Update variables.py

variables.py

@@ -11,16 +11,30 @@ metaprompt_explanations = {
     "bolism": "Utilize this method when working with autoregressive language models and when the task requires careful reasoning before conclusions. It's best for prompts that need detailed output formatting. Choose this over others when the prompt's structure and reasoning order are crucial."
 }
 
-# Load JSON data from environment variable
-PROMPT_DATA = json.loads(os.getenv('PROMPT_TEMPLATES', '[]'))
+# Load JSON data directly
+PROMPT_DATA = [
+    {
+        "name": name,
+        "description": data["description"],
+        "template": data["template"],
+        "examples": data.get("examples", [])  # Using get() to handle optional examples
+    }
+    for name, data in json.loads(os.getenv('PROMPT_TEMPLATES', '[]')).items()
+]
 
-# Create metaprompt_explanations dictionary from JSON data
+# Create metaprompt_explanations dictionary
 metaprompt_explanations = {
-    prompt["name"].lower().split()[0]: prompt["description"] 
+    prompt["name"].lower(): prompt["description"] 
     for prompt in PROMPT_DATA
 }
 
 
+# Generate explanation markdown
+explanation_markdown = "".join([
+    f"- **{key}**: {value}\n" 
+    for key, value in metaprompt_explanations.items()
+])
+
 models =         [
         # Meta-Llama models (all support system)
         "meta-llama/Meta-Llama-3-70B-Instruct",
@@ -45,11 +59,6 @@ models =         [
 
 explanation_markdown = "".join([f"- **{key}**: {value}\n" for key, value in metaprompt_explanations.items()])
 # Generate explanation markdown from JSON data
-explanation_markdown = "".join([
-    f"- **{prompt['name'].lower().split()[0]}**: {prompt['description']}\n" 
-    for prompt in PROMPT_DATA
-])
-
 
 
 meta_info=""
@@ -60,7 +69,7 @@ if not api_token:
 
 # Store templates in a dictionary
 meta_prompts = {
-    prompt["name"].lower().split()[0]: prompt["template"]
+    prompt["name"].lower(): prompt["template"]
     for prompt in PROMPT_DATA
 }