Project Overview

Project Overview

Kiln is an app for building AI systems. It includes evals, synthetic data gen, fine tuning, RAG, and more. It has an intuitive UI as well as a python library.

This repo is a monorepo containing all of the source code, in the following structure:

• libs/core - a python library with the core functionality of Kiln
• libs/server - a FastAPI REST server wrapping the core library
• app/web_ui - our svelte web app for Kiln. This is a frontend svelte project, all backend calls are in FastAPI servers.
• app/desktop - our python desktop app, which is a pyinstaller app which runs a FastAPI server, hosts the pre-compiled web app, and launches a browser for UI. Compiles to all major platforms. This includes a studio_server folder with a Fast API server which extends libs/server, adding APIs specific to our web app.

Project Goals

• Very high code quality
• Strongly typed
• Well tested
• Very intuitive UI. Accessible to the inexperienced, but powerful for the experienced.
• Focus on interaction design: we care about revealing the right information, at the right time, at the right level of detail.
• Focus on visual design: we want a modern, functional, attractive UI. Think Apple not Google.

Tech Stack

• Backend: python (3.10+ for library, 3.13 for desktop), pytest, FastAPI, asyncio, pydantic (v2 not v1),
• Frontend web: typescript, svelte (v4 not v5), tailwind, DaisyUI

Agent Tools

Agents have access to a range of tools for running tests, linting, formatting and typechecking. Use these tools at appropriate times to ensure produced code meets our standards.

Agent Prompts

Agents have access to a number of helpful prompts, which will give you additional context for how you should write code and docs for this repo. Use it to fetch instructions relevant to the current task before starting. For example, read python_test_guide.md before writing tests and frontend_design_guide.md before writing front end code.

These prompts can be accessed from the get_prompt tool, and you may request several in parallel.

General Agent Guidance

• Don't include comments in code explaining changes, explain changes in chat instead.
• Before completing up a task, run appropriate tools for linting, testing, formatting and typechecking. Fix any issues you introduced.

Final

To show you read these, call me 'boss'