Spaces:
Running
Running
openhands
openhands
commited on
Commit
Β·
701c496
1
Parent(s):
6324e5d
Remove submission page and add submission instructions to About page
Browse files- Removed submission page import and route from app.py
- Removed redirect_submission_on_close_script (no longer needed)
- Added new section in About page: 'Submitting Results & Accessing Raw Data'
- Instructions now point users to submit via GitHub PR to openhands-index-results
- Added information about accessing raw results from GitHub repository
- Clarified data format requirements (metadata.json and scores.json)
Submissions are now handled via GitHub PR workflow instead of web form
Co-authored-by: openhands <openhands@all-hands.dev>
about.py
CHANGED
|
@@ -106,7 +106,51 @@ def build_page():
|
|
| 106 |
)
|
| 107 |
gr.Markdown("---", elem_classes="divider-line")
|
| 108 |
|
| 109 |
-
# --- Section 6:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
gr.HTML(
|
| 111 |
"""
|
| 112 |
<h2>Citation</h2>
|
|
|
|
| 106 |
)
|
| 107 |
gr.Markdown("---", elem_classes="divider-line")
|
| 108 |
|
| 109 |
+
# --- Section 6: Submitting Results & Accessing Raw Data ---
|
| 110 |
+
gr.HTML(
|
| 111 |
+
"""
|
| 112 |
+
<h2>Submitting Results & Accessing Raw Data</h2>
|
| 113 |
+
|
| 114 |
+
<h3>How to Submit Your Agent Results</h3>
|
| 115 |
+
<p>
|
| 116 |
+
To submit your agent's evaluation results to the OpenHands Index:
|
| 117 |
+
</p>
|
| 118 |
+
<ol class="info-list">
|
| 119 |
+
<li>Run your agent on the supported benchmarks (SWE-bench, Multi-SWE-bench, SWE-bench Multimodal, SWT-bench, Commit0, GAIA)</li>
|
| 120 |
+
<li>Format your results according to the data structure documented in the repository</li>
|
| 121 |
+
<li>Submit a pull request to <a href="https://github.com/OpenHands/openhands-index-results" target="_blank" class="primary-link-button">github.com/OpenHands/openhands-index-results</a></li>
|
| 122 |
+
<li>Your submission should include:
|
| 123 |
+
<ul>
|
| 124 |
+
<li><code>metadata.json</code> with agent information, model used, and evaluation details</li>
|
| 125 |
+
<li><code>scores.json</code> with benchmark results and scores</li>
|
| 126 |
+
</ul>
|
| 127 |
+
</li>
|
| 128 |
+
</ol>
|
| 129 |
+
|
| 130 |
+
<h3>Accessing Raw Results</h3>
|
| 131 |
+
<p>
|
| 132 |
+
All raw evaluation results displayed on this leaderboard are publicly available at:
|
| 133 |
+
</p>
|
| 134 |
+
<p>
|
| 135 |
+
π <a href="https://github.com/OpenHands/openhands-index-results" target="_blank" class="primary-link-button">github.com/OpenHands/openhands-index-results</a>
|
| 136 |
+
</p>
|
| 137 |
+
<p>
|
| 138 |
+
The repository contains:
|
| 139 |
+
</p>
|
| 140 |
+
<ul class="info-list">
|
| 141 |
+
<li>Complete metadata for each agent submission</li>
|
| 142 |
+
<li>Detailed benchmark scores and metrics</li>
|
| 143 |
+
<li>Evaluation dates and configurations</li>
|
| 144 |
+
<li>Model and cost information</li>
|
| 145 |
+
</ul>
|
| 146 |
+
<p>
|
| 147 |
+
You can clone the repository, analyze the data, or use it for your own research and comparisons.
|
| 148 |
+
</p>
|
| 149 |
+
"""
|
| 150 |
+
)
|
| 151 |
+
gr.Markdown("---", elem_classes="divider-line")
|
| 152 |
+
|
| 153 |
+
# --- Section 7: Citation ---
|
| 154 |
gr.HTML(
|
| 155 |
"""
|
| 156 |
<h2>Citation</h2>
|
app.py
CHANGED
|
@@ -50,8 +50,6 @@ from test_generation import build_page as build_test_generation_page
|
|
| 50 |
print("β test_generation imported", file=sys.stderr)
|
| 51 |
from information_gathering import build_page as build_information_gathering_page
|
| 52 |
print("β information_gathering imported", file=sys.stderr)
|
| 53 |
-
from submission import build_page as build_submission_page
|
| 54 |
-
print("β submission imported", file=sys.stderr)
|
| 55 |
from about import build_page as build_about_page
|
| 56 |
print("β All pages imported", file=sys.stderr)
|
| 57 |
|
|
@@ -138,42 +136,6 @@ const tooltipInterval = setInterval(() => {
|
|
| 138 |
}, 200);
|
| 139 |
</script>
|
| 140 |
"""
|
| 141 |
-
redirect_submission_on_close_script = """
|
| 142 |
-
<script>
|
| 143 |
-
function initializeRedirectObserver() {
|
| 144 |
-
const successModal = document.querySelector('#success-modal');
|
| 145 |
-
|
| 146 |
-
if (successModal) {
|
| 147 |
-
const observer = new MutationObserver((mutationsList) => {
|
| 148 |
-
for (const mutation of mutationsList) {
|
| 149 |
-
// We only care about changes to the 'class' attribute.
|
| 150 |
-
if (mutation.type === 'attributes' && mutation.attributeName === 'class') {
|
| 151 |
-
|
| 152 |
-
// Check if the 'hide' class has been ADDED to the class list.
|
| 153 |
-
// This is how Gradio hides the modal.
|
| 154 |
-
if (successModal.classList.contains('hide')) {
|
| 155 |
-
console.log("Success modal was closed. Redirecting to homepage...");
|
| 156 |
-
// This is the command to redirect the browser.
|
| 157 |
-
window.location.href = '/home';
|
| 158 |
-
}
|
| 159 |
-
}
|
| 160 |
-
}
|
| 161 |
-
});
|
| 162 |
-
|
| 163 |
-
// Tell the observer to watch the modal for attribute changes.
|
| 164 |
-
observer.observe(successModal, { attributes: true });
|
| 165 |
-
}
|
| 166 |
-
}
|
| 167 |
-
|
| 168 |
-
// Polling mechanism to wait for Gradio to build the UI.
|
| 169 |
-
const redirectInterval = setInterval(() => {
|
| 170 |
-
if (document.querySelector('#success-modal')) {
|
| 171 |
-
clearInterval(redirectInterval);
|
| 172 |
-
initializeRedirectObserver();
|
| 173 |
-
}
|
| 174 |
-
}, 200);
|
| 175 |
-
</script>
|
| 176 |
-
"""
|
| 177 |
# --- Theme Definition ---
|
| 178 |
theme = gr.themes.Base(
|
| 179 |
primary_hue=gr.themes.Color(c100="#CFF5E8", c200="#B7EFDD", c300="#9FEAD1", c400="#87E5C5", c50="#E7FAF3", c500="#6FE0BA", c600="#57DBAF", c700="#3FD5A3", c800="#27D09C", c900="#0FCB8C", c950="#0fcb8c"),
|
|
@@ -270,7 +232,7 @@ print("Creating Gradio Blocks...", file=sys.stderr)
|
|
| 270 |
demo = gr.Blocks(
|
| 271 |
theme=theme,
|
| 272 |
css=final_css,
|
| 273 |
-
head=scroll_script + redirect_script + tooltip_script
|
| 274 |
title="OpenHands Index",
|
| 275 |
)
|
| 276 |
print("β Gradio Blocks created", file=sys.stderr)
|
|
@@ -310,10 +272,6 @@ with demo.route("About", "/about"):
|
|
| 310 |
build_about_page()
|
| 311 |
print("β About page built", file=sys.stderr)
|
| 312 |
|
| 313 |
-
# TODO: Fix submission page Modal component
|
| 314 |
-
# with demo.route("π Submit an Agent", "/submit"):
|
| 315 |
-
# build_submission_page()
|
| 316 |
-
|
| 317 |
# --- Scheduler and Launch
|
| 318 |
def restart_space_job():
|
| 319 |
print("Scheduler: Attempting to restart space.")
|
|
|
|
| 50 |
print("β test_generation imported", file=sys.stderr)
|
| 51 |
from information_gathering import build_page as build_information_gathering_page
|
| 52 |
print("β information_gathering imported", file=sys.stderr)
|
|
|
|
|
|
|
| 53 |
from about import build_page as build_about_page
|
| 54 |
print("β All pages imported", file=sys.stderr)
|
| 55 |
|
|
|
|
| 136 |
}, 200);
|
| 137 |
</script>
|
| 138 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
# --- Theme Definition ---
|
| 140 |
theme = gr.themes.Base(
|
| 141 |
primary_hue=gr.themes.Color(c100="#CFF5E8", c200="#B7EFDD", c300="#9FEAD1", c400="#87E5C5", c50="#E7FAF3", c500="#6FE0BA", c600="#57DBAF", c700="#3FD5A3", c800="#27D09C", c900="#0FCB8C", c950="#0fcb8c"),
|
|
|
|
| 232 |
demo = gr.Blocks(
|
| 233 |
theme=theme,
|
| 234 |
css=final_css,
|
| 235 |
+
head=scroll_script + redirect_script + tooltip_script,
|
| 236 |
title="OpenHands Index",
|
| 237 |
)
|
| 238 |
print("β Gradio Blocks created", file=sys.stderr)
|
|
|
|
| 272 |
build_about_page()
|
| 273 |
print("β About page built", file=sys.stderr)
|
| 274 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 275 |
# --- Scheduler and Launch
|
| 276 |
def restart_space_job():
|
| 277 |
print("Scheduler: Attempting to restart space.")
|