Weaviate
Open-source vector database with hybrid search, multi-tenancy, and native ML module integrations.
Weaviate
Weaviate is an open-source, cloud-native vector database that stores both objects and their vector representations. It enables semantic search, hybrid search (vector + BM25), Q&A, generative search, and multi-modal search at production scale — with modules for OpenAI, Cohere, Hugging Face, and more built-in.
Key Features
- Hybrid search: combine vector similarity and keyword (BM25) search with fusion ranking
- Native ML modules: integrate OpenAI, Cohere, Hugging Face, Google PaLM directly
- HNSW indexing with optional flat quantization for speed/memory tradeoffs
- Multi-tenancy: thousands of isolated tenants in a single deployment
- GraphQL + REST + gRPC APIs
- Kubernetes-native: Helm chart, horizontal scaling, replication
Quick Start
import weaviate
client = weaviate.connect_to_local()
collection = client.collections.create(
name="Articles",
vectorizer_config=weaviate.classes.config.Configure.Vectorizer.text2vec_openai()
)
collection.data.insert({"title": "AI in 2026", "body": "..."})
results = collection.query.near_text(query="machine learning trends", limit=5)
Install via ai-supply
npx ai-supply add weaviate-vector-database
Curated mirror of the open-source Weaviate (BSD-3-Clause). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/weaviate-vector-database/check). Click a policy:
Consume Weaviate programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/weaviate-vector-database
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/weaviate-vector-database/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add weaviate-vector-database
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/weaviate-vector-database/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "weaviate-vector-database" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.