il2cpp-dump-analyzer-mcp/dist/embeddings/supabase-vector-store.d.ts

Agentic RAG system for analyzing IL2CPP dump.cs files from Unity games

import { SupabaseClient } from '@supabase/supabase-js';
import { Document } from '@langchain/core/documents';
import { Embeddings } from '@langchain/core/embeddings';
import { CodeChunk } from './chunker';
/**
 * Vector store for IL2CPP code chunks using Supabase
 */
export declare class SupabaseIL2CPPVectorStore {
    private embeddings;
    supabaseClient: SupabaseClient;
    private tableName;
    private dimensions;
    /**
     * Initialize the Supabase vector store
     * @param embeddings Embeddings instance to use
     * @param supabaseUrl Supabase URL
     * @param supabaseKey Supabase API key
     * @param tableName Table name for vector storage
     */
    constructor(embeddings: Embeddings, supabaseUrl: string, supabaseKey: string, tableName?: string);
    /**
     * Initialize the Supabase table with the correct schema
     * This ensures the document_hash column exists for deduplication
     */
    private initializeTable;
    /**
     * Create a new instance of the vector store from texts
     * @param texts Array of texts
     * @param metadatas Array of metadata objects
     * @param embeddings Embeddings instance
     * @param supabaseUrl Supabase URL
     * @param supabaseKey Supabase API key
     * @param tableName Table name
     * @returns New SupabaseIL2CPPVectorStore instance
     */
    static fromTexts(texts: string[], metadatas: Record<string, any>[], embeddings: Embeddings, supabaseUrl: string, supabaseKey: string, tableName?: string): Promise<SupabaseIL2CPPVectorStore>;
    /**
     * Add documents to the vector store
     * @param documents Array of documents to add
     */
    addDocuments(documents: Document[]): Promise<void>;
    /**
     * Add code chunks to the vector store
     * @param chunks Array of code chunks to add
     */
    addCodeChunks(chunks: CodeChunk[]): Promise<void>;
    /**
     * Search for similar documents based on a query string
     * @param query Query string
     * @param k Number of results to return
     * @returns Array of documents with similarity scores
     */
    similaritySearch(query: string, k?: number): Promise<Document[]>;
    /**
     * Search for similar documents with scores
     * @param query Query string
     * @param k Number of results to return
     * @returns Array of documents with similarity scores
     */
    similaritySearchWithScore(query: string, k?: number): Promise<[Document, number][]>;
    /**
     * Get the total number of documents in the vector store
     * @returns Number of documents
     */
    getDocumentCount(): Promise<number>;
    /**
     * Delete all documents from the vector store
     */
    deleteAll(): Promise<void>;
    /**
     * Get the dimensionality of the embeddings
     * @returns The number of dimensions in the embedding vectors
     */
    getDimension(): number;
    /**
     * Generate a unique hash for a document based on its content and metadata
     * @param document Document to generate hash for
     * @returns SHA-256 hash of the document content and metadata
     */
    private generateDocumentHash;
}