From b0322b099a70dcee0626277e32aba32b9c66e086 Mon Sep 17 00:00:00 2001
From: Zachary Huang <33015448+zachary62@users.noreply.github.com>
Date: Thu, 9 Jan 2025 13:38:11 -0500
Subject: [PATCH] Update README.md
---
README.md | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/README.md b/README.md
index 5e8ccf3..c03ab18 100644
--- a/README.md
+++ b/README.md
@@ -1,8 +1,16 @@
Pocket Flow - LLM Framework in 100 Lines
+
+

[](https://minillmflow.github.io/PocketFlow/)
+
+

+
+
+
+
A [100-line](pocketflow/__init__.py) minimalist LLM framework for ([Multi-](https://minillmflow.github.io/PocketFlow/multi_agent.html))[Agents](https://minillmflow.github.io/PocketFlow/agent.html), [task decomposition](https://minillmflow.github.io/PocketFlow/decomp.html), [RAG](https://minillmflow.github.io/PocketFlow/rag.html), etc.
- Install via ```pip install pocketflow```, or just copy the [source codes](pocketflow/__init__.py) (only 100 lines)
@@ -43,10 +51,6 @@ The ideal framework for LLMs should (1) **strip away low-level implementation de
Pocket Flow is also a *learning resource*, as current frameworks abstract too much away.
-
-

-
-
## How Does it Work?
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.