parent page

docs/async.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Async"
-parent: Core Abstraction
+parent: "Core Abstraction"
 nav_order: 5
 ---
 

docs/batch.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Batch"
-parent: Core Abstraction
+parent: "Core Abstraction"
 nav_order: 4
 ---
 

docs/communication.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Communication"
-parent: Core Abstraction
+parent: "Core Abstraction"
 nav_order: 3
 ---
 

docs/core_abstraction.md

@@ -0,0 +1,14 @@
+---
+layout: default
+title: "Core Abstraction"
+nav_order: 3
+has_children: true
+---
+
+## Core Abstraction
+
+- [Node](./node.md)
+- [Flow](./flow.md)
+- [Communication](./communication.md)
+- [Batch](./batch.md)
+- [Async](./async.md)

docs/flow.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Flow"
-parent: Core Abstraction
+parent: "Core Abstraction"
 nav_order: 2
 ---
 

docs/node.md

@@ -1,7 +1,7 @@
 ---
 layout: default
 title: "Node"
-parent: Core Abstraction
+parent: "Core Abstraction"
 nav_order: 1
 ---
 
@@ -10,7 +10,7 @@ nav_order: 1
 A **Node** is the smallest building block of Mini LLM Flow. Each Node has three lifecycle methods:
 
 1. **`prep(shared)`**  
-   - Optionally preprocess data before calling your LLM or doing heavy computation.
+   - Optionally preprocess data before calling your LLM or doing heavy computation. 
    - Often used for tasks like reading files, chunking text, or validation.
    - Returns `prep_res`, which will be passed to both `exec()` and `post()`.