ai-ml-pipeline

Build end-to-end AI and ML pipelines with LLM integration and RAG systems.

Updated Jan 31, 2026
One-click install
npx skills add https://github.com/tuyenht/Antigravity-Core --skill ai-ml-pipeline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-ml-pipeline
Source: https://github.com/tuyenht/Antigravity-Core/tree/main/.agent/skills/ai-ml-pipeline
Command: npx skills add https://github.com/tuyenht/Antigravity-Core --skill ai-ml-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive framework for building, training, and deploying sophisticated AI and Machine Learning pipelines, including LLM integration and vector database management.

Core Features & Use Cases

  • LLM Integration: Seamlessly integrate with various LLMs (OpenAI, Anthropic, Google, local) using tools like Vercel AI SDK for text generation, structured output, and multi-step tool use.
  • RAG Pipelines: Implement Retrieval-Augmented Generation by embedding documents, storing them in vector databases (Pinecone, Chroma, pgvector), and querying for contextually relevant information to enhance LLM responses.
  • Agent Orchestration: Design and manage multi-agent systems for complex task execution and self-correction.
  • ML Training & Serving: Utilize Python scripts for configurable ML training pipelines (using libraries like Transformers, PyTorch, scikit-learn) and FastAPI for efficient model serving.
  • Use Case: Develop a customer support chatbot that leverages RAG to answer questions based on your company's documentation and can also perform actions by calling external tools.

Quick Start

Use the ai-ml-pipeline skill to set up a RAG pipeline for answering questions based on provided documents.

Frequently Asked Questions about ai-ml-pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a RAG pipeline for querying company documentation?▼

To build a RAG pipeline, you embed documents and store them in vector databases like Pinecone, Chroma, or pgvector, then query the database for contextually relevant information to enhance LLM responses.

Can I use TypeScript and Python libraries for ML model training and serving?▼

Yes, you can use Python libraries like Transformers, PyTorch, and scikit-learn for configurable ML training pipelines, and FastAPI for efficient model serving, alongside TypeScript/JavaScript for AI integration.

What is the best way to integrate large language models with external tools?▼

The best way to integrate large language models is using the Vercel AI SDK, which supports text generation, structured output, and multi-step tool use with OpenAI, Anthropic, Google, or local models.

How does agent orchestration work for complex task execution?▼

Agent orchestration works by designing and managing multi-agent systems that execute complex tasks and perform self-correction, enabling sophisticated workflows like automated customer support chatbots.

Do I need prior expertise in AI/ML development to use this pipeline framework?▼

Yes, you need expertise in TypeScript/JavaScript and Python libraries for AI/ML development to effectively utilize the framework for LLM integration, RAG systems, and model deployment.