weaviate /weaviate
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
★ 16,948⑂ 1,438👁 137⑃ 10,828● 2,945▤ 615
Download: v1.40.5 - Alter schema reindex property improvements, Weaviate Embeddings module Fixv1.40.5 ↓1.40.52026-11-10
+1
Daily
16,948
stars
1,438
forks
137
watchers
10,828
prs
2,945
issues
615
releases
README
Weaviate
Weaviate is a cloud-native vector database that stores both objects and vectors, enabling semantic search at scale. It combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG), and reranking in a single query interface. Common use cases include RAG systems, semantic and image search, recommendation engines, chatbots, and content classification.
Weaviate supports two approaches to store vectors: automatic vectorization at import using integrated models (OpenAI, Cohere, HuggingFace, and others) or direct import of pre-computed vector embeddings. Production deployments benefit from built-in multi-tenancy, replication, RBAC authorization, and many other features.
To get started quickly, have a look at one of these tutorials:
- Quickstart - Weaviate Cloud
- Quickstart - local Docker instance
Installation
Weaviate offers multiple installation and deployment options:
- Docker
- Kubernetes
- Weaviate Cloud
See the installation docs for more deployment options, such as AWS and GCP.
Getting started
You can easily start Weaviate and a local vector embedding model with Docker.
Create a docker-compose.yml file:
yml
services:
weaviate:
image: cr.weaviate.io/semitechnologies/weaviate:1.36.0
ports:
- "8080:8080"
- "50051:50051"
environment:
ENABLE_MODULES: text2vec-model2vec
MODEL2VEC_INFERENCE_API: http://text2vec-model2vec:8080
A lightweight embedding model that will generate vectors from objects during import
text2vec-model2vec:
image: cr.weaviate.io/semitechnologies/model2vec-inference:minishlab-potion-base-32M
Start Weaviate and the embedding service with:
bash
docker compose up -d
Install the Python client (or use another client library):
bash
pip install -U weaviate-client
The following Python example shows how easy it is to populate a Weaviate database with data, create vector embeddings and perform semantic search:
python
import weaviate
from weaviate.classes.config import Configure, DataType, Property
Connect to Weaviate
client = weaviate.connect_to_local()
Create a collection
client.collections.create(
name="Article",
properties=[Property(name="content", data_type=DataType.TEXT)],
vector_config=Configure.Vectors.text2vec_model2vec(), Use a vectorizer to generate embeddings during import
vector_config=Configure.Vectors.self_provided() If you want to import your own pre-generated embeddings
)
Insert objects and generate embeddings
articles = client.collections.get("Article")
articles.data.insert_many(
[
{"content": "Vector databases enable semantic search"},
{"content": "Machine learning models generate embeddings"},
{"content": "Weaviate supports hybrid search capabilities"},
]
)
Perform semantic search
results = articles.query.near_text(query="Search objects by meaning", limit=1)
print(results.objects[0])
client.close()
This example uses the Model2Vec vectorizer, butTop issues
#10675Runtime Property Reindex39 comments · 2026-03-05#4234Add pagination to "list tenants" endpoint32 comments · 2024-02-15#2848Possibility to update or/and delete a property17 comments · 2023-03-30#2124Support for batch patch (partial update)16 comments · 2022-08-22#2996Slice out of bounds recovering objects14 comments · 2023-05-09#1684FR: Allow arbitrary ID instead of forcing a UUID14 comments · 2021-09-19#2228Dynamic Scaling: Move shards around nodes, drain node, etc.13 comments · 2022-09-22#4019FR: Support SPLADE / Sparse vectors12 comments · 2024-01-16
Latest release
v1.40.5 - Alter schema reindex property improvements, Weaviate Embeddings module Fix v1.40.5 2026-11-10Breaking Changes none New Features none Fixes Require every verb of a manage permission before assigning its role by @dirkkul in https://github.com/weaviate/weaviate/pull/13775 perf(lsmkv): stripe the segment read-bytes metric across cache lines by @aliszka in https://github.com/weaviate/weaviate/pull/13658 test(reindex): make the merged-barrier restart test deterministic by @etiennedi in https://github.com/weaviate/weaviate/pull/13743 chore(tools): enforce golangci-lint version in gen-code-from-swagger.sh by @antas-marcin in https://github.com/weaviate/weaviate/pull/13791