Commit 3f78e465 authored by Kostis Trantzas's avatar Kostis Trantzas
Browse files

Re-positions the introductory image to appear right after the initial text at... 

Re-positions the introductory image to appear right after the initial text at the AI Architecture section
parent 6602b90e

doc/architecture/ai.md

+5 −5
Changes for doc/architecture/ai.md: 5 added lines, 5 removed lines.
Original line number Diff line number Diff line 
# OSL AI



<figure>

  <img src="../images/ai/osl_ai.png" alt="OSL AI architecture">

  <figcaption>Figure 1. OSL AI architecture</figcaption>

</figure>



OpenSlice introduces a dedicated AI layer that brings conversational and agentic capabilities on top of the existing NaaS and Service Orchestration functionalities. The goal is to let stakeholders, like operators, developers, and end customers interact with OpenSlice through natural language, and to let OpenSlice itself use AI agents to support orchestration decisions.



The OSL AI layer is built around four concepts:
@@ -16,6 +11,11 @@ The OSL AI layer is built around four concepts: 


Each of these is described below.



<figure>

  <img src="../images/ai/osl_ai.png" alt="OSL AI architecture">

  <figcaption>Figure 1. OSL AI architecture</figcaption>

</figure>



## MCP Server



The OpenSlice MCP Server implements a [Model Context Protocol](https://modelcontextprotocol.io/) endpoint on top of OpenSlice's existing TMF-based service and product management stack. It is a standalone component that translates MCP tool invocations into calls against OpenSlice's internal catalog, ordering, and inventory subsystems, and returns the results in the structured format MCP clients expect.