Instill Core

Normal
GitHub Python NOASSERTION

Description

A full-stack AI infrastructure tool for data, model, and pipeline orchestration. Streamlines building versatile AI-first applications with a visual pipeline editor for end-to-end workflows from data ingestion to model inference.

Key Features

  • End-to-end AI platform for data, pipeline, and model orchestration
  • Visual pipeline editor for building versatile AI-first APIs and automated workflows
  • Unstructured data processing turning documents, images, audio, and video into AI-ready formats
  • Built-in LLM hosting and model deployment without GPU infrastructure management
  • RAG capabilities with automatic vectorization and vector database storage
  • Component-based architecture connecting essential building blocks into powerful pipelines

Use Cases

πŸ’‘ Parse PDF files to Markdown with AI-powered document processing
πŸ’‘ Build end-to-end AI pipelines from data ingestion to model inference
πŸ’‘ Deploy and serve open-source LLMs without managing GPU infrastructure
πŸ’‘ Create RAG applications with automatic document vectorization

Tags

workflow python automation llm data-processing framework

Categories

πŸ”„ Workflow πŸ“š RAG Tools

Quick Start

Install with Docker Compose: clone the repo and run `docker compose -f docker-compose.lite.yml up -d`. Access the visual pipeline editor at localhost:3000. Build AI workflows by connecting components like data loaders, LLM models, and output processors.
Visit GitHub

Related Projects