From 0f7e2b0d66ae721ee0010d040b2faeb98f3665d8 Mon Sep 17 00:00:00 2001 From: Zachary Huang <33015448+zachary62@users.noreply.github.com> Date: Thu, 2 Jan 2025 22:49:32 -0500 Subject: [PATCH] Update README.md --- README.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4045530..8917cca 100644 --- a/README.md +++ b/README.md @@ -31,9 +31,11 @@ Mini LLM Flow is also a *learning resource*, as current frameworks abstract too -## Tutorial +## How Does it Work? -- Please check out documentation: https://minillmflow.github.io/miniLLMFlow/ +The [100 lines](minillmflow/__init__.py) capture what we see as the core abstraction of most LLM frameworks: a **nested directed graph** that breaks down tasks into multiple (LLM) steps, with branching and recursion for agent-like decision-making. From there, it’s easy to layer on more complex features. + +- To learn more details, please check out documentation: https://minillmflow.github.io/miniLLMFlow/ - Beginner Tutorial: [Text summarization for Paul Graham Essay + QA agent](https://colab.research.google.com/github/zachary62/miniLLMFlow/blob/main/cookbook/demo.ipynb)