Prompts2026年4月7日·1 分钟阅读

Ell — Prompt Engineering as Code in Python

Treat prompts as versioned Python functions with automatic tracking, visualization, and A/B testing. Like Git for your AI prompts with a beautiful studio UI.

What is Ell?

Ell treats AI prompts as versioned Python functions. Every call is auto-tracked with inputs and outputs, viewable in the Ell Studio visualization dashboard.

In one sentence: Ell is a Python library that manages prompts as versioned functions with automatic tracing, visualization, and A/B testing — 6k+ GitHub stars.

For: Teams needing prompt version management and analytics. Supports: OpenAI, Anthropic, and compatible APIs.

Core Features

1. Prompts as Functions

Define with the @ell.simple decorator — automatically traced.

2. Ell Studio Visualization

A local dashboard shows version history, call records, and performance metrics.

3. Automatic Versioning

Modifying a prompt function automatically creates a new version.

4. Multimodal Support

Supports mixed text + image inputs.

FAQ

Q: How does it compare to LangChain? A: Ell focuses on prompt engineering (versioning, tracing, iteration); LangChain is a broader framework.

Q: Where is the data stored? A: Local SQLite — nothing is sent externally.

🙏

来源与感谢

MadcowD/ell — 6k+ stars, MIT

讨论

登录后参与讨论。
还没有评论,来写第一条吧。

相关资产