FluxIndex.Core 0.3.2

FluxIndex

RAG library for .NET 10.0 - Build semantic search and retrieval systems with vector + keyword hybrid search.

Key Features

• Hybrid Search - Vector (semantic) + Keyword (BM25) with automatic strategy selection
• High Performance - Embedding cache (100% faster), batch indexing (24ms/1K chunks)
• Local Reranking - Cross-encoder neural reranking with automatic algorithmic fallback
• Graph Traversal - BFS/DFS, Dijkstra shortest path, PageRank-style importance
• Vector Quantization - Scalar (Int8/Int4), Product Quantization, Binary (32x compression)
• Multiple Storage - SQLite, PostgreSQL with pgvector
• AI Flexibility - OpenAI, Azure OpenAI, or custom embedding services
• Document Processing - PDF/DOCX/TXT via FileFlux, web crawling via WebFlux
• MCP Server - Model Context Protocol for AI assistant integration
• Production Ready - Redis caching, clean architecture, .NET 10.0

Quick Start

dotnet add package FluxIndex.SDK
dotnet add package FluxIndex.Storage.SQLite
dotnet add package FluxIndex.AI.LocalReranker  # Optional: neural reranking

using FluxIndex.SDK;

// 1. Setup
var context = FluxIndexContext.CreateBuilder()
    .UseSQLite("fluxindex.db")
    .UseOpenAI("your-api-key", "text-embedding-3-small")
    .UseResilientLocalReranker()  // Auto fallback to algorithmic
    .Build();

// 2. Index
await context.Indexer.IndexDocumentAsync(
    "FluxIndex is a RAG library for .NET", "doc-001");

// 3. Search
var results = await context.Retriever.SearchAsync("RAG library", maxResults: 5);

👉 See Tutorial for complete examples and best practices

MCP Server

FluxIndex provides Model Context Protocol (MCP) server for AI assistant integration.

Available Tools: search, memorize, unmemorize, status

See FluxIndex.MCP for integration details.

Performance

Full benchmarks: BENCHMARK_RESULTS.md

Documentation

• Getting Started - Setup and configuration
• Tutorial - Comprehensive examples
• Architecture - Design principles and patterns
• Cheat Sheet - Quick reference
• Testing Guide - Unit and integration testing
• LocalReranker Guide - Neural reranking integration
• Vector Quantization Guide - Memory optimization with quantization

Examples

• RealQualityTest - OpenAI + SQLite integration
• FileFluxIndexSample - PDF/DOCX processing
• WebFluxSample - Web crawling
• IntegrationTestSample - Integration testing patterns

Requirements

• .NET 10.0 or later
• SQLite or PostgreSQL
• OpenAI API key (optional)

License

MIT License - see LICENSE file.

Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.