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.
Supported Vector Stores
The MAC Vectors connector supports the following embedding stores.
- Azure AI Search
- Chroma
- Elasticsearch
- Milvus
- OpenSearch
- PGVector
- Pinecone
- Qdrant
Supported Model Providers
The MAC Vectors connector supports the following model providers to generate embeddings.
- Azure Open AI
- Open AI
- Mistral AI
- Nomic
- Hugging Face
Supported Storage Options
- Local: Allows to load data from application local storage
- Azure Blob Storage: Allows to load data from Azure Blob Storage
- AWS S3 Bucket: Allows to load data from AWS S3 Buckets
Operations
The MAC Vectors connector offers a range of features to implement advanced RAG use cases:
- Generate Embeddings
- Add Text to Vector Store
- Add Document to Vector Store (Text, PDF and URL)
- Upload complete Folders to Vector Store
- Query Vector Store based on semantic search and metadata filtering
- List sources within Vector Store
- Remove Embeddings from Vector Store
Table of Supported Operations by Store
Not all the operations are supported by each embedding store, following a detailed view.
| Name | Storing Metadata | Filtering by Metadata | Removing Embeddings | List All Embeddings |
|---|---|---|---|---|
| Azure AI Search | ✅ | ✅ | ✅ | ✅ |
| Chroma | ✅ | ✅ | ✅ | ✅ |
| Elasticsearch | ✅ | ✅ | ✅ | |
| Milvus | ✅ | ✅ | ✅ | ✅ |
| OpenSearch | ✅ | ✅ | ||
| PGVector | ✅ | ✅ | ✅ | ✅ |
| Pinecone | ✅ | ✅ | ||
| Qdrant | ✅ | ✅ | ✅ | ✅ |
Additional Integrations
MAC Vectors Connector integrates seamlessly with other MAC Projects AI Connectors and the MuleSoft ecosystem, offering enhanced functionalities.