Miyagi

Visit Tool

Miyagi is an AI coding and development tool that showcases Microsoft's Copilot stack for building intelligent applications. It provides a sample for designing, developing, and deploying enterprise-grade AI apps.

Claim this tool

3Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is miyagi?

Miyagi is a comprehensive sample project designed to help developers envision and build intelligent applications using Microsoft's Copilot stack. It offers an experiential approach to developing AI-infused product experiences, covering both generative and traditional machine learning use cases. The project introduces traditional software engineers to emerging design patterns in prompt engineering, such as chain-of-thought and retrieval-augmentation, alongside techniques like vectorization for long-term memory, fine-tuning of open-source models, agent-like orchestration, and plugins for augmenting and grounding LLMs. It includes examples utilizing Semantic Kernel, Promptflow, LlamaIndex, LangChain, and various vector stores, making it ideal for modernizing applications with AI.

Best used for

Ideal for developers who need to understand and implement Microsoft's Copilot stack, explore generative and traditional ML use cases, and learn advanced prompt engineering techniques. Especially valuable for those looking to modernize and transform applications with AI and fine-tune private data for custom Copilots.

Common actions

build AI applications

learn prompt engineering

integrate AI services

develop intelligent apps

orchestrate AI agents

workflowslow-code/no-codeopen-sourceautomated workflowcollaborationdeepfake"AI Agents"face swappinggithub copilot

Capabilities

Key features

Prompt engineering patterns
Vectorization for memory
Fine-tuning OSS models
Agent-like orchestration
LLM plugins
Generative text/images
Cloud-native architecture

Target Audience

developer

Integrations

azure-openaisemantic-kernellangchainllama-indexgithub-copilotazure-ai-searchcosmosdbpromptflow+ 2 more

Pricing & Plans

Open Source

Free

FAQs

What is the primary purpose of Project Miyagi?

Project Miyagi serves as a sample to envision intelligent applications using Microsoft's Copilot stack. It guides developers through designing, developing, and deploying enterprise-grade AI apps, showcasing both generative and traditional machine learning approaches.

What AI technologies and frameworks does Miyagi demonstrate?

Miyagi demonstrates a wide array of AI technologies including Semantic Kernel, Promptflow, LlamaIndex, LangChain, Azure AI Search, CosmosDB Postgres pgvector, and generative image utilities like DreamFusion and ControlNet. It also features fine-tuned models such as Llama2 and Phi-2.

Is Miyagi suitable for learning prompt engineering?

Yes, Miyagi is designed to introduce traditional software engineers to emerging design patterns in prompt engineering, including chain-of-thought and retrieval-augmentation. It also covers techniques like vectorization for long-term memory and agent-like orchestration.

What kind of use cases are implemented in Miyagi?

Miyagi includes partial implementations for use cases such as personalized financial coaching, summarization, and agent-like orchestration. It also features a ChatGPT Plugin, knowledge graph memory, and integration with MS Graph API via Semantic Kernel's skills.

Trending

Subcategories trending in Coding & Development

Open Source & Models Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce