updated vision tool docs to include required parameters

2025-12-16 12:28:30 +00:00 · 2024-08-14 19:41:49 +08:00
1 changed files with 3 additions and 1 deletions
--- a/docs/tools/VisionTool.md
+++ b/docs/tools/VisionTool.md
@@ -4,6 +4,8 @@

 This tool is used to extract text from images. When passed to the agent it will extract the text from the image and then use it to generate a response, report or any other output. The URL or the PATH of the image should be passed to the Agent.

+Supported filetypes are JPG, PNG, WEBP and GIF
+

 ## Installation
 Install the crewai_tools package
@@ -18,7 +20,7 @@ In order to use the VisionTool, the OpenAI API key should be set in the environm
 ```python
 from crewai_tools import VisionTool

-vision_tool = VisionTool()
+vision_tool = VisionTool(image_path_url="/path/to/your/local/image.jpg")

@agent
 def researcher(self) -> Agent: