70 lines
3.1 KiB
Markdown
70 lines
3.1 KiB
Markdown
---
|
||
layout: default
|
||
title: "Home"
|
||
nav_order: 1
|
||
---
|
||
|
||
# Pocket Flow
|
||
|
||
A [100-line](https://github.com/the-pocket/PocketFlow/blob/main/pocketflow/__init__.py) minimalist LLM framework for *Agents, Task Decomposition, RAG, etc*.
|
||
|
||
- **Lightweight**: Just the core graph abstraction in 100 lines. ZERO dependencies, and vendor lock-in.
|
||
- **Expressive**: Everything you love from larger frameworks—([Multi-](./design_pattern/multi_agent.html))[Agents](./design_pattern/agent.html), [Workflow](./design_pattern/workflow.html), [RAG](./design_pattern/rag.html), and more.
|
||
- **Agentic-Coding**: Intuitive enough for AI agents to help humans build complex LLM applications.
|
||
|
||
<div align="center">
|
||
<img src="https://github.com/the-pocket/.github/raw/main/assets/meme.jpg?raw=true" width="400"/>
|
||
</div>
|
||
|
||
|
||
## Core Abstraction
|
||
|
||
We model the LLM workflow as a **Graph + Shared Store**:
|
||
|
||
- [Node](./core_abstraction/node.md) handles simple (LLM) tasks.
|
||
- [Flow](./core_abstraction/flow.md) connects nodes through **Actions** (labeled edges).
|
||
- [Shared Store](./core_abstraction/communication.md) enables communication between nodes within flows.
|
||
- [Batch](./core_abstraction/batch.md) nodes/flows allow for data-intensive tasks.
|
||
- [Async](./core_abstraction/async.md) nodes/flows allow waiting for asynchronous tasks.
|
||
- [(Advanced) Parallel](./core_abstraction/parallel.md) nodes/flows handle I/O-bound tasks.
|
||
|
||
<div align="center">
|
||
<img src="https://github.com/the-pocket/.github/raw/main/assets/abstraction.png" width="900"/>
|
||
</div>
|
||
|
||
## Design Pattern
|
||
|
||
From there, it’s easy to implement popular design patterns:
|
||
|
||
- [Agent](./design_pattern/agent.md) autonomously makes decisions.
|
||
- [Workflow](./design_pattern/workflow.md) chains multiple tasks into pipelines.
|
||
- [RAG](./design_pattern/rag.md) integrates data retrieval with generation.
|
||
- [Map Reduce](./design_pattern/mapreduce.md) splits data tasks into Map and Reduce steps.
|
||
- [Structured Output](./design_pattern/structure.md) formats outputs consistently.
|
||
- [(Advanced) Multi-Agents](./design_pattern/multi_agent.md) coordinate multiple agents.
|
||
|
||
<div align="center">
|
||
<img src="https://github.com/the-pocket/.github/raw/main/assets/design.png" width="900"/>
|
||
</div>
|
||
|
||
## Utility Function
|
||
|
||
We **do not** provide built-in utilities. Instead, we offer *examples*—please *implement your own*:
|
||
|
||
- [LLM Wrapper](./utility_function/llm.md)
|
||
- [Viz and Debug](./utility_function/viz.md)
|
||
- [Web Search](./utility_function/websearch.md)
|
||
- [Chunking](./utility_function/chunking.md)
|
||
- [Embedding](./utility_function/embedding.md)
|
||
- [Vector Databases](./utility_function/vector.md)
|
||
- [Text-to-Speech](./utility_function/text_to_speech.md)
|
||
|
||
**Why not built-in?**: I believe it's a *bad practice* for vendor-specific APIs in a general framework:
|
||
- *API Volatility*: Frequent changes lead to heavy maintenance for hardcoded APIs.
|
||
- *Flexibility*: You may want to switch vendors, use fine-tuned models, or run them locally.
|
||
- *Optimizations*: Prompt caching, batching, and streaming are easier without vendor lock-in.
|
||
|
||
## Ready to build your Apps?
|
||
|
||
Check out [Agentic Coding Guidance](./guide.md), the fastest way to develop LLM projects with Pocket Flow!
|