Instill Core

instill-core

🔮 Instill Core A complete unstructured data solution: ETL processing, AI-readiness, open-source LLM hosting, and RAG capabilities in one powerful platform. Quick start Follow the installation steps below or documentation for more details to build versatile AI applications locally. What is Instill Core? Instill Core is an end-to-end AI platform for data, pipeline and model orchestration. 🔮 Instill Core simplifies infrastructure hassle and encompasses these core features: 💧 Pipeline: Quickly build versatile AI-first APIs or automated workflows. ⚗️ Model: Deploy and monitor AI models without GPU infrastructure hassles. 💾 Artifact: Transform unstructured data (e.g., documents, images, audio, video) into AI-ready formats. ⚙️ Component: Connect essential building blocks to construct powerful pipelines. What can you build? 📖 Parsing PDF Files to Markdown: Cookbook 🧱 Generating Structured Outputs from LLMs: Cookbook & Tutorial 🕸️ Web scraping & Google Search with Structured Insights 🌱 Instance segmentation on microscopic plant stomata images: Cookbook See Examples for more! Installation Prerequisites | Operating System | Requirements and Instructions | | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | macOS or Linux | Instill Core works natively | | Windows | • Use Windows Subsystem for Linux (WSL2)• Install latest yq from GitHub Repository• Install latest Docker Desktop and enable WSL2 integration (tutorial)• (Optional) Install cuda-toolkit on WSL2 (NVIDIA tutorial) | | All Systems | • Docker Engine v25 or later• Docker Compose v2 or later• Install latest stable Docker and Docker Compose | Steps Use stable release version Execute the following commands to pull pre-built images with all the dependencies to launch: [!NOTE] We have restructured our project repositories. If you need to access 🔮 Instill Core projects up to version v0.13.0-beta, please refer to the instill-ai/deprecated-core repository. Use the latest version for local development Execute the following commands to build images with all the dependencies to launch: [!IMPORTANT] Code in the main branch tracks under-development progress towards the next release and may not work as expected. If you are looking for a stable alpha version, please use latest release. 🚀 That's it! Once all the services are up with health status, the UI is ready to go at . Please find the default login credentials in the documentation. To shut down all running services: Deployment Visit the Deployment Overview for more details. Client Access 📺 Console ⌨️ CLI 📦 SDK: Python SDK TypeScript SDK Stay tuned, as more SDKs are on the way! Documentation Please visit our official documentation for more. Additional resources: API Reference Cookbooks Tutorials Examples Contributing We welcome contributions from our community! Checkout the methods below: Cookbooks: Help us create helpful pipelines and guides for the community. Visit our Cookbook repository to get started. Issues: Contribute to improvements by raising tickets using templates here or discuss in existing ones you think you can help with. Community Standards We are committed to maintaining a respectful and welcoming atmosphere for all contributors. Before contributing, please read: Contributing Guidelines Code of Conduct Support Get help by joining our Discord community where you can post any questions on our #ask-for-help channel. Contributors ✨ Thank you to all these wonderful people (emoji key): Vibhor Bhatt Miguel Ortiz Sajda Kabir Henry Chen Hari Bhandari Shiva Gaire Zubeen ShihChun-H Ikko Eltociear Ashimine Farookh Zaheer Siddiqui Brian Gallagher hairyputtar David Marx Deniz Parlak Po-Yu Chen Po Chun Chiu Sarthak HR Wu phelan Chang, Hui-Tang Xiaofei Du Ping-Lin Chang Tony Wang Pratik date Juan Vallés Naman Anand totuslink Praharsh Jain Utsav Paul CaCaBlocker Rafael Melo Jeremy Shih Romit Mohane ChunHao Amelia C 楊竣凱 andre.liang Zoodane George Strong Anni Mubeen Kodvavi RCKT Wojciech Bandzerewicz Gary Leo felixcorleone Zoe Daniel Manul Thanura Akash Jana Anish0203 Prathamesh Tugaonkar Shubham This project follows the all-contributors specification. Contributions of any kind welcome! License See the LICENSE file for licensing information.