Reference · Glossary

Weaviate

Last updated

An **open-source vector database** that can run self-hosted or managed, with built-in hybrid search (vector + keyword) and optional modules that generate embeddings for you at ingest time.

#When to use

Teams that want hybrid search out of the box, or need to self-host for data-residency reasons instead of using a fully managed vendor.

#When not to

Quick prototypes — the setup (schema, classes, modules) has more moving parts than an in-process store like Chroma for a first RAG demo.

#Example

import weaviate
client = weaviate.connect_to_local()
collection = client.collections.get("Docs")
collection.data.insert({"text": "Refunds take 5-7 business days", "source": "faq.md"})
results = collection.query.hybrid(query="how long do refunds take", limit=3)