Database-Specific Embeddings

Database-specific embedding components provide specialized embedding generation optimized for vector database integrations and database-native operations.

Astra DB Vectorize

Connect this component to the Embeddings port of the Astra DB vector store component to generate embeddings.

This component requires that your Astra DB database has a collection that uses a vectorize embedding provider integration. For more information and instructions, see Embedding Generation.

Usage

Astra DB Vectorize features:

  • Native database integration

  • Serverless embedding generation

  • Multiple provider support

  • Automatic scaling

  • Cost optimization

Inputs

Name
Display Name
Info

provider

Embedding Provider

The embedding provider to use

model_name

Model Name

The embedding model to use

authentication

Authentication

The name of the API key in Astra that stores your vectorize embedding provider credentials. (Not required if using an Astra-hosted embedding provider.)

provider_api_key

Provider API Key

As an alternative to authentication, directly provide your embedding provider credentials.

model_parameters

Model Parameters

Additional model parameters

Outputs

Name
Type
Description

embeddings

Embeddings

An instance for generating embeddings using Astra vectorize

Supported Providers

Astra-Hosted Providers

  • NVIDIA: NV-Embed-QA and other NVIDIA models

  • OpenAI: text-embedding-3-small, text-embedding-3-large

  • Hugging Face: Various open-source models

External Providers

  • OpenAI: Custom API key required

  • Cohere: Commercial embedding models

  • Voyage AI: Specialized embedding models

  • Azure OpenAI: Enterprise OpenAI models

Model Categories

General Purpose

  • text-embedding-3-small: Balanced performance and cost

  • text-embedding-3-large: High-quality general embeddings

  • nv-embed-qa: Question-answering optimized

Specialized Models

  • voyage-2: Advanced semantic understanding

  • cohere-embed-v3: Multilingual capabilities

  • e5-large-v2: Research-grade embeddings

Multilingual Support

  • Comprehensive language coverage

  • Cross-lingual semantic understanding

  • Language-specific optimizations

  • Cultural context awareness

Integration Benefits

Native Database Integration

  • Seamless Setup: Direct integration with Astra DB

  • Automatic Scaling: Database-managed scaling

  • Cost Optimization: Pay-per-use embedding generation

  • Performance: Optimized for database operations

Security & Compliance

  • Credential Management: Secure API key storage

  • Data Protection: Enterprise-grade security

  • Compliance: SOC 2, GDPR compliance

  • Access Control: Fine-grained permissions

Operational Advantages

  • Managed Service: No infrastructure management

  • Monitoring: Built-in metrics and monitoring

  • Updates: Automatic model updates

  • Support: Enterprise support options

Usage Notes

  • Provider Selection: Choose based on use case and requirements

  • Authentication: Secure credential management through Astra

  • Model Parameters: Fine-tune for specific applications

  • Cost Management: Monitor usage and optimize costs

  • Performance: Leverage database-native optimizations

  • Scalability: Automatic scaling with database growth

Last updated