> ## Documentation Index
> Fetch the complete documentation index at: https://docs.antryk.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Vector Databases Overview

> Deploy vector databases for AI applications and embeddings

## What are Vector Databases?

A Vector Database is a specialized database management system designed to store, index, and query data in the form of high-dimensional vector embeddings. Unlike traditional relational databases that rely on exact keyword matching, vector databases are architected to perform semantic similarity searches, identifying data points that are contextually related rather than textually identical.They're essential for AI applications like semantic search, recommendation systems, and RAG (Retrieval-Augmented Generation).

## Supported Databases

### Milvus

Open-source vector database built specifically for scalable similarity search and AI applications.

<Card title="Learn More" icon="brain" href="/vector-databases/milvus">
  Deploy Milvus
</Card>

### Qdrant

High-performance vector database and vector similarity search engine written in Rust.

<Card title="Learn More" icon="brain" href="/vector-databases/qdrant">
  Deploy Qdrant
</Card>

### Chroma

AI-native open-source embedding database optimized for LLM applications.

<Card title="Learn More" icon="brain" href="/vector-databases/chroma">
  Deploy Chroma
</Card>

### Weaviate

Open-source vector database with a GraphQL API and built-in ML models.

<Card title="Learn More" icon="brain" href="/vector-databases/weaviate">
  Deploy Weaviate
</Card>

<img src="https://mintcdn.com/antryk/uhpTfUsno7-8Oqtr/images/vector-db-listing.png?fit=max&auto=format&n=uhpTfUsno7-8Oqtr&q=85&s=9db3ffe5de6d1f875ed81e5c0483dc97" alt="vector databases listing page" width="1362" height="658" data-path="images/vector-db-listing.png" />

## Use Cases

* **Semantic Search**: Search by meaning, not keywords
* **RAG Applications**: Retrieval-Augmented Generation for LLMs
* **Recommendation Systems**: Find similar items
* **Image Search**: Visual similarity search
* **Anomaly Detection**: Find outliers in high-dimensional data
* **Deduplication**: Find duplicate content

## Getting Started

1. **Choose a vector database** (Milvus, Qdrant, Chroma, or Weaviate)
2. **Create instance** from your dashboard
3. **Configure collection** and schema
4. **Get connection string** and credentials
5. **Connect** your AI application

## Common Workflows

### Store Embeddings

```python theme={null}
import openai
from pymilvus import connections, Collection

# Generate embedding
response = openai.Embedding.create(
    input="Your text here",
    model="text-embedding-ada-002"
)
embedding = response['data'][0]['embedding']

# Store in vector database
collection.insert([{"id": 1, "vector": embedding, "text": "Your text here"}])
```

### Query Similar Vectors

```python theme={null}
# Search for similar embeddings
results = collection.search(
    data=[query_embedding],
    anns_field="vector",
    param={"metric_type": "L2", "params": {"nprobe": 10}},
    limit=10
)
```

## Features

All Antryk vector databases include:

* **Scalability**: Horizontal scaling for large datasets
* **High Availability**: Multi-node clusters
* **Metadata Filtering**: Filter by metadata attributes
* **Hybrid Search**: Combine vector and keyword search
* **Monitoring**: Performance metrics and query analytics
* **Backups**: Automated backup and restore

## Performance Optimization

* **Indexing**: Built-in indexing for fast queries
* **Sharding**: Distribute data across nodes
* **GPU Acceleration**: Optional GPU support
* **Batch Operations**: Efficient bulk inserts

## Best Practices

* **Dimension Size**: Choose appropriate embedding dimensions
* **Index Type**: Select index based on your use case
* **Batch Size**: Optimize batch insert sizes
* **Query Parameters**: Tune search parameters for accuracy vs speed

<Card title="Create Vector Database" icon="rocket" href="/quickstart">
  Get started with vector databases
</Card>