instill-core
🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-
What is instill-core?
🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications
Overview of instill-core
What it is
Instill Core is an end-to-end AI platform for data, pipeline and model orchestration. It is designed to streamline building versatile AI-first applications by providing a complete unstructured data solution that includes ETL processing, AI-readiness, open-source LLM hosting, and RAG capabilities in one platform.
Key features
- Pipeline: Quickly build versatile AI-first APIs or automated workflows.
- Component: Connect essential building blocks to construct powerful pipelines.
- Artifact: Transform unstructured data (e.g., documents, images, audio, video) into AI-ready formats.
- Model: Deploy and monitor AI models without GPU infrastructure hassles.
Use cases
- Parsing PDF files to Markdown.
- Generating structured outputs from LLMs.
- Web scraping and Google Search with structured insights.
- Instance segmentation on microscopic plant stomata images.
Getting started
Prerequisites: Docker Engine v25 or later, Docker Compose v2 or later. For Windows, use WSL2 with Docker Desktop and WSL2 integration enabled.git clone -b v0.58.1 https://github.com/instill-ai/instill-core.git && cd instill-core# Launch all servicesmake runTo shut down all running services:make down
License and pricing
The license is not stated in the provided metadata (NOASSERTION). See the LICENSE file in the repository for licensing information.
Based on the project's public README and repository metadata.
