@kaibanjs/tools/dist/pdf-search/index.d.ts

A set of tools to work with LLMs and KaibanJS

/**
 * Pdf Search Tool
 *
 * This tool is used to perform a RAG (Retrieval-Augmented Generation) search within the content of a text file.
 * It allows for semantic searching of a query within a specified text file's content, making it an invaluable resource
 * for quickly extracting information or finding specific sections of text based on the query provided.
 *
 * The tool uses the following components:
 * - A Chunker options, which chunks and processes text for the RAG model
 * - An Embeddings instance, which handles embeddings for the RAG model
 * - A VectorStore instance, which stores vectors for the RAG model
 * - An LLM instance, which handles the language model for the RAG model
 * - A promptQuestionTemplate, which defines the template for asking questions
 * - An OpenAI API key, which is used for interacting with the OpenAI API
 */
import { StructuredTool } from '@langchain/core/tools';
import { z } from 'zod';
/**
 * Input parameters for the PdfSearch tool
 * @typedef {Object} PdfSearchParams
 * @property {string} query - The question to ask
 * @property {string | File} [file] - The pdf file path or file object to process
 */
type PdfSearchParams = {
    query: string;
    file?: string | File;
};
/**
 * Response type for the PdfSearch tool
 * @typedef {string} RagToolkitAnswerResponse
 * @example
 * "The answer to your question is: [answer]"
 */
type RagToolkitAnswerResponse = string;
/**
 * Error type for the PdfSearch tool
 * @typedef {string} PdfSearchError
 * @example
 * "ERROR_MISSING_FILE: No pdf file was provided for analysis. Agent should provide valid pdf file in the 'file' field."
 */
type PdfSearchError = string;
/**
 * Response type for the PdfSearch tool
 * @typedef {RagToolkitAnswerResponse | PdfSearchError} PdfSearchResponse
 */
type PdfSearchResponse = RagToolkitAnswerResponse | PdfSearchError;
/**
 * Configuration options for the PdfSearch tool
 * @interface PdfSearchFields
 * @property {string} OPENAI_API_KEY - The OpenAI API key for authentication
 * @property {string | File} [file] - The pdf file path or file object to process
 * @property {any} [chunkOptions] - Chunking options for the RAG model
 * @property {any} [embeddings] - Embeddings instance for the RAG model
 * @property {any} [vectorStore] - Vector store instance for the RAG model
 * @property {any} [llmInstance] - LLM instance for the RAG model
 * @property {string} [promptQuestionTemplate] - Prompt question template for the RAG model
 */
interface PdfSearchFields {
    OPENAI_API_KEY: string;
    file?: string | File;
    chunkOptions?: any;
    embeddings?: any;
    vectorStore?: any;
    llmInstance?: any;
    promptQuestionTemplate?: string;
}
/**
 * PdfSearch tool for performing semantic search within a PDF file
 *
 * This tool allows for semantic searching of a query within the content of a text file.
 * It uses the RAGToolkit to perform the search, which includes a Chunker, Embeddings,
 * VectorStore, and LLM instance. The tool also supports loading a PDF file from a URL.
 *
 * The tool supports the following components:
 * - A Chunker options, which chunks and processes text for the RAG model
 * - An Embeddings instance, which handles embeddings for the RAG model
 * - A VectorStore instance, which stores vectors for the RAG model
 * - An LLM instance, which handles the language model for the RAG model
 * - A promptQuestionTemplate, which defines the template for asking questions
 * - An OpenAI API key, which is used for interacting with the OpenAI API
 */
export declare class PdfSearch extends StructuredTool {
    private OPENAI_API_KEY;
    private file?;
    private chunkOptions;
    private embeddings;
    private vectorStore;
    private llmInstance;
    private promptQuestionTemplate;
    private ragToolkit;
    private httpClient;
    name: string;
    description: string;
    schema: z.ZodObject<{
        file: z.ZodString;
        query: z.ZodString;
    }, "strip", z.ZodTypeAny, {
        query: string;
        file: string;
    }, {
        query: string;
        file: string;
    }>;
    /**
     * Constructor for the PdfSearch tool
     * @param {PdfSearchFields} fields - The configuration fields for the tool
     */
    constructor(fields: PdfSearchFields);
    /**
     * Call the PdfSearch tool
     * @param {PdfSearchParams} input - The input parameters for the tool
     * @returns {Promise<PdfSearchResponse>} The response from the tool
     */
    _call(input: PdfSearchParams): Promise<PdfSearchResponse>;
}
export {};