Assembling...
Weaviate is an open-source vector database that combines vector search with structured filtering and keyword search in a single query. It offers built-in vectorization modules that automatically generate embeddings using OpenAI, Cohere, or HuggingFace models. Weaviate supports GraphQL and REST APIs, multi-tenancy, and can be self-hosted or used as a managed cloud service.
Store objects with text fields and let Weaviate automatically generate and index embeddings using integrated vectorization modules, eliminating manual embedding pipelines.
Build a SaaS knowledge base where each customer's data is isolated in separate tenants but shares the same Weaviate cluster for cost efficiency.
Combine vector retrieval with LLM generation using Weaviate's generative modules, which pass retrieved objects to an LLM to synthesize answers in a single API call.
import weaviate from "weaviate-client";const client = await weaviate.connectToWeaviateCloud(process.env.WEAVIATE_URL!, {authCredentials: new weaviate.ApiKey(process.env.WEAVIATE_API_KEY!),});export async function hybridSearch(query: string, limit = 5) {const articles = client.collections.get("Article");const result = await articles.query.hybrid(query, {limit,alpha: 0.75, // 75% vector, 25% keywordreturnMetadata: ["score"],returnProperties: ["title", "content", "author"],});return result.objects.map((obj) => ({title: obj.properties.title,content: obj.properties.content,score: obj.metadata?.score,}));}
Seamless integration, great documentation. Set up in under 10 minutes.
2 days ago
Works well for our use case. Would love to see more webhook event types.
1 week ago
Excellent compliance coverage. HIPAA audit trail works perfectly.
2 weeks ago
| Key | Description | Example |
|---|---|---|
| WEAVIATE_URL | Weaviate cluster URL | https://my-cluster.weaviate.network |
| WEAVIATE_API_KEY | API key for Weaviate Cloud | xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx |
Weaviate is an open-source vector database that differentiates itself with built-in vectorization modules, hybrid vector+keyword search, and a GraphQL API. It can automatically generate embeddings using OpenAI or Cohere models, eliminating separate embedding pipelines. Weaviate is ideal for teams that want the flexibility of self-hosting or need hybrid search combining semantic and keyword matching.