> For the complete documentation index, see [llms.txt](https://docs.rierino.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rierino.com/data-science/data-science-overview.md).

# Data Science Overview

## **What the Data Science app does**

The Data Science app is where you configure and govern ML and GenAI capabilities in a reusable way. You define model parameters, execution settings, and supporting assets so they can be invoked from real-time APIs (runners + sagas) or from batch jobs (Python processes, schedulers, and offline pipelines).

<figure><img src="/files/oaadtoHS2JIxmT7hOiWW" alt=""><figcaption><p>Data Science App</p></figcaption></figure>

## **Core Data Science capability areas**

Data Science capabilities are organized into these areas:

* **GenAI Models:** Manage LLM providers, credentials, and agent-facing configuration in [GenAI Models](/data-science/genai-models.md). This is the starting point for agent APIs and GenAI troubleshooting.
* **MCP Servers:** Expose existing platform capabilities over MCP by configuring [MCP Servers](/data-science/mcp-servers.md). Use this when you want tools and microservices to be consumable by MCP clients.
* **ML Models:** Configure traditional machine learning models, their inputs, and runtime settings in [ML Models](/data-science/ml-models.md). Use this when you want consistent inference behavior across environments.
* **Complex Event Processing:** Define real-time stream logic and windowed aggregations in [Complex Event Processing](/data-science/complex-event-processing.md). This is typically used for CEP and near-real-time enrichment pipelines.
* **Data Visualizations:** Publish embedded dashboards and reporting views through [Data Visualizations](/data-science/data-visualizations.md). Use this for observability of outcomes and business-facing reporting.

## **How Data Science components work together**

In practice, you configure assets here and invoke them elsewhere. A saga step might call an ML/GenAI handler for inference, a batch task might train or backfill features, and CEP flows might continuously compute derived signals. Keeping those definitions centralized makes changes traceable and easier to roll out safely.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.rierino.com/data-science/data-science-overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.