ConfigsMar 31, 2026·2 min read

Weaviate — Open-Source Vector Database at Scale

Weaviate is an open-source vector database for semantic search at scale. 15.9K+ GitHub stars. Hybrid search (vector + BM25), built-in RAG, reranking, multi-tenancy, and horizontal scaling. BSD 3-Claus

TO
TokRepo精选 · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

# Docker (quickest)
docker run -d -p 8080:8080 -p 50051:50051 cr.weaviate.io/semitechnologies/weaviate:latest

# Or Weaviate Cloud (managed)
# Sign up at https://console.weaviate.cloud

# Python client
pip install weaviate-client

# Quick start
python -c "
import weaviate
client = weaviate.connect_to_local()
collection = client.collections.create('Articles')
collection.data.insert({'title': 'AI is here', 'body': 'Vector search makes it fast'})
results = collection.query.near_text(query='artificial intelligence', limit=2)
print(results)
client.close()
"
Intro

Weaviate is an open-source vector database that stores objects and vectors, enabling semantic search at scale with sub-second query latency across billions of vectors. With 15,900+ GitHub stars and BSD 3-Clause license, Weaviate provides hybrid search combining vector similarity and keyword (BM25) search, built-in RAG and reranking, integrated vectorization from OpenAI/Cohere/HuggingFace, horizontal scaling, multi-tenancy with RBAC, and vector compression for cost efficiency.

Best for: Teams building production semantic search, RAG pipelines, or recommendation systems Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf Clients: Python, JavaScript/TypeScript, Go, Java

Key Features

  • Hybrid search: Combine vector similarity and BM25 keyword search in one query
  • Built-in RAG: Retrieval-augmented generation with integrated LLM support
  • Flexible vectorization: Use OpenAI, Cohere, HuggingFace, or bring your own embeddings
  • Horizontal scaling: Multi-node clusters with replication and sharding
  • Multi-tenancy: Isolated tenant data with RBAC access control
  • Vector compression: PQ and BQ compression for cost-efficient storage
  • Object TTL: Automatic data expiration with time-to-live

FAQ

Q: What is Weaviate? A: Weaviate is an open-source vector database with 15.9K+ stars for semantic search at scale. It supports hybrid search, built-in RAG, reranking, and horizontal scaling across billions of vectors. BSD 3-Clause licensed.

Q: How do I install Weaviate? A: Run docker run -d -p 8080:8080 cr.weaviate.io/semitechnologies/weaviate:latest for local setup, or use Weaviate Cloud for managed hosting. Python client: pip install weaviate-client.

🙏

Source & Thanks

Created by Weaviate. Licensed under BSD 3-Clause. weaviate/weaviate — 15,900+ GitHub stars

Related Assets

Kokoro — Lightweight 82M TTS in 9 Languages

Kokoro is an 82M parameter text-to-speech model delivering quality comparable to larger models. 6.2K+ GitHub stars. Supports English, Spanish, French, Japanese, Chinese, and more. Apache 2.0.

TokRepo精选

GPT4All — Run LLMs Privately on Your Desktop

GPT4All runs large language models privately on everyday desktops and laptops without GPUs or API calls. 77.2K+ GitHub stars. Desktop app + Python SDK, LocalDocs for private data. MIT licensed.

TokRepo精选

vLLM — High-Throughput LLM Serving Engine

vLLM is a high-throughput and memory-efficient LLM inference engine. 74.8K+ GitHub stars. PagedAttention, continuous batching, OpenAI-compatible API, multi-GPU serving. Apache 2.0.

TokRepo精选
◈Home🏆Trending👤Me