Welcome to AI Agents for OSM’s documentation!

Contents:

• 1. Scope
• 2. Understanding the Concept
  • 2.1. Introduction
  • 2.2. What about AI Models?
  • 2.3. Integration in the OSM architecture
• 3. Usage
  • 3.1. Quick Start: VNF scaling based on road-traffic images recognition.
  • 3.2. Deploying my own AI Agent
• 4. Contribute to the code
  • 4.1. Report a Bug
  • 4.2. Contribution Guidelines
• 5. Q&A
  • 5.1. Which OSM release do we need?
  • 5.2. Could we deploy these AI Agents on other ETSI NFV platforms besides OSM?
  • 5.3. Can we use an AI framework other than Tensor Flow Serving?
  • 5.4. Is it possible to perform other orchestration actions beyond scaling?
  • 5.5. Which VIMs can be used to host the VNFs created by running the descriptors from OSM to launch AI-Agents?
  • 5.6. Which AI Models are supported?
  • 5.7. Can the conditions to be assessed by the thresholds be modified?
  • 5.8. If I have several models in the ‘values.yaml’ file, how can I select the one I want to work with?
  • 5.9. Is it possible to have several AI Agents running?
  • 5.10. What OSM installation options should we use?
  • 5.11. Is this an official OSM feature?
• 6. Roadmap
• 7. Usage License
• 8. Contact
• 9. Acknowledgement
• 10. Annex 1. AI Models Server installation procedure
  • 10.1. Installing TensorFlow Serving
  • 10.2. Configuring AI Models
• 11. Annex 2. AI Agent Code
  • 11.1. AI Agent Orchestrator
  • 11.2. Interfaces

The AI-Agent was introduced in the OSM PoC 11 in the context of the H2020 Project 5GTours to include a novel way of adding a scheduled Job in K8s that performs proactive scaling of a VNF. The source code of this project is OpenSource and available in the ATOS GitLab