Skip to main content
Weaviate
ContactLog inTry now

Weaviate:AI Database for Developers who Love to Build

Purpose-built open source AI database for a new breed of software applications.

Get startedDocumentation
Vector database diagram

Bring the power of AI to more developers

Help developers build and scale AI applications with an open source, developer-friendly platform and ecosystem.

Easily connect to popular ML models

Build and iterate faster with integrations, quickly adopt and test new models as the ecosystem evolves.

Get the best of vector and keyword search

Enhance semantic understanding and accuracy for better insights by leveraging hybrid search with vector and BM25 keyword search.

Run securely, flexibly, and reliably—at scale

Run freely with Weaviate, available as a self-hosted database, managed service, or Kubernetes package in your VPC.

What is Weaviate?

Search by meaning, not just keywords

Store, index, and search high-dimensional vectors at any scale. The foundation for search, RAG, and agents.

Weaviate architecture diagram

Weaviate is an open-source vector database that simplifies the development of AI applications. Built-in vector and hybrid search, easy-to-connect machine learning models, and a focus on data privacy enable developers of all levels to build, iterate, and scale AI capabilities faster.

  • Hybrid search
  • Scalable infrastructure
  • AI ecosystem integrations
  • Production-ready architecture
Read the docs

Built-in hybrid search

Merge various search algorithms and re-rank results.

Advanced filtering

Apply complex filters across large datasets in milliseconds.

Out-of-the box RAG

Use proprietary data to securely interact with ML models.

Vectorizer modules

Easily generate new vector embeddings or bring your own.

Configurable backups

Back up as often as needed with zero downtime.

Native multi-tenancy

Scale horizontally and consume resources efficiently.

Vector index compression

Improve the memory footprint of large datasets.

Tenant isolation

Ensure security with strict resource isolation.

Get started

Spin up a cluster, point it at your data, and go

Weaviate can take care of embeddings, ranking, and auto-scaling so you can ship features, not infrastructure.

Set up a collection

Import data from any source. Define the schema and configure your collection.

Search

Perform hybrid, semantic, and keyword search with fine-tuned parameters.

Ask

Get answers from your data by using a natural language prompt/question.

Generate

Combine retrieved context with a model to generate accurate answers.

Personalize

Recommendations, content, and responses that adapt to each individual.

# Select collection
collection = client.collections.get("SupportTickets")


# Pure vector search
response = collection.query.near_vector(
    near_vector=[0.1, 0.1, 0.1],
    limit=5
)


# Semantic search
response = collection.query.near_text(
    query="login issues after OS upgrade",
    limit=5
)


# Hybrid search (vector + keyword)
response = collection.query.hybrid(
    query="login issues after OS upgrade",
    alpha=0.75,
    limit=5
)

Give your agents memory
that works in production

Get started

Related products:

Query Agent

Ask questions in natural language. Query Agent translates intent into optimized database queries automatically.

Explore

Embeddings

Built-in vector generation from text, images, and more. No external embedding pipeline required.

Explore

Engram

Create personalized AI experiences that learn and adapt to each user over time.

Explore