Home

⚡ Welcome to Spector Search

Ultra-fast, SIMD-accelerated semantic search engine built on Java Vector API + modern JVM technologies.

Welcome to the Spector Search wiki — your central hub for everything about Spector Search, a high-performance pure-Java vector search engine. Whether you're building RAG pipelines, powering recommendation systems, or need sub-millisecond search with zero infrastructure, you're in the right place.

---

🔥 Why Spector Search?

Metric	Value
⚡ Vector Search Latency	0.05 ms avg @ 10K docs (128-dim)
🔍 Keyword Search Latency	0.98 ms avg @ 100K docs
🧬 Hybrid Search Latency	0.17 ms avg @ 10K docs
🚀 Vector Throughput	18,800 queries/sec @ 10K
🧵 Concurrent Hybrid	14,000+ ops/sec @ 16 threads (384-dim)
🗜️ IVF-PQ + TurboQuant	8–32× memory reduction
✅ Test Suite	316+ tests, all passing
📦 Dependencies	Zero (JDK only)

---

🗺️ Quick Navigation

🚀 Getting Started

Page	Description
Getting Started	Build, run, and search in 5 minutes
What is Spector Search	Product overview, use cases, and comparisons
FAQ	Common questions answered

🏗️ Architecture & Concepts

Page	Description
Architecture Overview	Module diagram, data flow, threading model
Core Concepts	HNSW, IVF-PQ, BM25, RRF, SIMD deep-dives
Ingestion Pipeline	Document → chunk → embed → index pipeline
RAG Pipeline	End-to-end retrieval-augmented generation
Distributed Mode	Clustering, sharding, and replication
GPU Acceleration	CUDA setup and kernel details

📖 Reference

Page	Description
REST API Reference	All endpoints with curl examples
Java SDK Guide	Programmatic usage (client + embedded)
Spring AI Integration	Spring AI VectorStore adapter
CLI Reference	spectorctl commands
Configuration Guide	All parameters with tuning advice

⚙️ Operations & Community

Page	Description
Performance Tuning	Benchmarks and optimization strategies
Contributing	Development setup and PR process

---

💡 Highlights at a Glance

graph LR
    A[📄 Document] --> B[🧩 Chunking]
    B --> C[🧠 Embedding]
    C --> D[⚡ HNSW + BM25 Index]
    D --> E[🔍 Hybrid Search]
    E --> F[🎯 RRF Fusion]
    F --> G[🤖 LLM Re-ranking]
    G --> H[✨ Results]

Loading

Tip

New here? Start with Getting Started to build and run your first search in under 5 minutes.

---

🌟 Project Stats

Language	Java 25
License	Apache 2.0
Modules	16 Maven modules
Dependencies	Zero (JDK only)
SIMD	AVX2 / AVX-512 / NEON
GPU	CUDA via Panama FFM
Distributed	gRPC fan-out + consistent hashing

---

Built with ⚡ by Spectrayan · GitHub · Apache 2.0 License