update images

docs/agent.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Agent"
-parent: "Design"
+parent: "Design Pattern"
 nav_order: 6
 ---
 

docs/decomp.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Workflow"
-parent: "Design"
+parent: "Design Pattern"
 nav_order: 2
 ---
 

docs/guide.md

@@ -10,11 +10,11 @@ nav_order: 1
 
 ## System Design Steps
 
-1. **Project Requirements**  
-   - Identify the project's core entities, and provide a step-by-step user story.  
-   - Define a list of both functional and non-functional requirements.
+1. **Project Requirements**: Understand what the project is for and what are required.
+
+2. **Utility Functions**: LLM Systems are like the brain
+
 
-2. **Utility Functions**  
    - Determine the utility functions on which this project depends (e.g., for LLM calls, web searches, file handling).  
    - Implement these functions and write basic tests to confirm they work correctly.
 

docs/index.md

@@ -37,7 +37,7 @@ We model the LLM workflow as a **Nested Directed Graph**:
 - [(Advanced) Async](./async.md)
 - [(Advanced) Parallel](./parallel.md)
 
-## Utility Functions
+## Utility Function
 
 - [LLM Wrapper](./llm.md)
 - [Tool](./tool.md)
@@ -48,7 +48,7 @@ We model the LLM workflow as a **Nested Directed Graph**:
 {: .warning }
 
 
-## Design Patterns
+## Design Pattern
 
 - [Structured Output](./structure.md)
 - [Workflow](./decomp.md)

docs/llm.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "LLM Wrapper"
-parent: "Utility"
+parent: "Utility Function"
 nav_order: 1
 ---
 

docs/mapreduce.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Map Reduce"
-parent: "Design"
+parent: "Design Pattern"
 nav_order: 3
 ---
 

docs/memory.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Chat Memory"
-parent: "Design"
+parent: "Design Pattern"
 nav_order: 5
 ---
 

docs/multi_agent.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "(Advanced) Multi-Agents"
-parent: "Design"
+parent: "Design Pattern"
 nav_order: 7
 ---
 

docs/node.md

@@ -26,6 +26,11 @@ A **Node** is the smallest building block. Each Node has 3 steps `prep->exec->po
    - Examples: *update DB, change states, log results*.
    - **Decide the next action** by returning a *string* (`action = "default"` if *None*).
 
+<div align="center">
+  <img src="https://github.com/the-pocket/PocketFlow/raw/main/assets/node.png?raw=true" width="400"/>
+</div>
+
+
 > **Why 3 steps?** To enforce the principle of *separation of concerns*. The data storage and data processing are operated separately.
 >
 > All steps are *optional*. E.g., you can only implement `prep` and `post` if you just need to process data.

docs/paradigm.md

@@ -1,6 +1,6 @@
 ---
 layout: default
-title: "Design"
+title: "Design Pattern"
 nav_order: 4
 has_children: true
 ---

docs/preparation.md

@@ -1,6 +1,6 @@
 ---
 layout: default
-title: "Utility"
+title: "Utility Function"
 nav_order: 3
 has_children: true
 ---

docs/rag.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "RAG"
-parent: "Design" 
+parent: "Design Pattern"
 nav_order: 4
 ---
 

docs/structure.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Structured Output"
-parent: "Design"
+parent: "Design Pattern"
 nav_order: 1
 ---
 

docs/tool.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Tool"
-parent: "Utility"
+parent: "Utility Function"
 nav_order: 2
 ---
 

docs/viz.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Viz and Debug"
-parent: "Utility"
+parent: "Utility Function"
 nav_order: 3
 ---