# Memory Data Connector

Define an in-memory store table where language models with memory tools save data, and make that data searchable with embeddings.

The Memory Data Connector enables configuring an in-memory dataset for tables used, or produced by the Spice runtime. Only certain tables, with predefined schemas, can be defined by the connector. These are:

- `store`: Defines a table that LLMs, with [memory tooling](https://spiceai.org/docs/features/large-language-models/memory), can store data in. Requires `access: read_write`.

## Examples

```yaml
datasets:
  - from: memory:store
    name: llm_memory
    access: read_write
    columns:
      - name: value
        embeddings: # Easily make your LLM learnings searchable.
          - from: all-MiniLM-L6-v2

embeddings:
  - name: all-MiniLM-L6-v2
    from: huggingface:huggingface.co/sentence-transformers/all-MiniLM-L6-v2
```

## Cookbook

- A cookbook recipe to provide persistent memory capabilities for language models in Spice. [LLM Memory](https://github.com/spiceai/cookbook/tree/trunk/llm-memory#readme)