Update README.md

This commit is contained in:
Zachary Huang 2025-02-22 20:25:16 -05:00 committed by GitHub
parent 7f0901bc64
commit d7bb1711d8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 48 deletions

View File

@ -13,71 +13,40 @@
A [100-line](pocketflow/__init__.py) minimalist LLM framework for ([Multi-](https://the-pocket.github.io/PocketFlow/multi_agent.html))[Agents](https://the-pocket.github.io/PocketFlow/agent.html), [Prompt Chaining](https://the-pocket.github.io/PocketFlow/decomp.html), [RAG](https://the-pocket.github.io/PocketFlow/rag.html), etc.
- ⚙️ Install via ```pip install pocketflow```, or just copy the [source code](pocketflow/__init__.py) (only 100 lines)
- Install via ```pip install pocketflow```, or just copy the [source code](pocketflow/__init__.py) (only 100 lines)
- 😊 If the 100 lines feel terse and youd prefer a friendlier intro, [check this out](https://chatgpt.com/share/678564bd-1ba4-8000-98e4-a6ffe363c1b8)
- If the 100 lines are terse, check out a [friendlier intro](https://chatgpt.com/share/678564bd-1ba4-8000-98e4-a6ffe363c1b8)
- 📖 Documentation: https://the-pocket.github.io/PocketFlow/
- Documentation: https://the-pocket.github.io/PocketFlow/
## Why Pocket Flow? Let LLM Agents Build LLM Agents for you!
Pocket Flow is designed to be **the framework used by LLM Agents**:
- 🧑 Human users specify project requirements and provide high-level guidance
- 🧑 Human users only need to specify LLM project requirements
- 🤖 LLM Agents build and maintain LLM projects for you, using *Pocket Flow*
- 🤖 LLM Agents build the LLM project for you, using *Pocket Flow*
To build LLM projects with LLMs Agents (ChatGPT, Claude, Cursor.ai, etc.):
<details>
<summary><b>(🫵 Click to expand) Use Claude to build LLM apps</b></summary>
- Create a [project](https://www.anthropic.com/news/projects) and upload the [docs](docs) to project knowledge
- Set project custom instructions. For example:
```
1. check "tool.md" and "llm.md" for the required functions.
2. design the high-level (batch) flow and nodes in artifact using mermaid
3. design the shared memory structure: define its fields, data structures, and how they will be updated.
Think out aloud for above first and ask users if your design makes sense.
4. Finally, implement. Start with simple, minimalistic codes without, for example, typing. Write the codes in artifact.
```
- Ask it to build LLM apps (Sonnet 3.5 strongly recommended)!
```
Help me build a chatbot based on a directory of PDFs.
```
<div align="center">
<img src="./assets/claude_project.gif"/>
</div>
</details>
<details>
<summary><b>(🫵 Click to expand) Use ChatGPT to build LLM apps</b></summary>
- Try the [GPT assistant](https://chatgpt.com/g/g-677464af36588191b9eba4901946557b-mini-llm-flow-assistant). However, it uses older models, which are good for explaining but not that good at coding.
<div align="center">
<img src="./assets/gpt_store.gif"/>
</div>
- For stronger coding capabilities, consider sending the [docs](docs) to more advanced models like O1.
- Paste the docs link (https://github.com/the-pocket/PocketFlow/tree/main/docs) to [Gitingest](https://gitingest.com/).
- Then, paste the generated contents into your O1 prompt, and ask it to build LLM apps.
To build LLM projects with LLM Agents (Cursor, ChatGPT, Claude, etc.):
</details>
- **[Cursor Rules](https://docs.cursor.com/context/rules-for-ai)**: Copy and paste the [.cursorrule](https://github.com/The-Pocket/PocketFlow/blob/main/assets/.cursorrules) (created from [docs](docs)) into the root of your project.
- **[ChatGPT Project](https://help.openai.com/en/articles/10169521-using-projects-in-chatgpt)**: Create a project and upload the [docs](docs) to project knowledge
- **[Claude Project](https://www.anthropic.com/news/projects)**: Create a project and upload the [docs](docs) to project knowledge
- **GPT Store**: Try this [GPT assistant](https://chatgpt.com/g/g-677464af36588191b9eba4901946557b-mini-llm-flow-assistant). However, it uses older models and is not good at coding.
## What's Pocket Flow? Graph + Shared Store
The [100 lines](pocketflow/__init__.py) capture what what we believe to be the core abstraction of LLM projects:
- **Graph** as the *Computation Model* that breaks down tasks into multiple-step LLM chains, with branching, recursion and nesting for agent-like decision-making
- **Shared Store** as the *Communication Model* that all graph nodes can read and write to
The [100 lines](pocketflow/__init__.py) capture what we believe to be the core abstraction of LLM projects:
- **Computation Model**: *Graph* that breaks down tasks into multiple nodes, with *branching, recursion and nesting*
- **Communication Model**: *Shared Store* that all graph nodes can read and write to
<br>
<div align="center">
@ -93,8 +62,8 @@ From there, its easy to implement popular design patterns like ([Multi-](http
</div>
<br>
- 📖 To learn about how Pocket Flow works, please check out the [documentation](https://the-pocket.github.io/PocketFlow/)
- 🤓 For a more in-depth dive on the design choices, check out the [essay](https://github.com/The-Pocket/.github/blob/main/profile/pocketflow.md)
- To learn about how Pocket Flow works, check out the [documentation](https://the-pocket.github.io/PocketFlow/)
- For an in-depth dive on the design, check out the [essay](https://github.com/The-Pocket/.github/blob/main/profile/pocketflow.md)