---
layout: default
title: "Design"
nav_order: 2
---

# Design Doc: Your Project Name

> Please DON'T remove notes for AI

## Requirements

> Notes for AI: Keep it simple and clear.
> If the requirements are abstract, write concrete user stories


## Flow Design

> Notes for AI:
> 1. Consider the design patterns of agent, map-reduce, rag, and workflow. Apply them if they fit.
> 2. Present a concise, high-level description of the workflow.

### Applicable Design Pattern:

1. Map the file summary into chunks, then reduce these chunks into a final summary.
2. Agentic file finder
   - *Context*: The entire summary of the file
   - *Action*: Find the file

### Flow high-level Design:

1. **First Node**: This node is for ...
2. **Second Node**: This node is for ...
3. **Third Node**: This node is for ...

```mermaid
flowchart TD
    firstNode[First Node] --> secondNode[Second Node]
    secondNode --> thirdNode[Third Node]
```
## Utility Functions

> Notes for AI:
> 1. Understand the utility function definition thoroughly by reviewing the doc.
> 2. Include only the necessary utility functions, based on nodes in the flow.

1. **Call LLM** (`utils/call_llm.py`)
   - *Input*: prompt (str)
   - *Output*: response (str)
   - Generally used by most nodes for LLM tasks

2. **Embedding** (`utils/get_embedding.py`)
   - *Input*: str
   - *Output*: a vector of 3072 floats
   - Used by the second node to embed text

## Node Design

### Shared Memory

> Notes for AI: Try to minimize data redundancy

The shared memory structure is organized as follows:

```python
shared = {
    "key": "value"
}
```

### Node Steps

> Notes for AI: Carefully decide whether to use Batch/Async Node/Flow.

1. First Node
  - *Purpose*: Provide a short explanation of the node’s function
  - *Type*: Decide between Regular, Batch, or Async
  - *Steps*:
    - *prep*: Read "key" from the shared store
    - *exec*: Call the utility function
    - *post*: Write "key" to the shared store

2. Second Node
  ...