1.3 KiB
miniLLMFlow
Minimalist LLM framework in 100 lines. Express popular paradigms like agents, task decomposition, RAG, and more.
- Install via
pip install minillmflow. Or just copy the source codes (it's only 100 lines) - We strongly recommened using LLMs (e.g., Claude, ChatGPT, Cursor) to build LLM applications with this prompt
Why miniLLMFlow?
The future of programming will be heavily LLM-assited, and LLMs:
-
👍 Excel at Feature Implementation: Give proper context/docs, they know how to use APIs, tools, text chunking, prompt wrapping, etc. These shouldn't be part of an LLM framework, as they're hard to maintain, update, and optimize.
-
👎 Suck at Paradigm Design: Paradigms like MapReduce, DAG workflows, and recent agents are powerful for reasoning about problems. However, designing elegant paradigms is challenging, and LLMs tend to write redundant code.
Can we build a framework that: (1) removes redunant feature implementations, (2) but keep core paradigms for LLMs to program against? Turns out that we just need 100 lines of codes.
