Adapter for AI and LLMs

Description

Meshery is the open-source cloud native manager that empowers platform engineers to design and operate infrastructure. As infrastructure complexity grows, the need for intelligent assistance becomes critical.

This project focuses on developing and enhancing a dedicated AI Adapter and AI Connections for Meshery. This adapter serves as the bridge between Meshery’s core orchestration engine and various Large Language Models (LLMs). The goal is to enable "Natural Language to Infrastructure" capabilities, allowing users to describe their architectural intent (e.g., "Deploy a highly available Kubernetes cluster on AWS with Prometheus monitoring") and have Meshery auto-generate the visual topology and configuration manifests.

Decouple the AI logic from the core platform, allowing users to "Bring Your Own Model" (BYOM)—supporting both cloud-based providers (OpenAI, Anthropic) and local inference runners (Ollama, LocalAI).

Implementation

• Co-design and implement the interface for the AI Adapter in Go to communicate with the Meshery Server.
• Implement support for connecting to local LLMs (via Ollama) to ensure data privacy for users who cannot send infrastructure data to the public cloud.
• Improve the "System Prompt" and context-window management to feed the LLM relevant data regarding Meshery Models (schema definitions) so the AI generates valid infrastructure configurations.
• Write unit and integration tests to ensure the reliability of the adapter.
• Create user guides on how to configure the adapter with different AI providers.

Acceptance Tests

• A fully functional AI Adapter (or Connection) integrated into the Meshery ecosystem.
• Demonstrable capability for users to swap between at least two different LLM providers (e.g., OpenAI vs. a local Llama 3 model).
• Implementation of a feature where natural language queries result in a rendered design.
• Merged pull requests (PRs) including code, tests, and documentation.

Mockups

---

Contributor Guides and Handbook

• 🛠 Meshery Build & Release Strategy
• 📚 Instructions for contributing to documentation
  • Meshery documentation site and source
• 🎨 Wireframes and designs for Meshery UI in Figma
• 📺 Self-paced Contributor Trainings
• 🙋🏾🙋🏼 Questions: Discussion Forum and Community Slack