Docs
Connector Overview

MAC Vectors Connector Overview

MAC Vectors provides access to a broad number of external Vector Stores and Databases. It is built to be leveraged by the MAC Projects AI Connector (Amazon Bedrock, MuleSoft AI Chain & Einstein AI)

What is MAC Vectors Connector?

MAC Vectors is a custom connector for MuleSoft, to provide MuleSoft users access to Vector Databases.

Connector Overview

Supported Vector Stores

The MAC Vectors connector supports the following embedding stores.

Supported Operations by Vector Stores

Not all the operations are supported by each embedding store, following a detailed view.


NameStoring MetadataFiltering by MetadataRemoving EmbeddingsList All Embeddings
Azure AI Search
Chroma
Elasticsearch
Milvus
Amazon OpenSearch
PGVector
Pinecone
Qdrant

Supported Model Providers

The MAC Vectors connector supports the following model providers to generate embeddings.

Supported Embedding Types by Model Providers


NameText EmbeddingImage EmbeddingVideo Embedding
Azure Open AI
Azure Vision AI
Einstein
Google Vertex AI
Hugging Face
Mistral AI
Nomic
Ollama
Open AI

Supported Storage Options

Operations

The MAC Vectors connector offers a range of features to implement advanced RAG use cases:

  • Load, parse and split single Document
  • Load, parse and split list of Documents
  • Load and process single Media
  • Load and process list of Media
  • Generate Embeddings from text
  • Generate Embeddings from document
  • Generate Embeddings from binary
  • Generate Embeddings from media
  • Add embeddings to Store
  • List sources from Store
  • Query Store
  • Remove embeddings from Store

Additional Integrations

MAC Vectors Connector integrates seamlessly with other MAC Projects AI Connectors and the MuleSoft ecosystem, offering enhanced functionalities.