Data Pool | SmythOS Documentation

On this page

The Data Pool is the central interface for managing indexed data in SmythOS. It allows you to create Data Spaces, upload files or paste raw text, and connect to multiple vector database providers including SmythOS managed Pinecone, your own Pinecone instance, or Milvus. This enables agents to use retrieval-augmented generation (RAG) and answer queries using relevant context from your documents.

What the Data Pool enables

Agents in SmythOS can use your files and text content for precise responses. The Data Pool powers this by indexing data into searchable embeddings across your choice of vector database providers.

How the Data Pool supports RAG

RAG stands for retrieval-augmented generation. When an agent is connected to a Data Space, it can search through indexed content and use the most relevant snippets to generate informed answers. This makes your agents more accurate, grounded, and useful for knowledge-based tasks.

RAG gives your agent real knowledge

Without data, your agent only knows what you prompt it with. With RAG, it retrieves meaningful information from your own sources before generating output.

Key features of the Data Pool

Feature Description Learn More
Data Spaces Containers where you upload files or paste raw text for indexing Create Data Spaces
Multi-Provider Support Connect SmythOS Pinecone, your own Pinecone instance, or Milvus for vector storage Set Up Providers
Data source preview Review uploaded files, chunking configuration, metadata, and content from the interface Managed inside each Data Space
Provider Management Create and organize multiple provider connections for flexible infrastructure management Manage Providers

Use one Data Pool, many agents

You can reuse the same Data Spaces across multiple agents. This makes your content modular and efficient to maintain.

Using the Data Pool

To access the Data Pool:

  1. Open the SmythOS Studio sidebar
  2. Click Data Pool
  3. View your list of existing Data Spaces in a table with:
    • Data Space Name – displays the name and embedding model
    • Provider – shows which vector database provider is being used
    • Actions – add data sources or delete the data space
  4. Click Add Data Space to create a new container
  5. Click the actions column to manage data sources or delete spaces

The Data Pool displays your data spaces, their providers, and quick actions for managing content.

Storage options

The Data Pool supports multiple vector storage providers for embeddings, giving you flexibility to choose what works best for your needs.

Storage Type Hosted By Setup Required Best For Docs
SmythOS Managed Pinecone SmythOS None Quick setups, default RAG usage, no configuration Data Spaces
Your Own Pinecone You (Pinecone) API key, index name, connection setup Full control, enterprise use, scalable vectors Custom Storage
Milvus You (Milvus) Address, token, connection setup Open-source deployment, self-hosted infrastructure Custom Storage

Vector dimension requirements

Ensure your vector database is configured with the correct dimensions for your embedding model. Mismatched dimensions will prevent successful indexing.

Provider flexibility

With Data Pool, you can:

Mix and match providers

You can use different providers for different Data Spaces. Create one space with SmythOS Pinecone for testing, and another with your own Pinecone for production.

What's Next