HomeProjectsArticlesPK BoardAbout
Explore Projects

TurboVec

Active
GitHub Rust MIT

Description

turbovec is a high-performance vector retrieval library written in Rust, offering BM25, ANN and hybrid retrieval as the retrieval layer for RAG and agents.

Key Features

  • Rust implementation — high performance, low memory, embeddable
  • ANN retrieval — multiple approximate nearest neighbor algorithms
  • BM25 — classic term-frequency retrieval and sparse vectors
  • Hybrid retrieval — dense + sparse fusion for better Top-K
  • Embeddable — usable as the retrieval layer in Python/Node/JS projects
  • Batch pipelines — offline batch index building supported

Use Cases

💡 Providing high-throughput, low-latency retrieval for RAG
💡 Replacing managed vector DBs like Pinecone / Weaviate
💡 Accelerating large-scale document indexing with Rust on prem
💡 Providing millisecond semantic retrieval as an agent tool

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (14.8k stars)
  • • Permissive open-source license (MIT)
  • • Responsive to issues, low backlog

Tags

vector-search rust high-performance embeddings rag

Categories

📚 RAG Tools ⚡ Agent Tools

Quick Start

pip install turbovec
import turbovec as tv
index = tv.AnnIndex(dims=384, kind="hnsw")
index.add(vecs)
Visit GitHub Visit Website

Related Projects

Meilisearch

59.0k · Rust
Active A

Meilisearch is a lightweight open-source search engine with typo tolerance, native vector search and instant indexing, commonly used as the retrieval layer for agents and RAG.

search-enginefull-text-searchvector-search +2
  • · Typo-tolerant — forgiving search out of the box
  • · Instant indexing — new or updated docs are searchable within milliseconds
  • · Native vector search — built-in ANN vector index, hybrid with full-text
View full details → View on GitHub