Weaviate Has a Free API You Should Know About

Weaviate is an open-source vector database with built-in vectorization modules. It can automatically generate embeddings using OpenAI, Cohere, or Hugging Face — no separate embedding pipeline needed.

Why Weaviate Simplifies AI Search

A team was managing separate services for embedding generation, vector storage, and search orchestration. Weaviate replaced all three — it generates embeddings, stores them, and searches them in one system.

Key Features:

• Built-in Vectorization — Automatic embedding generation
• Hybrid Search — Combine vector + keyword search
• GraphQL API — Query with GraphQL
• Multi-Tenancy — Isolate data per tenant
• Generative Search — RAG built into the database

Quick Start

docker compose up -d

import weaviate

client = weaviate.connect_to_local()

articles = client.collections.create(
    name="Article",
    vectorizer_config=weaviate.Configure.Vectorizer.text2vec_openai()
)

articles.data.insert({"title": "AI in 2024", "content": "AI is transforming every industry"})

results = articles.query.near_text(query="artificial intelligence trends", limit=5)
for item in results.objects:
    print(item.properties["title"])

Hybrid Search

results = articles.query.hybrid(
    query="machine learning",
    alpha=0.5  # Balance between vector and keyword search
)

Why Choose Weaviate

1. All-in-one — vectorization + storage + search
2. Hybrid search — best of vector and keyword
3. Production-ready — used by major companies

Check out Weaviate docs to get started.

---

Need AI data solutions? Check out my Apify actors or email [e-mail] for custom solutions.