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

Update agent.md

This commit is contained in:
Zachary Huang 2025-03-14 13:02:38 -04:00 committed by GitHub
parent 61b8edbb78
commit 2905c6f5a8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/design_pattern/agent.md
View File

@ -9,12 +9,6 @@ nav_order: 6
Agent is a powerful design pattern in which nodes can take dynamic actions based on the context.
The core of building **high-performance** and **reliable** agents boils down to:
1. **Input Context:** Provide *relevant, minimal context.* For example, rather than including an entire chat history, retrieve the most relevant via [RAG](./rag.md). Even with larger context windows, LLMs still fall victim to ["lost in the middle"](https://arxiv.org/abs/2307.03172), overlooking mid-prompt content.
2. **Action Space:** Provide *a well-structured and unambiguous* set of actions—avoiding overlap like separate `read_databases` or `read_csvs`. Instead, import CSVs into the database and then use one parameterized (e.g., table name) or programmable action (e.g., via SQL) to query data.
<div align="center">
<img src="https://github.com/the-pocket/PocketFlow/raw/main/assets/agent.png?raw=true" width="350"/>
</div>
@ -49,6 +43,13 @@ parameters:
```"""
```
The core of building **high-performance** and **reliable** agents boils down to:
1. **Input Context:** Provide *relevant, minimal context.* For example, rather than including an entire chat history, retrieve the most relevant via [RAG](./rag.md). Even with larger context windows, LLMs still fall victim to ["lost in the middle"](https://arxiv.org/abs/2307.03172), overlooking mid-prompt content.
2. **Action Space:** Provide *a well-structured and unambiguous* set of actions—avoiding overlap like separate `read_databases` or `read_csvs`. Instead, import CSVs into the database and then use one parameterized (e.g., table name) or programmable action (e.g., via SQL) to query data.
### Example: Search Agent
This agent:
@ -130,4 +131,4 @@ search - "decide" >> decide # Loop back
flow = Flow(start=decide)
flow.run({"query": "Who won the Nobel Prize in Physics 2024?"})
```
```