From 9effc1f4e054ad357e67a62dcde0cd38445fb4c0 Mon Sep 17 00:00:00 2001
From: Dillon Laird <dillonalaird@gmail.com>
Date: Mon, 22 Apr 2024 14:38:41 -0700
Subject: [PATCH] updated readme

---
 README.md | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 741b8ff2..3daa36ef 100644
--- a/README.md
+++ b/README.md
@@ -31,7 +31,7 @@ pip install vision-agent
 ```
 
 Ensure you have an OpenAI API key and set it as an environment variable (if you are
-using Azure OpenAI please see the additional setup section):
+using Azure OpenAI please see the Azure setup section):
 
 ```bash
 export OPENAI_API_KEY="your-api-key"
@@ -96,6 +96,31 @@ you. For example:
 }]
 ```
 
+#### Custom Tools
+You can also add your own custom tools for your vision agent to use:
+    
+```python
+>>> from vision_agent.tools import Tool, register_tool
+>>> @register_tool
+>>> class NumItems(Tool):
+>>>    name = "num_items_"
+>>>    description = "Returns the number of items in a list."
+>>>    usage = {
+>>>        "required_parameters": [{"name": "prompt", "type": "list"}],
+>>>        "examples": [
+>>>            {
+>>>                "scenario": "How many items are in this list? ['a', 'b', 'c']",
+>>>                "parameters": {"prompt": "['a', 'b', 'c']"},
+>>>            }
+>>>        ],
+>>>    }
+>>>    def __call__(self, prompt: str) -> int:
+>>>        return len(prompt)
+```
+This will register it with the list of tools Vision Agent has access to. It will be able
+to pick it based on the tool description and use it based on the usage provided.
+
+#### Tool List
 | Tool | Description |
 | --- | --- |
 | CLIP | CLIP is a tool that can classify or tag any image given a set of input classes or tags. |
@@ -112,7 +137,7 @@ you. For example:
 
 It also has a basic set of calculate tools such as add, subtract, multiply and divide.
 
-### Additional Setup
+### Azure Setup
 If you want to use Azure OpenAI models, you can set the environment variable:
 
 ```bash