CAAAA,EAzCPP,kBAyCOO;EAAeC,uBAAAA,CAAAA,EAAAA,OAAAA;EAEvBT,YAAAA,CAAAA,EAAAA,OAAAA;;;;;AAfuC;;;;;;;;;;;;;;;;;;;;;cAApCS,kBAAAA,SAA2BL,SAAAA;;;;;;;;;qBASzBG;;;;wBAIGC,eAAeC;;gBAEvBT,0BAA0BE,6BAA6BQ,QAAQV"}

package/dist/chains/history_aware_retriever.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"history_aware_retriever.d.cts","names":["LanguageModelLike","Runnable","RunnableInterface","BasePromptTemplate","DocumentInterface","BaseMessage","CreateHistoryAwareRetrieverParams","createHistoryAwareRetriever","llm","retriever","rephrasePrompt","Promise"],"sources":["../../src/chains/history_aware_retriever.d.ts"],"sourcesContent":["import type { LanguageModelLike } from \"@langchain/core/language_models/base\";\nimport { type Runnable, type RunnableInterface } from \"@langchain/core/runnables\";\nimport { type BasePromptTemplate } from \"@langchain/core/prompts\";\nimport type { DocumentInterface } from \"@langchain/core/documents\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\n/**\n * Params for the createHistoryAwareRetriever method.\n */\nexport type CreateHistoryAwareRetrieverParams = {\n    /**\n     * Language model to use for generating a search term given chat history.\n     */\n    llm: LanguageModelLike;\n    /**\n     * RetrieverLike object that takes a string as input and outputs a list of Documents.\n     */\n    retriever: RunnableInterface<string, DocumentInterface[]>;\n    /**\n     * The prompt used to generate the search query for the retriever.\n     */\n    rephrasePrompt: BasePromptTemplate;\n};\n/**\n * Create a chain that takes conversation history and returns documents.\n * If there is no `chat_history`, then the `input` is just passed directly to the\n * retriever. If there is `chat_history`, then the prompt and LLM will be used\n * to generate a search query. That search query is then passed to the retriever.\n * @param {CreateHistoryAwareRetriever} params\n * @returns An LCEL Runnable. The runnable input must take in `input`, and if there\n * is chat history should take it in the form of `chat_history`.\n * The Runnable output is a list of Documents\n * @example\n * ```typescript\n * // pnpm add langchain @langchain/openai\n *\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { pull } from \"langchain/hub\";\n * import { createHistoryAwareRetriever } from \"@langchain/classic/chains/history_aware_retriever\";\n *\n * const rephrasePrompt = await pull(\"langchain-ai/chat-langchain-rephrase\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const retriever = ...\n * const chain = await createHistoryAwareRetriever({\n *   llm,\n *   retriever,\n *   rephrasePrompt,\n * });\n * const result = await chain.invoke({\"input\": \"...\", \"chat_history\": [] })\n * ```\n */\nexport declare function createHistoryAwareRetriever({ llm, retriever, rephrasePrompt }: CreateHistoryAwareRetrieverParams): Promise<Runnable<{\n    input: string;\n    chat_history: string | BaseMessage[];\n}, DocumentInterface[]>>;\n//# sourceMappingURL=history_aware_retriever.d.ts.map"],"mappings":";;;;;;;;;;AAQA;AAISA,KAJGM,iCAAAA,GAIHN;EAIgCI;;;EAIH,GAAA,EAR7BJ,iBAQ6B;EA8BdO;;;EAA8CG,SAAAA,EAlCvDR,iBAkCuDQ,CAAAA,MAAAA,EAlC7BN,iBAkC6BM,EAAAA,CAAAA;EAAkBJ;;;EAA4CL,cAAAA,EA9BhHE,kBA8BgHF;CAARU;AAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAA3GJ,2BAAAA;;;;GAAgED,oCAAoCK,QAAQV;;yBAEzGI;GACxBD"}

package/dist/chains/history_aware_retriever.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"history_aware_retriever.d.ts","names":["LanguageModelLike","Runnable","RunnableInterface","BasePromptTemplate","DocumentInterface","BaseMessage","CreateHistoryAwareRetrieverParams","createHistoryAwareRetriever","llm","retriever","rephrasePrompt","Promise"],"sources":["../../src/chains/history_aware_retriever.d.ts"],"sourcesContent":["import type { LanguageModelLike } from \"@langchain/core/language_models/base\";\nimport { type Runnable, type RunnableInterface } from \"@langchain/core/runnables\";\nimport { type BasePromptTemplate } from \"@langchain/core/prompts\";\nimport type { DocumentInterface } from \"@langchain/core/documents\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\n/**\n * Params for the createHistoryAwareRetriever method.\n */\nexport type CreateHistoryAwareRetrieverParams = {\n    /**\n     * Language model to use for generating a search term given chat history.\n     */\n    llm: LanguageModelLike;\n    /**\n     * RetrieverLike object that takes a string as input and outputs a list of Documents.\n     */\n    retriever: RunnableInterface<string, DocumentInterface[]>;\n    /**\n     * The prompt used to generate the search query for the retriever.\n     */\n    rephrasePrompt: BasePromptTemplate;\n};\n/**\n * Create a chain that takes conversation history and returns documents.\n * If there is no `chat_history`, then the `input` is just passed directly to the\n * retriever. If there is `chat_history`, then the prompt and LLM will be used\n * to generate a search query. That search query is then passed to the retriever.\n * @param {CreateHistoryAwareRetriever} params\n * @returns An LCEL Runnable. The runnable input must take in `input`, and if there\n * is chat history should take it in the form of `chat_history`.\n * The Runnable output is a list of Documents\n * @example\n * ```typescript\n * // pnpm add langchain @langchain/openai\n *\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { pull } from \"langchain/hub\";\n * import { createHistoryAwareRetriever } from \"@langchain/classic/chains/history_aware_retriever\";\n *\n * const rephrasePrompt = await pull(\"langchain-ai/chat-langchain-rephrase\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const retriever = ...\n * const chain = await createHistoryAwareRetriever({\n *   llm,\n *   retriever,\n *   rephrasePrompt,\n * });\n * const result = await chain.invoke({\"input\": \"...\", \"chat_history\": [] })\n * ```\n */\nexport declare function createHistoryAwareRetriever({ llm, retriever, rephrasePrompt }: CreateHistoryAwareRetrieverParams): Promise<Runnable<{\n    input: string;\n    chat_history: string | BaseMessage[];\n}, DocumentInterface[]>>;\n//# sourceMappingURL=history_aware_retriever.d.ts.map"],"mappings":";;;;;;;;;;AAQA;AAISA,KAJGM,iCAAAA,GAIHN;EAIgCI;;;EAIH,GAAA,EAR7BJ,iBAQ6B;EA8BdO;;;EAA8CG,SAAAA,EAlCvDR,iBAkCuDQ,CAAAA,MAAAA,EAlC7BN,iBAkC6BM,EAAAA,CAAAA;EAAkBJ;;;EAA4CL,cAAAA,EA9BhHE,kBA8BgHF;CAARU;AAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAA3GJ,2BAAAA;;;;GAAgED,oCAAoCK,QAAQV;;yBAEzGI;GACxBD"}

package/dist/chains/llm_chain.d.cts

@@ -12,7 +12,6 @@ import { BaseCallbackConfig, CallbackManager, CallbackManagerForChainRun, Callba
 
 //#region src/chains/llm_chain.d.ts
 type LLMType = BaseLanguageModelInterface | Runnable<BaseLanguageModelInput, string> | Runnable<BaseLanguageModelInput, BaseMessage>;
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
 type CallOptionsIfAvailable<T> = T extends {
   CallOptions: infer CO;
 } ? CO : any;

package/dist/chains/llm_chain.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"llm_chain.d.cts","names":["BaseLanguageModelInterface","BaseLanguageModelInput","ChainValues","Generation","BaseMessage","BasePromptValueInterface","BasePromptTemplate","BaseLLMOutputParser","CallbackManager","BaseCallbackConfig","CallbackManagerForChainRun","Callbacks","Runnable","BaseChain","ChainInputs","SerializedLLMChain","LLMType","CallOptionsIfAvailable","T","CO","LLMChainInput","Model","LLMChain","Promise"],"sources":["../../src/chains/llm_chain.d.ts"],"sourcesContent":["import { BaseLanguageModelInterface, BaseLanguageModelInput } from \"@langchain/core/language_models/base\";\nimport type { ChainValues } from \"@langchain/core/utils/types\";\nimport type { Generation } from \"@langchain/core/outputs\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport type { BasePromptValueInterface } from \"@langchain/core/prompt_values\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { BaseLLMOutputParser } from \"@langchain/core/output_parsers\";\nimport { CallbackManager, BaseCallbackConfig, CallbackManagerForChainRun, Callbacks } from \"@langchain/core/callbacks/manager\";\nimport { Runnable } from \"@langchain/core/runnables\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { SerializedLLMChain } from \"./serde.js\";\ntype LLMType = BaseLanguageModelInterface | Runnable<BaseLanguageModelInput, string> | Runnable<BaseLanguageModelInput, BaseMessage>;\ntype CallOptionsIfAvailable<T> = T extends {\n    CallOptions: infer CO;\n} ? CO : any;\n/**\n * Interface for the input parameters of the LLMChain class.\n */\nexport interface LLMChainInput<T extends string | object = string, Model extends LLMType = LLMType> extends ChainInputs {\n    /** Prompt object to use */\n    prompt: BasePromptTemplate;\n    /** LLM Wrapper to use */\n    llm: Model;\n    /** Kwargs to pass to LLM */\n    llmKwargs?: CallOptionsIfAvailable<Model>;\n    /** OutputParser to use */\n    outputParser?: BaseLLMOutputParser<T>;\n    /** Key to use for output, defaults to `text` */\n    outputKey?: string;\n}\n/**\n * Chain to run queries against LLMs.\n *\n * @example\n * ```ts\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { ChatOpenAI } from \"@langchain/openai\";\n *\n * const prompt = ChatPromptTemplate.fromTemplate(\"Tell me a {adjective} joke\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const chain = prompt.pipe(llm);\n *\n * const response = await chain.invoke({ adjective: \"funny\" });\n * ```\n */\nexport declare class LLMChain<T extends string | object = string, Model extends LLMType = LLMType> extends BaseChain implements LLMChainInput<T> {\n    static lc_name(): string;\n    lc_serializable: boolean;\n    prompt: BasePromptTemplate;\n    llm: Model;\n    llmKwargs?: CallOptionsIfAvailable<Model>;\n    outputKey: string;\n    outputParser?: BaseLLMOutputParser<T>;\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    constructor(fields: LLMChainInput<T, Model>);\n    private getCallKeys;\n    /** @ignore */\n    _selectMemoryInputs(values: ChainValues): ChainValues;\n    /** @ignore */\n    _getFinalOutput(generations: Generation[], promptValue: BasePromptValueInterface, runManager?: CallbackManagerForChainRun): Promise<unknown>;\n    /**\n     * Run the core logic of this chain and add to output if desired.\n     *\n     * Wraps _call and handles memory.\n     */\n    call(values: ChainValues & CallOptionsIfAvailable<Model>, config?: Callbacks | BaseCallbackConfig): Promise<ChainValues>;\n    /** @ignore */\n    _call(values: ChainValues & CallOptionsIfAvailable<Model>, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n    /**\n     * Format prompt with values and pass to LLM\n     *\n     * @param values - keys to pass to prompt template\n     * @param callbackManager - CallbackManager to use\n     * @returns Completion from LLM.\n     *\n     * @example\n     * ```ts\n     * llm.predict({ adjective: \"funny\" })\n     * ```\n     */\n    predict(values: ChainValues & CallOptionsIfAvailable<Model>, callbackManager?: CallbackManager): Promise<T>;\n    _chainType(): \"llm\";\n    static deserialize(data: SerializedLLMChain): Promise<LLMChain>;\n    /** @deprecated */\n    serialize(): SerializedLLMChain;\n    _getNumTokens(text: string): Promise<number>;\n}\nexport {};\n//# sourceMappingURL=llm_chain.d.ts.map"],"mappings":";;;;;;;;;;;;;KAWKgB,OAAAA,GAAUhB,6BAA6BY,SAASX,kCAAkCW,SAASX,wBAAwBG;KACnHa,4BAA4BC;EAD5BF,WAAO,EAAA,KAAA,GAAA;CAAGhB,GAGXmB,EAHWnB,GAAAA,GAAAA;;;;AAAyGI,UAOvGgB,aAPuGhB,CAAAA,UAAAA,MAAAA,GAAAA,MAAAA,GAAAA,MAAAA,EAAAA,cAOvCY,OAPuCZ,GAO7BY,OAP6BZ,CAAAA,SAOZU,WAPYV,CAAAA;EAAjCQ;EAAQ,MAAA,EASnFN,kBATmF;EAC1FW;EAMYG,GAAAA,EAIRC,KAJQD;EAAgEJ;EAAUA,SAAAA,CAAAA,EAM3EC,sBAN2ED,CAMpDK,KANoDL,CAAAA;EAE/EV;EAEHe,YAAAA,CAAAA,EAIUd,mBAJVc,CAI8BH,CAJ9BG,CAAAA;EAE8BA;EAAvBJ,SAAAA,CAAAA,EAAAA,MAAAA;;;;AANuG;AA2BvH;;;;;;;;;;;;AAUwBG,cAVHE,QAUGF,CAAAA,UAAAA,MAAAA,GAAAA,MAAAA,GAAAA,MAAAA,EAAAA,cAVwDJ,OAUxDI,GAVkEJ,OAUlEI,CAAAA,SAVmFP,SAAAA,YAAqBO,aAUxGA,CAVsHF,CAUtHE,CAAAA,CAAAA;EAGQlB,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAAA;EAAcA,eAAAA,EAAAA,OAAAA;EAEbC,MAAAA,EAZrBG,kBAYqBH;EAA2BE,GAAAA,EAXnDgB,KAWmDhB;EAAuCK,SAAAA,CAAAA,EAVnFO,sBAUmFP,CAV5DW,KAU4DX,CAAAA;EAA6Ba,SAAAA,EAAAA,MAAAA;EAM/GrB,YAAAA,CAAAA,EAdEK,mBAcFL,CAdsBgB,CActBhB,CAAAA;EAAqCmB,IAAAA,SAAAA,CAAAA,CAAAA,EAAAA,MAAAA,EAAAA;EAAvBJ,IAAAA,UAAAA,CAAAA,CAAAA,EAAAA,MAAAA,EAAAA;EAAwCN,WAAAA,CAAAA,MAAAA,EAX/CS,aAW+CT,CAXjCO,CAWiCP,EAX9BU,KAW8BV,CAAAA;EAAYF,QAAAA,WAAAA;EAA6BP;EAARqB,mBAAAA,CAAAA,MAAAA,EARxErB,WAQwEqB,CAAAA,EAR1DrB,WAQ0DqB;EAEtFrB;EAAqCmB,eAAAA,CAAAA,WAAAA,EARtBlB,UAQsBkB,EAAAA,EAAAA,WAAAA,EARKhB,wBAQLgB,EAAAA,UAAAA,CAAAA,EAR4CX,0BAQ5CW,CAAAA,EARyEE,OAQzEF,CAAAA,OAAAA,CAAAA;EAAvBJ;;;;;EAayBI,IAAAA,CAAAA,MAAAA,EAfxCnB,WAewCmB,GAf1BJ,sBAe0BI,CAfHA,KAeGA,CAAAA,EAAAA,MAAAA,CAAAA,EAfcV,SAedU,GAf0BZ,kBAe1BY,CAAAA,EAf+CE,OAe/CF,CAfuDnB,WAevDmB,CAAAA;EAAvBJ;EAAiDT,KAAAA,CAAAA,MAAAA,EAbjEN,WAaiEM,GAbnDS,sBAamDT,CAb5Ba,KAa4Bb,CAAAA,EAAAA,UAAAA,CAAAA,EAbPE,0BAaOF,CAAAA,EAbsBe,OAatBf,CAb8BN,WAa9BM,CAAAA;EAA0BU;;;;;;;;;AApCgC;;;kBAoCzHhB,cAAce,uBAAuBI,0BAA0Bb,kBAAkBe,QAAQL;;2BAEhFH,qBAAqBQ,QAAQD;;eAEzCP;+BACgBQ"}

package/dist/chains/llm_chain.d.ts

@@ -12,7 +12,6 @@ import { BasePromptValueInterface } from "@langchain/core/prompt_values";
 
 //#region src/chains/llm_chain.d.ts
 type LLMType = BaseLanguageModelInterface | Runnable<BaseLanguageModelInput, string> | Runnable<BaseLanguageModelInput, BaseMessage>;
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
 type CallOptionsIfAvailable<T> = T extends {
   CallOptions: infer CO;
 } ? CO : any;

package/dist/chains/llm_chain.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"llm_chain.d.ts","names":["BaseLanguageModelInterface","BaseLanguageModelInput","ChainValues","Generation","BaseMessage","BasePromptValueInterface","BasePromptTemplate","BaseLLMOutputParser","CallbackManager","BaseCallbackConfig","CallbackManagerForChainRun","Callbacks","Runnable","BaseChain","ChainInputs","SerializedLLMChain","LLMType","CallOptionsIfAvailable","T","CO","LLMChainInput","Model","LLMChain","Promise"],"sources":["../../src/chains/llm_chain.d.ts"],"sourcesContent":["import { BaseLanguageModelInterface, BaseLanguageModelInput } from \"@langchain/core/language_models/base\";\nimport type { ChainValues } from \"@langchain/core/utils/types\";\nimport type { Generation } from \"@langchain/core/outputs\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport type { BasePromptValueInterface } from \"@langchain/core/prompt_values\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { BaseLLMOutputParser } from \"@langchain/core/output_parsers\";\nimport { CallbackManager, BaseCallbackConfig, CallbackManagerForChainRun, Callbacks } from \"@langchain/core/callbacks/manager\";\nimport { Runnable } from \"@langchain/core/runnables\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { SerializedLLMChain } from \"./serde.js\";\ntype LLMType = BaseLanguageModelInterface | Runnable<BaseLanguageModelInput, string> | Runnable<BaseLanguageModelInput, BaseMessage>;\ntype CallOptionsIfAvailable<T> = T extends {\n    CallOptions: infer CO;\n} ? CO : any;\n/**\n * Interface for the input parameters of the LLMChain class.\n */\nexport interface LLMChainInput<T extends string | object = string, Model extends LLMType = LLMType> extends ChainInputs {\n    /** Prompt object to use */\n    prompt: BasePromptTemplate;\n    /** LLM Wrapper to use */\n    llm: Model;\n    /** Kwargs to pass to LLM */\n    llmKwargs?: CallOptionsIfAvailable<Model>;\n    /** OutputParser to use */\n    outputParser?: BaseLLMOutputParser<T>;\n    /** Key to use for output, defaults to `text` */\n    outputKey?: string;\n}\n/**\n * Chain to run queries against LLMs.\n *\n * @example\n * ```ts\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { ChatOpenAI } from \"@langchain/openai\";\n *\n * const prompt = ChatPromptTemplate.fromTemplate(\"Tell me a {adjective} joke\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const chain = prompt.pipe(llm);\n *\n * const response = await chain.invoke({ adjective: \"funny\" });\n * ```\n */\nexport declare class LLMChain<T extends string | object = string, Model extends LLMType = LLMType> extends BaseChain implements LLMChainInput<T> {\n    static lc_name(): string;\n    lc_serializable: boolean;\n    prompt: BasePromptTemplate;\n    llm: Model;\n    llmKwargs?: CallOptionsIfAvailable<Model>;\n    outputKey: string;\n    outputParser?: BaseLLMOutputParser<T>;\n    get inputKeys(): string[];\n    get outputKeys(): string[];\n    constructor(fields: LLMChainInput<T, Model>);\n    private getCallKeys;\n    /** @ignore */\n    _selectMemoryInputs(values: ChainValues): ChainValues;\n    /** @ignore */\n    _getFinalOutput(generations: Generation[], promptValue: BasePromptValueInterface, runManager?: CallbackManagerForChainRun): Promise<unknown>;\n    /**\n     * Run the core logic of this chain and add to output if desired.\n     *\n     * Wraps _call and handles memory.\n     */\n    call(values: ChainValues & CallOptionsIfAvailable<Model>, config?: Callbacks | BaseCallbackConfig): Promise<ChainValues>;\n    /** @ignore */\n    _call(values: ChainValues & CallOptionsIfAvailable<Model>, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;\n    /**\n     * Format prompt with values and pass to LLM\n     *\n     * @param values - keys to pass to prompt template\n     * @param callbackManager - CallbackManager to use\n     * @returns Completion from LLM.\n     *\n     * @example\n     * ```ts\n     * llm.predict({ adjective: \"funny\" })\n     * ```\n     */\n    predict(values: ChainValues & CallOptionsIfAvailable<Model>, callbackManager?: CallbackManager): Promise<T>;\n    _chainType(): \"llm\";\n    static deserialize(data: SerializedLLMChain): Promise<LLMChain>;\n    /** @deprecated */\n    serialize(): SerializedLLMChain;\n    _getNumTokens(text: string): Promise<number>;\n}\nexport {};\n//# sourceMappingURL=llm_chain.d.ts.map"],"mappings":";;;;;;;;;;;;;KAWKgB,OAAAA,GAAUhB,6BAA6BY,SAASX,kCAAkCW,SAASX,wBAAwBG;KACnHa,4BAA4BC;EAD5BF,WAAO,EAAA,KAAA,GAAA;CAAGhB,GAGXmB,EAHWnB,GAAAA,GAAAA;;;;AAAyGI,UAOvGgB,aAPuGhB,CAAAA,UAAAA,MAAAA,GAAAA,MAAAA,GAAAA,MAAAA,EAAAA,cAOvCY,OAPuCZ,GAO7BY,OAP6BZ,CAAAA,SAOZU,WAPYV,CAAAA;EAAjCQ;EAAQ,MAAA,EASnFN,kBATmF;EAC1FW;EAMYG,GAAAA,EAIRC,KAJQD;EAAgEJ;EAAUA,SAAAA,CAAAA,EAM3EC,sBAN2ED,CAMpDK,KANoDL,CAAAA;EAE/EV;EAEHe,YAAAA,CAAAA,EAIUd,mBAJVc,CAI8BH,CAJ9BG,CAAAA;EAE8BA;EAAvBJ,SAAAA,CAAAA,EAAAA,MAAAA;;;;AANuG;AA2BvH;;;;;;;;;;;;AAUwBG,cAVHE,QAUGF,CAAAA,UAAAA,MAAAA,GAAAA,MAAAA,GAAAA,MAAAA,EAAAA,cAVwDJ,OAUxDI,GAVkEJ,OAUlEI,CAAAA,SAVmFP,SAAAA,YAAqBO,aAUxGA,CAVsHF,CAUtHE,CAAAA,CAAAA;EAGQlB,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAAA;EAAcA,eAAAA,EAAAA,OAAAA;EAEbC,MAAAA,EAZrBG,kBAYqBH;EAA2BE,GAAAA,EAXnDgB,KAWmDhB;EAAuCK,SAAAA,CAAAA,EAVnFO,sBAUmFP,CAV5DW,KAU4DX,CAAAA;EAA6Ba,SAAAA,EAAAA,MAAAA;EAM/GrB,YAAAA,CAAAA,EAdEK,mBAcFL,CAdsBgB,CActBhB,CAAAA;EAAqCmB,IAAAA,SAAAA,CAAAA,CAAAA,EAAAA,MAAAA,EAAAA;EAAvBJ,IAAAA,UAAAA,CAAAA,CAAAA,EAAAA,MAAAA,EAAAA;EAAwCN,WAAAA,CAAAA,MAAAA,EAX/CS,aAW+CT,CAXjCO,CAWiCP,EAX9BU,KAW8BV,CAAAA;EAAYF,QAAAA,WAAAA;EAA6BP;EAARqB,mBAAAA,CAAAA,MAAAA,EARxErB,WAQwEqB,CAAAA,EAR1DrB,WAQ0DqB;EAEtFrB;EAAqCmB,eAAAA,CAAAA,WAAAA,EARtBlB,UAQsBkB,EAAAA,EAAAA,WAAAA,EARKhB,wBAQLgB,EAAAA,UAAAA,CAAAA,EAR4CX,0BAQ5CW,CAAAA,EARyEE,OAQzEF,CAAAA,OAAAA,CAAAA;EAAvBJ;;;;;EAayBI,IAAAA,CAAAA,MAAAA,EAfxCnB,WAewCmB,GAf1BJ,sBAe0BI,CAfHA,KAeGA,CAAAA,EAAAA,MAAAA,CAAAA,EAfcV,SAedU,GAf0BZ,kBAe1BY,CAAAA,EAf+CE,OAe/CF,CAfuDnB,WAevDmB,CAAAA;EAAvBJ;EAAiDT,KAAAA,CAAAA,MAAAA,EAbjEN,WAaiEM,GAbnDS,sBAamDT,CAb5Ba,KAa4Bb,CAAAA,EAAAA,UAAAA,CAAAA,EAbPE,0BAaOF,CAAAA,EAbsBe,OAatBf,CAb8BN,WAa9BM,CAAAA;EAA0BU;;;;;;;;;AApCgC;;;kBAoCzHhB,cAAce,uBAAuBI,0BAA0Bb,kBAAkBe,QAAQL;;2BAEhFH,qBAAqBQ,QAAQD;;eAEzCP;+BACgBQ"}

package/dist/chains/load.d.cts

@@ -1,6 +1,6 @@
 import { BaseChain } from "./base.cjs";
-import { ChainValues } from "../langchain-core/dist/utils/types/index.cjs";
 import { LoadValues } from "../util/load.cjs";
+import * as _langchain_core_utils_types0 from "@langchain/core/utils/types";
 
 //#region src/chains/load.d.ts
 
@@ -22,7 +22,7 @@ import { LoadValues } from "../util/load.cjs";
  * const chain = await loadChain("/path/to/chain.json");
  * ```
  */
-declare const loadChain: (uri: string, values?: LoadValues) => Promise<BaseChain<ChainValues, ChainValues>>;
+declare const loadChain: (uri: string, values?: LoadValues) => Promise<BaseChain<_langchain_core_utils_types0.ChainValues, _langchain_core_utils_types0.ChainValues>>;
 //#endregion
 export { loadChain };
 //# sourceMappingURL=load.d.cts.map

package/dist/chains/load.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"load.d.cts","names":["BaseChain","LoadValues","loadChain","_langchain_core_utils_types0","ChainValues","Promise"],"sources":["../../src/chains/load.d.ts"],"sourcesContent":["import { BaseChain } from \"./base.js\";\nimport { LoadValues } from \"../util/load.js\";\n/**\n * Load a chain from {@link https://github.com/hwchase17/langchain-hub | LangchainHub} or local filesystem.\n *\n * @example\n * Loading from LangchainHub:\n * ```ts\n * import { loadChain } from \"@langchain/classic/chains/load\";\n * const chain = await loadChain(\"lc://chains/hello-world/chain.json\");\n * const res = await chain.call({ topic: \"my favorite color\" });\n * ```\n *\n * @example\n * Loading from local filesystem:\n * ```ts\n * import { loadChain } from \"@langchain/classic/chains/load\";\n * const chain = await loadChain(\"/path/to/chain.json\");\n * ```\n */\nexport declare const loadChain: (uri: string, values?: LoadValues) => Promise<BaseChain<import(\"@langchain/core/utils/types\").ChainValues, import(\"@langchain/core/utils/types\").ChainValues>>;\n//# sourceMappingURL=load.d.ts.map"],"mappings":";;;;;;;;;AAoBA;;;;;;AAA6E;;;;;;;;;cAAxDE,kCAAkCD,eAAeI,QAAQL,UAAbG,4BAAAA,CAA6DC,WAAAA,EAAWD,4BAAAA,CAAwCC,WAAAA"}

package/dist/chains/load.d.ts

@@ -1,6 +1,6 @@
 import { BaseChain } from "./base.js";
-import { ChainValues } from "../libs/langchain-core/dist/utils/types/index.js";
 import { LoadValues } from "../util/load.js";
+import * as _langchain_core_utils_types0 from "@langchain/core/utils/types";
 
 //#region src/chains/load.d.ts
 
@@ -22,7 +22,7 @@ import { LoadValues } from "../util/load.js";
  * const chain = await loadChain("/path/to/chain.json");
  * ```
  */
-declare const loadChain: (uri: string, values?: LoadValues) => Promise<BaseChain<ChainValues, ChainValues>>;
+declare const loadChain: (uri: string, values?: LoadValues) => Promise<BaseChain<_langchain_core_utils_types0.ChainValues, _langchain_core_utils_types0.ChainValues>>;
 //#endregion
 export { loadChain };
 //# sourceMappingURL=load.d.ts.map

package/dist/chains/load.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"load.d.ts","names":["BaseChain","LoadValues","loadChain","_langchain_core_utils_types0","ChainValues","Promise"],"sources":["../../src/chains/load.d.ts"],"sourcesContent":["import { BaseChain } from \"./base.js\";\nimport { LoadValues } from \"../util/load.js\";\n/**\n * Load a chain from {@link https://github.com/hwchase17/langchain-hub | LangchainHub} or local filesystem.\n *\n * @example\n * Loading from LangchainHub:\n * ```ts\n * import { loadChain } from \"@langchain/classic/chains/load\";\n * const chain = await loadChain(\"lc://chains/hello-world/chain.json\");\n * const res = await chain.call({ topic: \"my favorite color\" });\n * ```\n *\n * @example\n * Loading from local filesystem:\n * ```ts\n * import { loadChain } from \"@langchain/classic/chains/load\";\n * const chain = await loadChain(\"/path/to/chain.json\");\n * ```\n */\nexport declare const loadChain: (uri: string, values?: LoadValues) => Promise<BaseChain<import(\"@langchain/core/utils/types\").ChainValues, import(\"@langchain/core/utils/types\").ChainValues>>;\n//# sourceMappingURL=load.d.ts.map"],"mappings":";;;;;;;;;AAoBA;;;;;;AAA6E;;;;;;;;;cAAxDE,kCAAkCD,eAAeI,QAAQL,UAAbG,4BAAAA,CAA6DC,WAAAA,EAAWD,4BAAAA,CAAwCC,WAAAA"}

package/dist/chains/openai_functions/base.d.cts

@@ -11,9 +11,7 @@ import { JsonSchema7Type } from "@langchain/core/utils/json_schema";
 /**
  * Configuration params for the createOpenAIFnRunnable method.
  */
-type CreateOpenAIFnRunnableConfig<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any>, RunOutput> = {
+type CreateOpenAIFnRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {
   functions: FunctionDefinition[];
   /** Language model to use, assumed to support the OpenAI function-calling API. */
   llm: RunnableInterface<BaseLanguageModelInput, BaseMessage, BaseFunctionCallOptions>;
@@ -81,17 +79,11 @@ RunInput extends Record<string, any>, RunOutput> = {
  * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }
  * ```
  */
-declare function createOpenAIFnRunnable<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any> = Record<string, any>,
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunOutput extends Record<string, any> = Record<string, any>>(config: CreateOpenAIFnRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
+declare function createOpenAIFnRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateOpenAIFnRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
 /**
  * Configuration params for the createStructuredOutputRunnable method.
  */
-type CreateStructuredOutputRunnableConfig<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any>, RunOutput> = {
+type CreateStructuredOutputRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {
   /**
    * Schema to output. Must be either valid JSONSchema or a Zod schema.
    */
@@ -162,11 +154,7 @@ RunInput extends Record<string, any>, RunOutput> = {
  * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }
  * ```
  */
-declare function createStructuredOutputRunnable<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any> = Record<string, any>,
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunOutput extends Record<string, any> = Record<string, any>>(config: CreateStructuredOutputRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
+declare function createStructuredOutputRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateStructuredOutputRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
 //#endregion
 export { CreateOpenAIFnRunnableConfig, CreateStructuredOutputRunnableConfig, createOpenAIFnRunnable, createStructuredOutputRunnable };
 //# sourceMappingURL=base.d.cts.map

package/dist/chains/openai_functions/base.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"base.d.cts","names":["BaseOutputParser","BasePromptTemplate","Runnable","RunnableInterface","BaseFunctionCallOptions","BaseLanguageModelInput","FunctionDefinition","InputValues","InteropZodObject","BaseMessage","JsonSchema7Type","CreateOpenAIFnRunnableConfig","RunInput","RunOutput","Record","Extract","createOpenAIFnRunnable","CreateStructuredOutputRunnableConfig","createStructuredOutputRunnable"],"sources":["../../../src/chains/openai_functions/base.d.ts"],"sourcesContent":["import type { BaseOutputParser } from \"@langchain/core/output_parsers\";\nimport type { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport type { Runnable, RunnableInterface } from \"@langchain/core/runnables\";\nimport type { BaseFunctionCallOptions, BaseLanguageModelInput, FunctionDefinition } from \"@langchain/core/language_models/base\";\nimport { type InputValues, InteropZodObject } from \"@langchain/core/utils/types\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport { type JsonSchema7Type } from \"@langchain/core/utils/json_schema\";\n/**\n * Configuration params for the createOpenAIFnRunnable method.\n */\nexport type CreateOpenAIFnRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {\n    functions: FunctionDefinition[];\n    /** Language model to use, assumed to support the OpenAI function-calling API. */\n    llm: RunnableInterface<BaseLanguageModelInput, BaseMessage, BaseFunctionCallOptions>;\n    /** BasePromptTemplate to pass to the model. */\n    prompt: BasePromptTemplate<InputValues<Extract<keyof RunInput, string>>>;\n    /**\n     * Only used if a single function is passed in. If `true`, then the model will be\n     * forced to use the given function. If `false`, then the model will be given the\n     * option to use the given function or not.\n     */\n    enforceSingleFunctionUsage?: boolean;\n    /**\n     * BaseLLMOutputParser to use for parsing model outputs.\n     * By default will be inferred from the function types.\n     */\n    outputParser?: BaseOutputParser<RunOutput>;\n};\n/**\n * Creates a runnable sequence that calls OpenAI functions.\n * @param config - The parameters required to create the runnable.\n * @returns A runnable sequence that will pass the given functions to the model when run.\n *\n * @example\n * ```typescript\n * const openAIFunction = {\n *   name: \"get_person_details\",\n *   description: \"Get details about a person\",\n *   parameters: {\n *     title: \"Person\",\n *     description: \"Identifying information about a person.\",\n *     type: \"object\",\n *     properties: {\n *       name: { title: \"Name\", description: \"The person's name\", type: \"string\" },\n *       age: { title: \"Age\", description: \"The person's age\", type: \"integer\" },\n *       fav_food: {\n *         title: \"Fav Food\",\n *         description: \"The person's favorite food\",\n *         type: \"string\",\n *       },\n *     },\n *     required: [\"name\", \"age\"],\n *   },\n * };\n *\n * const model = new ChatOpenAI();\n * const prompt = ChatPromptTemplate.fromMessages([\n *   [\"human\", \"Human description: {description}\"],\n * ]);\n * const outputParser = new JsonOutputFunctionsParser();\n *\n * const runnable = createOpenAIFnRunnable({\n *   functions: [openAIFunction],\n *   llm: model,\n *   prompt,\n *   enforceSingleFunctionUsage: true, // Default is true\n *   outputParser\n * });\n * const response = await runnable.invoke({\n *   description:\n *     \"My name's John Doe and I'm 30 years old. My favorite kind of food are chocolate chip cookies.\",\n * });\n *\n * console.log(response);\n *\n * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }\n * ```\n */\nexport declare function createOpenAIFnRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateOpenAIFnRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;\n/**\n * Configuration params for the createStructuredOutputRunnable method.\n */\nexport type CreateStructuredOutputRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {\n    /**\n     * Schema to output. Must be either valid JSONSchema or a Zod schema.\n     */\n    outputSchema: InteropZodObject | JsonSchema7Type;\n    /**\n     * Language model to use, assumed to support the OpenAI function-calling API.\n     */\n    llm: RunnableInterface<BaseLanguageModelInput, BaseMessage, BaseFunctionCallOptions>;\n    /** BasePromptTemplate to pass to the model. */\n    prompt: BasePromptTemplate<InputValues<Extract<keyof RunInput, string>>>;\n    /**\n     * BaseLLMOutputParser to use for parsing model outputs.\n     */\n    outputParser?: BaseOutputParser<RunOutput>;\n};\n/**\n * @deprecated Prefer the `.withStructuredOutput` method on chat model classes.\n *\n * Create a runnable that uses an OpenAI function to get a structured output.\n * @param config Params required to create the runnable.\n * @returns A runnable sequence that will pass the given function to the model when run.\n *\n * @example\n * ```typescript\n * import { createStructuredOutputRunnable } from \"@langchain/classic/chains/openai_functions\";\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { JsonOutputFunctionsParser } from \"@langchain/classic/output_parsers\";\n *\n * const jsonSchema = {\n *   title: \"Person\",\n *   description: \"Identifying information about a person.\",\n *   type: \"object\",\n *   properties: {\n *     name: { title: \"Name\", description: \"The person's name\", type: \"string\" },\n *     age: { title: \"Age\", description: \"The person's age\", type: \"integer\" },\n *     fav_food: {\n *       title: \"Fav Food\",\n *       description: \"The person's favorite food\",\n *       type: \"string\",\n *     },\n *   },\n *   required: [\"name\", \"age\"],\n * };\n *\n * const model = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const prompt = ChatPromptTemplate.fromMessages([\n *   [\"human\", \"Human description: {description}\"],\n * ]);\n *\n * const outputParser = new JsonOutputFunctionsParser();\n *\n * // Also works with Zod schema\n * const runnable = createStructuredOutputRunnable({\n *   outputSchema: jsonSchema,\n *   llm: model,\n *   prompt,\n *   outputParser\n * });\n *\n * const response = await runnable.invoke({\n *   description:\n *     \"My name's John Doe and I'm 30 years old. My favorite kind of food are chocolate chip cookies.\",\n * });\n *\n * console.log(response);\n *\n * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }\n * ```\n */\nexport declare function createStructuredOutputRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateStructuredOutputRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;\n//# sourceMappingURL=base.d.ts.map"],"mappings":";;;;;;;;;;;;AAUA;AAA0Dc,KAA9CH,4BAA8CG,CAAAA,iBAAAA,MAAAA,CAAAA,MAAAA,EAAAA,GAAAA,CAAAA,EAAAA,SAAAA,CAAAA,GAAAA;EAC3CR,SAAAA,EAAAA,kBAAAA,EAAAA;EAEYD;EAAwBI,GAAAA,EAA1CN,iBAA0CM,CAAxBJ,sBAAwBI,EAAAA,WAAAA,EAAaL,uBAAbK,CAAAA;EAAaL;EAAvDD,MAAAA,EAEGF,kBAFHE,CAEsBI,WAFtBJ,CAEkCY,OAFlCZ,CAAAA,MAEgDS,QAFhDT,EAAAA,MAAAA,CAAAA,CAAAA,CAAAA;EAEgDS;;;;;EAWtCZ,0BAAAA,CAAAA,EAAAA,OAAAA;EAAgB;AAoDnC;;;EAA6Hc,YAAAA,CAAAA,EApD1Gd,gBAoD0Gc,CApDzFD,SAoDyFC,CAAAA;CAAsBA;;;;;;;AAAyF;AAI5O;;;;;;;;;;;;;;AAcmC;AAyDnC;;;;;;;;;;;AAA4P;;;;;;;;;;;;;;;;;iBA3EpOE,wCAAwCF,sBAAsBA,uCAAuCA,sBAAsBA,6BAA6BH,6BAA6BC,UAAUC,aAAaX,SAASU,UAAUC;;;;KAI3OI,sDAAsDH;;;;gBAIhDN,mBAAmBE;;;;OAI5BP,kBAAkBE,wBAAwBI,aAAaL;;UAEpDH,mBAAmBM,YAAYQ,cAAcH;;;;iBAItCZ,iBAAiBa;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAyDZK,gDAAgDJ,sBAAsBA,uCAAuCA,sBAAsBA,6BAA6BG,qCAAqCL,UAAUC,aAAaX,SAASU,UAAUC"}

package/dist/chains/openai_functions/base.d.ts

@@ -11,9 +11,7 @@ import { JsonSchema7Type } from "@langchain/core/utils/json_schema";
 /**
  * Configuration params for the createOpenAIFnRunnable method.
  */
-type CreateOpenAIFnRunnableConfig<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any>, RunOutput> = {
+type CreateOpenAIFnRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {
   functions: FunctionDefinition[];
   /** Language model to use, assumed to support the OpenAI function-calling API. */
   llm: RunnableInterface<BaseLanguageModelInput, BaseMessage, BaseFunctionCallOptions>;
@@ -81,17 +79,11 @@ RunInput extends Record<string, any>, RunOutput> = {
  * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }
  * ```
  */
-declare function createOpenAIFnRunnable<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any> = Record<string, any>,
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunOutput extends Record<string, any> = Record<string, any>>(config: CreateOpenAIFnRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
+declare function createOpenAIFnRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateOpenAIFnRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
 /**
  * Configuration params for the createStructuredOutputRunnable method.
  */
-type CreateStructuredOutputRunnableConfig<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any>, RunOutput> = {
+type CreateStructuredOutputRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {
   /**
    * Schema to output. Must be either valid JSONSchema or a Zod schema.
    */
@@ -162,11 +154,7 @@ RunInput extends Record<string, any>, RunOutput> = {
  * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }
  * ```
  */
-declare function createStructuredOutputRunnable<
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunInput extends Record<string, any> = Record<string, any>,
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-RunOutput extends Record<string, any> = Record<string, any>>(config: CreateStructuredOutputRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
+declare function createStructuredOutputRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateStructuredOutputRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;
 //#endregion
 export { CreateOpenAIFnRunnableConfig, CreateStructuredOutputRunnableConfig, createOpenAIFnRunnable, createStructuredOutputRunnable };
 //# sourceMappingURL=base.d.ts.map

package/dist/chains/openai_functions/base.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"base.d.ts","names":["BaseOutputParser","BasePromptTemplate","Runnable","RunnableInterface","BaseFunctionCallOptions","BaseLanguageModelInput","FunctionDefinition","InputValues","InteropZodObject","BaseMessage","JsonSchema7Type","CreateOpenAIFnRunnableConfig","RunInput","RunOutput","Record","Extract","createOpenAIFnRunnable","CreateStructuredOutputRunnableConfig","createStructuredOutputRunnable"],"sources":["../../../src/chains/openai_functions/base.d.ts"],"sourcesContent":["import type { BaseOutputParser } from \"@langchain/core/output_parsers\";\nimport type { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport type { Runnable, RunnableInterface } from \"@langchain/core/runnables\";\nimport type { BaseFunctionCallOptions, BaseLanguageModelInput, FunctionDefinition } from \"@langchain/core/language_models/base\";\nimport { type InputValues, InteropZodObject } from \"@langchain/core/utils/types\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport { type JsonSchema7Type } from \"@langchain/core/utils/json_schema\";\n/**\n * Configuration params for the createOpenAIFnRunnable method.\n */\nexport type CreateOpenAIFnRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {\n    functions: FunctionDefinition[];\n    /** Language model to use, assumed to support the OpenAI function-calling API. */\n    llm: RunnableInterface<BaseLanguageModelInput, BaseMessage, BaseFunctionCallOptions>;\n    /** BasePromptTemplate to pass to the model. */\n    prompt: BasePromptTemplate<InputValues<Extract<keyof RunInput, string>>>;\n    /**\n     * Only used if a single function is passed in. If `true`, then the model will be\n     * forced to use the given function. If `false`, then the model will be given the\n     * option to use the given function or not.\n     */\n    enforceSingleFunctionUsage?: boolean;\n    /**\n     * BaseLLMOutputParser to use for parsing model outputs.\n     * By default will be inferred from the function types.\n     */\n    outputParser?: BaseOutputParser<RunOutput>;\n};\n/**\n * Creates a runnable sequence that calls OpenAI functions.\n * @param config - The parameters required to create the runnable.\n * @returns A runnable sequence that will pass the given functions to the model when run.\n *\n * @example\n * ```typescript\n * const openAIFunction = {\n *   name: \"get_person_details\",\n *   description: \"Get details about a person\",\n *   parameters: {\n *     title: \"Person\",\n *     description: \"Identifying information about a person.\",\n *     type: \"object\",\n *     properties: {\n *       name: { title: \"Name\", description: \"The person's name\", type: \"string\" },\n *       age: { title: \"Age\", description: \"The person's age\", type: \"integer\" },\n *       fav_food: {\n *         title: \"Fav Food\",\n *         description: \"The person's favorite food\",\n *         type: \"string\",\n *       },\n *     },\n *     required: [\"name\", \"age\"],\n *   },\n * };\n *\n * const model = new ChatOpenAI();\n * const prompt = ChatPromptTemplate.fromMessages([\n *   [\"human\", \"Human description: {description}\"],\n * ]);\n * const outputParser = new JsonOutputFunctionsParser();\n *\n * const runnable = createOpenAIFnRunnable({\n *   functions: [openAIFunction],\n *   llm: model,\n *   prompt,\n *   enforceSingleFunctionUsage: true, // Default is true\n *   outputParser\n * });\n * const response = await runnable.invoke({\n *   description:\n *     \"My name's John Doe and I'm 30 years old. My favorite kind of food are chocolate chip cookies.\",\n * });\n *\n * console.log(response);\n *\n * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }\n * ```\n */\nexport declare function createOpenAIFnRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateOpenAIFnRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;\n/**\n * Configuration params for the createStructuredOutputRunnable method.\n */\nexport type CreateStructuredOutputRunnableConfig<RunInput extends Record<string, any>, RunOutput> = {\n    /**\n     * Schema to output. Must be either valid JSONSchema or a Zod schema.\n     */\n    outputSchema: InteropZodObject | JsonSchema7Type;\n    /**\n     * Language model to use, assumed to support the OpenAI function-calling API.\n     */\n    llm: RunnableInterface<BaseLanguageModelInput, BaseMessage, BaseFunctionCallOptions>;\n    /** BasePromptTemplate to pass to the model. */\n    prompt: BasePromptTemplate<InputValues<Extract<keyof RunInput, string>>>;\n    /**\n     * BaseLLMOutputParser to use for parsing model outputs.\n     */\n    outputParser?: BaseOutputParser<RunOutput>;\n};\n/**\n * @deprecated Prefer the `.withStructuredOutput` method on chat model classes.\n *\n * Create a runnable that uses an OpenAI function to get a structured output.\n * @param config Params required to create the runnable.\n * @returns A runnable sequence that will pass the given function to the model when run.\n *\n * @example\n * ```typescript\n * import { createStructuredOutputRunnable } from \"@langchain/classic/chains/openai_functions\";\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { JsonOutputFunctionsParser } from \"@langchain/classic/output_parsers\";\n *\n * const jsonSchema = {\n *   title: \"Person\",\n *   description: \"Identifying information about a person.\",\n *   type: \"object\",\n *   properties: {\n *     name: { title: \"Name\", description: \"The person's name\", type: \"string\" },\n *     age: { title: \"Age\", description: \"The person's age\", type: \"integer\" },\n *     fav_food: {\n *       title: \"Fav Food\",\n *       description: \"The person's favorite food\",\n *       type: \"string\",\n *     },\n *   },\n *   required: [\"name\", \"age\"],\n * };\n *\n * const model = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const prompt = ChatPromptTemplate.fromMessages([\n *   [\"human\", \"Human description: {description}\"],\n * ]);\n *\n * const outputParser = new JsonOutputFunctionsParser();\n *\n * // Also works with Zod schema\n * const runnable = createStructuredOutputRunnable({\n *   outputSchema: jsonSchema,\n *   llm: model,\n *   prompt,\n *   outputParser\n * });\n *\n * const response = await runnable.invoke({\n *   description:\n *     \"My name's John Doe and I'm 30 years old. My favorite kind of food are chocolate chip cookies.\",\n * });\n *\n * console.log(response);\n *\n * // { name: 'John Doe', age: 30, fav_food: 'chocolate chip cookies' }\n * ```\n */\nexport declare function createStructuredOutputRunnable<RunInput extends Record<string, any> = Record<string, any>, RunOutput extends Record<string, any> = Record<string, any>>(config: CreateStructuredOutputRunnableConfig<RunInput, RunOutput>): Runnable<RunInput, RunOutput>;\n//# sourceMappingURL=base.d.ts.map"],"mappings":";;;;;;;;;;;;AAUA;AAA0Dc,KAA9CH,4BAA8CG,CAAAA,iBAAAA,MAAAA,CAAAA,MAAAA,EAAAA,GAAAA,CAAAA,EAAAA,SAAAA,CAAAA,GAAAA;EAC3CR,SAAAA,EAAAA,kBAAAA,EAAAA;EAEYD;EAAwBI,GAAAA,EAA1CN,iBAA0CM,CAAxBJ,sBAAwBI,EAAAA,WAAAA,EAAaL,uBAAbK,CAAAA;EAAaL;EAAvDD,MAAAA,EAEGF,kBAFHE,CAEsBI,WAFtBJ,CAEkCY,OAFlCZ,CAAAA,MAEgDS,QAFhDT,EAAAA,MAAAA,CAAAA,CAAAA,CAAAA;EAEgDS;;;;;EAWtCZ,0BAAAA,CAAAA,EAAAA,OAAAA;EAAgB;AAoDnC;;;EAA6Hc,YAAAA,CAAAA,EApD1Gd,gBAoD0Gc,CApDzFD,SAoDyFC,CAAAA;CAAsBA;;;;;;;AAAyF;AAI5O;;;;;;;;;;;;;;AAcmC;AAyDnC;;;;;;;;;;;AAA4P;;;;;;;;;;;;;;;;;iBA3EpOE,wCAAwCF,sBAAsBA,uCAAuCA,sBAAsBA,6BAA6BH,6BAA6BC,UAAUC,aAAaX,SAASU,UAAUC;;;;KAI3OI,sDAAsDH;;;;gBAIhDN,mBAAmBE;;;;OAI5BP,kBAAkBE,wBAAwBI,aAAaL;;UAEpDH,mBAAmBM,YAAYQ,cAAcH;;;;iBAItCZ,iBAAiBa;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAyDZK,gDAAgDJ,sBAAsBA,uCAAuCA,sBAAsBA,6BAA6BG,qCAAqCL,UAAUC,aAAaX,SAASU,UAAUC"}

package/dist/chains/openai_functions/extraction.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"extraction.d.cts","names":["BaseChatModel","BaseFunctionCallOptions","InteropZodObject","AIMessageChunk","FunctionParameters","LLMChain","createExtractionChain","createExtractionChainFromZod"],"sources":["../../../src/chains/openai_functions/extraction.d.ts"],"sourcesContent":["import { BaseChatModel } from \"@langchain/core/language_models/chat_models\";\nimport { BaseFunctionCallOptions } from \"@langchain/core/language_models/base\";\nimport { InteropZodObject } from \"@langchain/core/utils/types\";\nimport type { AIMessageChunk } from \"@langchain/core/messages\";\nimport { FunctionParameters } from \"../../output_parsers/openai_functions.js\";\nimport { LLMChain } from \"../llm_chain.js\";\n/**\n * Function that creates an extraction chain using the provided JSON schema.\n * It sets up the necessary components, such as the prompt, output parser, and tags.\n * @param schema JSON schema of the function parameters.\n * @param llm Must be a ChatOpenAI or AnthropicFunctions model that supports function calling.\n * @returns A LLMChain instance configured to return data matching the schema.\n */\nexport declare function createExtractionChain(schema: FunctionParameters, llm: BaseChatModel<BaseFunctionCallOptions>): LLMChain<object, BaseChatModel<BaseFunctionCallOptions, AIMessageChunk>>;\n/**\n * Function that creates an extraction chain from a Zod schema. It\n * converts the Zod schema to a JSON schema using before creating\n * the extraction chain.\n * @param schema The Zod schema which extracted data should match\n * @param llm Must be a ChatOpenAI or AnthropicFunctions model that supports function calling.\n * @returns A LLMChain instance configured to return data matching the schema.\n */\nexport declare function createExtractionChainFromZod(schema: InteropZodObject, llm: BaseChatModel<BaseFunctionCallOptions>): LLMChain<object, BaseChatModel<BaseFunctionCallOptions, AIMessageChunk>>;\n//# sourceMappingURL=extraction.d.ts.map"],"mappings":";;;;;;;;;;;AAaA;;;;;AAAgLG,iBAAxJG,qBAAAA,CAAwJH,MAAAA,EAA1HC,kBAA0HD,EAAAA,GAAAA,EAAjGH,aAAiGG,CAAnFF,uBAAmFE,CAAAA,CAAAA,EAAxDE,QAAwDF,CAAAA,MAAAA,EAAvCH,aAAuCG,CAAzBF,uBAAyBE,EAAAA,cAAAA,CAAAA,CAAAA;;;AAAhD;AAShI;;;;;AAAqLA,iBAA7JI,4BAAAA,CAA6JJ,MAAAA,EAAxHD,gBAAwHC,EAAAA,GAAAA,EAAjGH,aAAiGG,CAAnFF,uBAAmFE,CAAAA,CAAAA,EAAxDE,QAAwDF,CAAAA,MAAAA,EAAvCH,aAAuCG,CAAzBF,uBAAyBE,EAAAA,cAAAA,CAAAA,CAAAA"}

package/dist/chains/openai_functions/extraction.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"extraction.d.ts","names":["BaseChatModel","BaseFunctionCallOptions","InteropZodObject","AIMessageChunk","FunctionParameters","LLMChain","createExtractionChain","createExtractionChainFromZod"],"sources":["../../../src/chains/openai_functions/extraction.d.ts"],"sourcesContent":["import { BaseChatModel } from \"@langchain/core/language_models/chat_models\";\nimport { BaseFunctionCallOptions } from \"@langchain/core/language_models/base\";\nimport { InteropZodObject } from \"@langchain/core/utils/types\";\nimport type { AIMessageChunk } from \"@langchain/core/messages\";\nimport { FunctionParameters } from \"../../output_parsers/openai_functions.js\";\nimport { LLMChain } from \"../llm_chain.js\";\n/**\n * Function that creates an extraction chain using the provided JSON schema.\n * It sets up the necessary components, such as the prompt, output parser, and tags.\n * @param schema JSON schema of the function parameters.\n * @param llm Must be a ChatOpenAI or AnthropicFunctions model that supports function calling.\n * @returns A LLMChain instance configured to return data matching the schema.\n */\nexport declare function createExtractionChain(schema: FunctionParameters, llm: BaseChatModel<BaseFunctionCallOptions>): LLMChain<object, BaseChatModel<BaseFunctionCallOptions, AIMessageChunk>>;\n/**\n * Function that creates an extraction chain from a Zod schema. It\n * converts the Zod schema to a JSON schema using before creating\n * the extraction chain.\n * @param schema The Zod schema which extracted data should match\n * @param llm Must be a ChatOpenAI or AnthropicFunctions model that supports function calling.\n * @returns A LLMChain instance configured to return data matching the schema.\n */\nexport declare function createExtractionChainFromZod(schema: InteropZodObject, llm: BaseChatModel<BaseFunctionCallOptions>): LLMChain<object, BaseChatModel<BaseFunctionCallOptions, AIMessageChunk>>;\n//# sourceMappingURL=extraction.d.ts.map"],"mappings":";;;;;;;;;;;AAaA;;;;;AAAgLG,iBAAxJG,qBAAAA,CAAwJH,MAAAA,EAA1HC,kBAA0HD,EAAAA,GAAAA,EAAjGH,aAAiGG,CAAnFF,uBAAmFE,CAAAA,CAAAA,EAAxDE,QAAwDF,CAAAA,MAAAA,EAAvCH,aAAuCG,CAAzBF,uBAAyBE,EAAAA,cAAAA,CAAAA,CAAAA;;;AAAhD;AAShI;;;;;AAAqLA,iBAA7JI,4BAAAA,CAA6JJ,MAAAA,EAAxHD,gBAAwHC,EAAAA,GAAAA,EAAjGH,aAAiGG,CAAnFF,uBAAmFE,CAAAA,CAAAA,EAAxDE,QAAwDF,CAAAA,MAAAA,EAAvCH,aAAuCG,CAAzBF,uBAAyBE,EAAAA,cAAAA,CAAAA,CAAAA"}

package/dist/chains/openai_functions/openapi.d.cts

@@ -14,13 +14,10 @@ import { OpenAPIV3_1 } from "openapi-types";
 /**
  * Type representing a function for executing OpenAPI requests.
  */
-type OpenAPIExecutionMethod = (name: string,
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-requestArgs: Record<string, any>, options?: {
+type OpenAPIExecutionMethod = (name: string, requestArgs: Record<string, any>, options?: {
   headers?: Record<string, string>;
   params?: Record<string, string>;
 }) => Promise<string>;
-// OpenAI throws errors on extraneous schema properties, e.g. if "required" is set on individual ones
 /**
  * Converts OpenAPI schemas to JSON schema format.
  * @param schema The OpenAPI schema to convert.

package/dist/chains/openai_functions/openapi.d.cts.map

@@ -0,0 +1 @@
+{"version":3,"file":"openapi.d.cts","names":["OpenAIClient","JsonSchema7Type","OpenAPIV3_1","BaseChatModel","BaseFunctionCallOptions","BasePromptTemplate","OpenAPISpec","BaseChain","LLMChainInput","SequentialChain","OpenAPIExecutionMethod","Record","Promise","convertOpenAPISchemaToJSONSchema","SchemaObject","convertOpenAPISpecToOpenAIFunctions","Chat","ChatCompletionCreateParams","Function","OpenAPIChainOptions","createOpenAPIChain","Document"],"sources":["../../../src/chains/openai_functions/openapi.d.ts"],"sourcesContent":["import type { OpenAIClient } from \"@langchain/openai\";\nimport { type JsonSchema7Type } from \"@langchain/core/utils/json_schema\";\nimport type { OpenAPIV3_1 } from \"openapi-types\";\nimport { BaseChatModel } from \"@langchain/core/language_models/chat_models\";\nimport { BaseFunctionCallOptions } from \"@langchain/core/language_models/base\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { OpenAPISpec } from \"../../util/openapi.js\";\nimport { BaseChain } from \"../base.js\";\nimport { LLMChainInput } from \"../llm_chain.js\";\nimport { SequentialChain } from \"../sequential_chain.js\";\n/**\n * Type representing a function for executing OpenAPI requests.\n */\ntype OpenAPIExecutionMethod = (name: string, requestArgs: Record<string, any>, options?: {\n    headers?: Record<string, string>;\n    params?: Record<string, string>;\n}) => Promise<string>;\n/**\n * Converts OpenAPI schemas to JSON schema format.\n * @param schema The OpenAPI schema to convert.\n * @param spec The OpenAPI specification that contains the schema.\n * @returns The JSON schema representation of the OpenAPI schema.\n */\nexport declare function convertOpenAPISchemaToJSONSchema(schema: OpenAPIV3_1.SchemaObject, spec: OpenAPISpec): JsonSchema7Type;\n/**\n * Converts an OpenAPI specification to OpenAI functions.\n * @param spec The OpenAPI specification to convert.\n * @returns An object containing the OpenAI functions derived from the OpenAPI specification and a default execution method.\n */\nexport declare function convertOpenAPISpecToOpenAIFunctions(spec: OpenAPISpec): {\n    openAIFunctions: OpenAIClient.Chat.ChatCompletionCreateParams.Function[];\n    defaultExecutionMethod?: OpenAPIExecutionMethod;\n};\n/**\n * Type representing the options for creating an OpenAPI chain.\n */\nexport type OpenAPIChainOptions = {\n    llm?: BaseChatModel<BaseFunctionCallOptions>;\n    prompt?: BasePromptTemplate;\n    requestChain?: BaseChain;\n    llmChainInputs?: LLMChainInput;\n    headers?: Record<string, string>;\n    params?: Record<string, string>;\n    verbose?: boolean;\n};\n/**\n * Create a chain for querying an API from a OpenAPI spec.\n * @param spec OpenAPISpec or url/file/text string corresponding to one.\n * @param options Custom options passed into the chain\n * @returns OpenAPIChain\n */\nexport declare function createOpenAPIChain(spec: OpenAPIV3_1.Document | string, options?: OpenAPIChainOptions): Promise<SequentialChain>;\nexport {};\n//# sourceMappingURL=openapi.d.ts.map"],"mappings":";;;;;;;;;;;;;;;AASyD;KAIpDU,sBAAAA,GAAqDC,CAAAA,IAAAA,EAAAA,MAAAA,EAAAA,WAAAA,EAAAA,MAAAA,CAAAA,MAAAA,EAAAA,GAAAA,CAAAA,EAAAA,OAGpDC,CAHoDD,EAAAA;EAC5CA,OAAAA,CAAAA,EAAAA,MAAAA,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;EACDA,MAAAA,CAAAA,EAAAA,MAAAA,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;CACPC,EAAAA,GAAAA,OAAAA,CAAAA,MAAAA,CAAAA;AAAO;AAab;;;;AAEmD;;;;;;;AAUrCD,iBAZUI,mCAAAA,CAYVJ,IAAAA,EAZoDL,WAYpDK,CAAAA,EAAAA;EACDA,eAAAA,EAZQX,YAAAA,CAAagB,IAAAA,CAAKC,0BAAAA,CAA2BC,QAYrDP,EAAAA;EAAM,sBAAA,CAAA,EAXUD,sBAWV;AASnB,CAAA;;;;AAAgHE,KAfpGO,mBAAAA,GAeoGP;EAAO,GAAA,CAAA,EAd7GT,aAc6G,CAd/FC,uBAc+F,CAAA;WAb1GC;iBACME;mBACEC;YACPG;WACDA;;;;;;;;;iBASWS,kBAAAA,OAAyBlB,WAAAA,CAAYmB,6BAA6BF,sBAAsBP,QAAQH"}

package/dist/chains/openai_functions/openapi.d.ts

@@ -14,13 +14,10 @@ import { OpenAPIV3_1 } from "openapi-types";
 /**
  * Type representing a function for executing OpenAPI requests.
  */
-type OpenAPIExecutionMethod = (name: string,
-// eslint-disable-next-line @typescript-eslint/no-explicit-any
-requestArgs: Record<string, any>, options?: {
+type OpenAPIExecutionMethod = (name: string, requestArgs: Record<string, any>, options?: {
   headers?: Record<string, string>;
   params?: Record<string, string>;
 }) => Promise<string>;
-// OpenAI throws errors on extraneous schema properties, e.g. if "required" is set on individual ones
 /**
  * Converts OpenAPI schemas to JSON schema format.
  * @param schema The OpenAPI schema to convert.

package/dist/chains/openai_functions/openapi.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"openapi.d.ts","names":["OpenAIClient","JsonSchema7Type","OpenAPIV3_1","BaseChatModel","BaseFunctionCallOptions","BasePromptTemplate","OpenAPISpec","BaseChain","LLMChainInput","SequentialChain","OpenAPIExecutionMethod","Record","Promise","convertOpenAPISchemaToJSONSchema","SchemaObject","convertOpenAPISpecToOpenAIFunctions","Chat","ChatCompletionCreateParams","Function","OpenAPIChainOptions","createOpenAPIChain","Document"],"sources":["../../../src/chains/openai_functions/openapi.d.ts"],"sourcesContent":["import type { OpenAIClient } from \"@langchain/openai\";\nimport { type JsonSchema7Type } from \"@langchain/core/utils/json_schema\";\nimport type { OpenAPIV3_1 } from \"openapi-types\";\nimport { BaseChatModel } from \"@langchain/core/language_models/chat_models\";\nimport { BaseFunctionCallOptions } from \"@langchain/core/language_models/base\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { OpenAPISpec } from \"../../util/openapi.js\";\nimport { BaseChain } from \"../base.js\";\nimport { LLMChainInput } from \"../llm_chain.js\";\nimport { SequentialChain } from \"../sequential_chain.js\";\n/**\n * Type representing a function for executing OpenAPI requests.\n */\ntype OpenAPIExecutionMethod = (name: string, requestArgs: Record<string, any>, options?: {\n    headers?: Record<string, string>;\n    params?: Record<string, string>;\n}) => Promise<string>;\n/**\n * Converts OpenAPI schemas to JSON schema format.\n * @param schema The OpenAPI schema to convert.\n * @param spec The OpenAPI specification that contains the schema.\n * @returns The JSON schema representation of the OpenAPI schema.\n */\nexport declare function convertOpenAPISchemaToJSONSchema(schema: OpenAPIV3_1.SchemaObject, spec: OpenAPISpec): JsonSchema7Type;\n/**\n * Converts an OpenAPI specification to OpenAI functions.\n * @param spec The OpenAPI specification to convert.\n * @returns An object containing the OpenAI functions derived from the OpenAPI specification and a default execution method.\n */\nexport declare function convertOpenAPISpecToOpenAIFunctions(spec: OpenAPISpec): {\n    openAIFunctions: OpenAIClient.Chat.ChatCompletionCreateParams.Function[];\n    defaultExecutionMethod?: OpenAPIExecutionMethod;\n};\n/**\n * Type representing the options for creating an OpenAPI chain.\n */\nexport type OpenAPIChainOptions = {\n    llm?: BaseChatModel<BaseFunctionCallOptions>;\n    prompt?: BasePromptTemplate;\n    requestChain?: BaseChain;\n    llmChainInputs?: LLMChainInput;\n    headers?: Record<string, string>;\n    params?: Record<string, string>;\n    verbose?: boolean;\n};\n/**\n * Create a chain for querying an API from a OpenAPI spec.\n * @param spec OpenAPISpec or url/file/text string corresponding to one.\n * @param options Custom options passed into the chain\n * @returns OpenAPIChain\n */\nexport declare function createOpenAPIChain(spec: OpenAPIV3_1.Document | string, options?: OpenAPIChainOptions): Promise<SequentialChain>;\nexport {};\n//# sourceMappingURL=openapi.d.ts.map"],"mappings":";;;;;;;;;;;;;;;AASyD;KAIpDU,sBAAAA,GAAqDC,CAAAA,IAAAA,EAAAA,MAAAA,EAAAA,WAAAA,EAAAA,MAAAA,CAAAA,MAAAA,EAAAA,GAAAA,CAAAA,EAAAA,OAGpDC,CAHoDD,EAAAA;EAC5CA,OAAAA,CAAAA,EAAAA,MAAAA,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;EACDA,MAAAA,CAAAA,EAAAA,MAAAA,CAAAA,MAAAA,EAAAA,MAAAA,CAAAA;CACPC,EAAAA,GAAAA,OAAAA,CAAAA,MAAAA,CAAAA;AAAO;AAab;;;;AAEmD;;;;;;;AAUrCD,iBAZUI,mCAAAA,CAYVJ,IAAAA,EAZoDL,WAYpDK,CAAAA,EAAAA;EACDA,eAAAA,EAZQX,YAAAA,CAAagB,IAAAA,CAAKC,0BAAAA,CAA2BC,QAYrDP,EAAAA;EAAM,sBAAA,CAAA,EAXUD,sBAWV;AASnB,CAAA;;;;AAAgHE,KAfpGO,mBAAAA,GAeoGP;EAAO,GAAA,CAAA,EAd7GT,aAc6G,CAd/FC,uBAc+F,CAAA;WAb1GC;iBACME;mBACEC;YACPG;WACDA;;;;;;;;;iBASWS,kBAAAA,OAAyBlB,WAAAA,CAAYmB,6BAA6BF,sBAAsBP,QAAQH"}