embex 0.1.6

Embex: A Universal Vector Database ORM

Embex (Python)

The Universal Vector Database ORM. One API for Qdrant, Pinecone, Chroma, LanceDB, and more.

Embex is a high-performance, universal client for vector databases, built on a shared Rust core related to BridgeRust.

🚀 Features

• Unified API: Switch providers instantly. "Write once, run anywhere."
• Performance: Powered by Rust with SIMD acceleration.
• Type Safety: Fully typed Python bindings.

📦 Installation

uv pip install embex

pip install embex

⚡ Quick Start

Try Embex in 30 seconds - No setup required! Uses LanceDB embedded mode (no server needed).

import asyncio
from embex import EmbexClient, Point

async def main():
    # LanceDB embedded - zero setup, just a local path
    client = await EmbexClient.new_async("lancedb", "./data")
    collection = client.collection("documents")

    # Create collection
    await collection.create(dimension=768, distance="cosine")

    # Insert data
    await collection.insert([
        Point(id="1", vector=[0.1] * 768, metadata={"text": "Hello World"})
    ])

    # Search
    results = await collection.search(vector=[0.1] * 768, top_k=5)
    print(results.results)

asyncio.run(main())

Run it: python examples/lancedb/python/quickstart.py

All Provider Quick Starts

Try Embex with any provider! Same API, different backend:

Provider	Setup	Quick Start
LanceDB	None (embedded)	python examples/lancedb/python/quickstart.py
Qdrant	Docker server	python examples/qdrant/python/quickstart.py
Pinecone	API key	python examples/pinecone/python/quickstart.py
Chroma	Optional server	python examples/chroma/python/quickstart.py

💡 Same API everywhere! Just change the provider name - all code stays the same. See examples/README.md for setup instructions.

5. Filtered Search (Builder Pattern)

# Coming soon: Python Builder Pattern
# Currently supported via search() arguments:

```python
results = collection.search(
    vector=[0.1, 0.2, ...],
    limit=10,
    filter={"course": "CS101"}
)

☁️ Connecting to Cloud Providers

To connect to managed services like Pinecone, Qdrant Cloud, or Zilliz (Milvus), simply provide your API key and endpoint URL.

import os
from embex import EmbexClient

# Connect to Pinecone (or other cloud providers)
client = EmbexClient(
    provider="pinecone",
    url="https://index-name.svc.pinecone.io",
    api_key=os.getenv("PINECONE_API_KEY")
)

# Connect to Qdrant Cloud
client_qdrant = EmbexClient(
    provider="qdrant",
    url="https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
    api_key=os.getenv("QDRANT_API_KEY")
)

Official Documentation & API Keys

Need help finding your API key? Check the official provider documentation:

• Pinecone: Authentication & API Keys
• Qdrant: Cloud Authentication
• Milvus (Zilliz): Manage Credentials
• Weaviate: Authentication
• Chroma: Auth & Client Settings

🔌 Supported Providers

Provider	Key	Status
Qdrant	qdrant	Supported
Chroma	chroma	Supported
Pinecone	pinecone	Supported
Weaviate	weaviate	Supported
LanceDB	lancedb	Supported
Milvus	milvus	Supported
PgVector	pgvector	Supported

🔗 Resources

• Main Repository: github.com/bridgerust/bridgerust
• Issues: github.com/bridgerust/bridgerust/issues
• Documentation: Full Docs