phowell
/
pocketflow
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update docs

This commit is contained in:
zachary62 2025-01-01 22:42:46 +00:00
parent ae5600be2c
commit 9227b63811
2 changed files with 13 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docs/index.md
View File

@ -8,11 +8,6 @@ nav_order: 1
A [100-line](https://github.com/zachary62/miniLLMFlow/blob/main/minillmflow/__init__.py) minimalist LLM framework for *Agents, Task Decomposition, RAG, etc*. A [100-line](https://github.com/zachary62/miniLLMFlow/blob/main/minillmflow/__init__.py) minimalist LLM framework for *Agents, Task Decomposition, RAG, etc*.
<div align="center">
<img src="https://github.com/zachary62/miniLLMFlow/blob/main/assets/minillmflow.jpg?raw=true" width="400"/>
</div>
## Core Abstraction
We model the LLM workflow as a **Nested Directed Graph**: We model the LLM workflow as a **Nested Directed Graph**:
- **Nodes** handle simple (LLM) tasks. - **Nodes** handle simple (LLM) tasks.
@ -22,7 +17,12 @@ We model the LLM workflow as a **Nested Directed Graph**:
- **Batch** Nodes/Flows for data-intensive tasks. - **Batch** Nodes/Flows for data-intensive tasks.
- **Async** Nodes/Flows allow waits or **Parallel** execution - **Async** Nodes/Flows allow waits or **Parallel** execution
To learn more: <div align="center">
<img src="https://github.com/zachary62/miniLLMFlow/blob/main/assets/minillmflow.jpg?raw=true" width="400"/>
</div>
## Core Abstraction
- [Node](./node.md) - [Node](./node.md)
- [Flow](./flow.md) - [Flow](./flow.md)
- [Communication](./communication.md) - [Communication](./communication.md)
@ -30,22 +30,12 @@ To learn more:
- [(Advanced) Async](./async.md) - [(Advanced) Async](./async.md)
- [(Advanced) Parallel](./parallel.md) - [(Advanced) Parallel](./parallel.md)
## LLM Wrapper & Tools ## Low-Level Details (We Do Not Provide)
**We DO NOT provide built-in LLM wrappers and tools!**
I believe it is a *bad practice* to provide low-level implementations in a general framework:
- **APIs change frequently.** Hardcoding them makes maintenance a nightmare.
- You may need **flexibility.** E.g., using fine-tunined LLMs or deploying local ones.
- You may need **optimizations.** E.g., prompt caching, request batching, response streaming...
We provide some simple example implementations:
- [LLM Wrapper](./llm.md) - [LLM Wrapper](./llm.md)
- [Tool](./tool.md) - [Tool](./tool.md)
## Paradigm ## High-Level Paradigm
Based on the core abstraction, we implement common high-level paradigms:
- [Structured Output](./structure.md) - [Structured Output](./structure.md)
- Task Decomposition - Task Decomposition

5
docs/llm.md
View File

@ -62,3 +62,8 @@ def call_llm(prompt):
return response return response
``` ```
## Why Not Provide Built-in LLM Wrappers?
I believe it is a **bad practice** to provide LLM-specific implementations in a general framework:
- **LLM APIs change frequently**. Hardcoding them makes maintenance a nighmare.
- You may need **flexibility** to switch vendors, use fine-tuned models, or deploy local LLMs.
- You may need **optimizations** like prompt caching, request batching, or response streaming.