update scripts

.idea/workspace.xml

@@ -5,6 +5,7 @@
   </component>
   <component name="ChangeListManager">
     <list default="true" id="b60b8d5d-762f-4021-9ce4-054078cb27a7" name="Changes" comment="">
+      <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/app.py" beforeDir="false" afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
@@ -27,6 +28,7 @@
     "Python.app.executor": "Debug",
     "Python.main_backend.executor": "Run",
     "Python.model_operations.executor": "Run",
+    "Python.run_eval_suite.executor": "Debug",
     "Python.test.executor": "Run",
     "git-widget-placeholder": "main",
     "node.js.selected.package.tslint": "(autodetect)"
@@ -40,19 +42,24 @@
       <breakpoints>
         <line-breakpoint enabled="true" suspend="THREAD" type="python-line">
           <url>file://$PROJECT_DIR$/app.py</url>
-          <line>53</line>
-          <option name="timeStamp" value="39" />
-        </line-breakpoint>
-        <line-breakpoint enabled="true" suspend="THREAD" type="python-line">
-          <url>file://$PROJECT_DIR$/app.py</url>
-          <line>70</line>
+          <line>77</line>
           <option name="timeStamp" value="40" />
         </line-breakpoint>
         <line-breakpoint enabled="true" suspend="THREAD" type="python-line">
           <url>file://$PROJECT_DIR$/app.py</url>
-          <line>71</line>
+          <line>78</line>
           <option name="timeStamp" value="41" />
         </line-breakpoint>
+        <line-breakpoint enabled="true" suspend="THREAD" type="python-line">
+          <url>file://$PROJECT_DIR$/src/backend/run_eval_suite.py</url>
+          <line>46</line>
+          <option name="timeStamp" value="49" />
+        </line-breakpoint>
+        <line-breakpoint enabled="true" suspend="THREAD" type="python-line">
+          <url>file://$PROJECT_DIR$/src/populate.py</url>
+          <line>38</line>
+          <option name="timeStamp" value="50" />
+        </line-breakpoint>
       </breakpoints>
     </breakpoint-manager>
   </component>
@@ -60,10 +67,11 @@
     <SUITE FILE_PATH="coverage/HumanLikeness$.coverage" NAME=" Coverage Results" MODIFIED="1723441364832" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/tests" />
     <SUITE FILE_PATH="coverage/HumanLikeness$model_operations.coverage" NAME="model_operations Coverage Results" MODIFIED="1723539909992" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src/backend" />
     <SUITE FILE_PATH="coverage/HumanLikeness$main_backend.coverage" NAME="main_backend Coverage Results" MODIFIED="1723540718739" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
-    <SUITE FILE_PATH="coverage/HumanLikeness$app.coverage" NAME="app Coverage Results" MODIFIED="1723540867388" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+    <SUITE FILE_PATH="coverage/HumanLikeness$app.coverage" NAME="app Coverage Results" MODIFIED="1723543013531" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
     <SUITE FILE_PATH="coverage/HumanLikeness$evaluate_humanlike.coverage" NAME="evaluate_humanlike Coverage Results" MODIFIED="1723398170634" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/../Library/Containers/com.tencent.xinWeChat/Data/Library/Application Support/com.tencent.xinWeChat/2.0b4.0.9/32b9ff35361847f45b1e7909fcdff84c/Message/MessageTemp/7420e97876942c1eea73293c47ebb239/OpenData" />
     <SUITE FILE_PATH="coverage/HumanLikeness$humanlike.coverage" NAME="humanlike Coverage Results" MODIFIED="1723535841643" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="" />
     <SUITE FILE_PATH="coverage/HumanLikeness$envs.coverage" NAME="envs Coverage Results" MODIFIED="1723400161997" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src" />
+    <SUITE FILE_PATH="coverage/HumanLikeness$run_eval_suite.coverage" NAME="run_eval_suite Coverage Results" MODIFIED="1723542436560" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src/backend" />
     <SUITE FILE_PATH="coverage/HumanLikeness$test.coverage" NAME="test Coverage Results" MODIFIED="1723541738228" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/src" />
   </component>
 </project>

app.py

@@ -50,8 +50,15 @@ def process_pending_evals():
         return
 
     for _, eval_request in pending_eval_queue_df.iterrows():
-        # 根据具体的列名和数据格式调整 `eval_request` 的内容
-        print(f"Evaluating model: {eval_request.model}")
+        import re
+        model_link = eval_request['model']
+        match = re.search(r'>([^<]+)<', model_link)
+        if match:
+            eval_request['model'] = match.group(1)  # 赋值给 eval_request['model']
+        else:
+            eval_request['model'] = model_link  # 如果无法匹配，保留原始字符串
+
+        print(f"Evaluating model: {eval_request['model']}")
 
         # 调用评估函数
         run_eval_suite.run_evaluation(