webmarker-js 0.0.7 → 0.1.0

package/README.md

@@ -11,10 +11,11 @@ Mark web pages for use with vision-language models.
 
 ## Overview
 
-🚧 Under Construction
-
 **WebMarker** adds visual markings with labels to elements on a web page. This can be used for [Set-of-Mark (SoM)](https://github.com/microsoft/SoM) prompting, which improves visual grounding abilities of vision-language models such as GPT-4o, Claude 3.5, and Google Gemini 1.5.
 
+![Screenshot of marked Google homepage](https://github.com/user-attachments/assets/722e1034-06d4-4ccd-a7d6-f03749435681)
+
+
 ## How it works
 
 **1. Call the `mark()` function**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "webmarker-js",
-  "version": "0.0.7",
+  "version": "0.1.0",
   "description": "A library for marking web pages for Set-of-Mark (SoM) prompting with vision-language models.",
   "source": "src/index.ts",
   "main": "dist/main.js",

package/test-results/.last-run.json

@@ -1,4 +1,6 @@
 {
-  "status": "passed",
-  "failedTests": []
+  "status": "failed",
+  "failedTests": [
+    "bcbd25456d68a5d49fac-61d7a7d69e576e88625b"
+  ]
 }