Skip to main content

No project description provided

Project description

🍽️ KitchenAI

KitchenAI

Instantly turn AI Jupyter Notebooks into production-ready APIs.

Falco
Hatch Project
Docs


Documentation KitchenAI Cloud

What is KitchenAI?

KitchenAI bridges the gap between AI developers, Application developers, and Infrastructure developers making it easy to:

  • Author multiple AI techniques
  • Quickly test and iterate
  • Easily build and share

kitchenai-dev

  • For AI Developers: Focus on your techniques like RAG or embeddings—KitchenAI handles scalable, in the notebook you already feel comfortable in. KitchenAI will convert your notebook into a production-ready application.

  • For App Developers: Seamlessly integrate AI with a set of API's you can build an application on top of. Quickly test to see which AI technique best fits your application.

  • For Infrastructure Developers: Integrate with AI tooling, customize Django backends, build plugins, and leverage built-in support for observability platforms like Sentry and OpenTelemetry. KitchenAI is extensible to modify for more advanced use cases.

Say goodbye to boilerplate!

🚀 Go from notebook to production in minutes.

Example notebook: kitchenai-community/llama_index_starter

By annotating your notebook with KitchenAI annotations, you can go from this:

kitchenai-dev

To interacting with the API using the built in client:

kitchenai-dev


🚀 Why KitchenAI?

Integrating AI into applications is getting more complicated, making it tough to test, tweak, and improve your code quickly. KitchenAI is here to fix that by meeting AI developers and data scientists where they already work. It makes the journey from Jupyter notebooks to a fully functional AI backend seamless—getting you up and running in just minutes.

With KitchenAI, you can bridge the gap between experimenting and going live, helping teams work faster and stay productive. The goal is simple: give you a set of tools that cuts the time it takes to turn AI ideas into production-ready solutions in half, so you can focus on what really matters—delivering results.

The ultimate tool in your AI development kit. Improve your LLMOps.

Close the feedback loop between AI developers and App developers.

🔗 Learn more at docs.kitchenai.dev.


Quickstart

  1. Set Up Environment

    export OPENAI_API_KEY=<your key>
    export KITCHENAI_DEBUG=True
    python -m venv venv && source venv/bin/activate && pip install kitchenai
    
  2. Start a Project

    kitchenai cook list && kitchenai cook select llama-index-chat && pip install -r requirements.txt
    

    kitchenai-list

  3. Run the Server

    kitchenai init && kitchenai dev --module app:kitchen
    

    Alternatively, you can run the server with jupyter notebook:

    kitchenai dev --module app:kitchen --jupyter
    
  4. Test the API

    kitchenai client health
    
    kitchenai client labels
    

    kitchenai-client

  5. Build Docker Container

    kitchenai build . app:kitchenai
    

📖 Full quickstart guide at docs.kitchenai.dev.


Developer Experience

Developer Flow

Features

  • 📦 Quick Cookbook Creation: Build cookbooks in seconds.
  • 🚀 Production-Ready AI: Turn AI code into robust endpoints.
  • 🔌 Extensible Framework: Add custom recipes and plugins effortlessly.
  • 🐳 Docker-First Deployment: Deploy with ease.

🔧 Under the Hood

  • Django Ninja: Async-first API framework for high-performance endpoints.
  • Django Q2: Background workers for long-running tasks.
  • Plugin Framework: Django DJP integration
  • AI Ecosystem: Integrations to AI ecosystem and tools
  • S6 Overlay: Optimized container orchestration.

KitchenAI is built for developers, offering flexibility and scalability while letting you focus on AI.


🚀 Get Early Access

Be part of our exclusive KitchenAI Cloud launch program! Over the coming months, we’ll roll out the first versions of KitchenAI Cloud, and we’re looking for a small group of developers to join us.

🔗 Register now: Sign Up Here

🎁 Why Join the Program?

As part of the KitchenAI Cloud program, you’ll get:

  • 🌟 Early Access: Be the first to try out cutting-edge features.
  • 📞 Direct Support: A dedicated line to the KitchenAI team for feedback and assistance.
  • 📣 Influence the Future: Shape the direction of KitchenAI Cloud with your insights.
  • 💎 KitchenAI Credits: Enjoy tons of credits to experiment and build.
  • 🎁 Exclusive Swag: Special gifts for early adopters.

🛠️ Roadmap

  • SDKs for Python, Go, JS, and Rust.
  • Enhanced plugin system.
  • Signal-based architecture for event-driven apps.
  • Built-in support for Postgres and pgvector.

🧑‍🍳 Contribute

KitchenAI is in alpha—we welcome your contributions and feedback!


🙏 Acknowledgements

Inspired by the Falco Project. Thanks to the Python community for best practices and tools!


📊 Telemetry

KitchenAI collects anonymous usage data to improve the framework—no PII or sensitive data is collected.

Your feedback and support shape KitchenAI. Let's build the future of AI development together!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kitchenai-0.12.2.tar.gz (9.0 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kitchenai-0.12.2-py3-none-any.whl (3.0 MB view details)

Uploaded Python 3

File details

Details for the file kitchenai-0.12.2.tar.gz.

File metadata

  • Download URL: kitchenai-0.12.2.tar.gz
  • Upload date:
  • Size: 9.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.27.2

File hashes

Hashes for kitchenai-0.12.2.tar.gz
Algorithm Hash digest
SHA256 3b1ab6270e8ab622d6039ce35dc9a5eb33643de38f8f8401a7585e9da4bf4827
MD5 eaaa805df1e9355fd589342909929712
BLAKE2b-256 a003dd56a08fd344de0589c609c5a930ae98ff3eedfca6db72cffbe8cc3f837f

See more details on using hashes here.

File details

Details for the file kitchenai-0.12.2-py3-none-any.whl.

File metadata

  • Download URL: kitchenai-0.12.2-py3-none-any.whl
  • Upload date:
  • Size: 3.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.27.2

File hashes

Hashes for kitchenai-0.12.2-py3-none-any.whl
Algorithm Hash digest
SHA256 b3e32514196400c966766de8322394e59fa8dde764a60acffcf6705e3356f310
MD5 83e52e394ab19e6b70e5ab0b687237e1
BLAKE2b-256 21739d6e9450b65b90041eee539a3c3483c42f952dd3a3006bb0b57bb272fc46

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page