Document {{ loop.index }} - {{ doc_data.document_id }}
Example {{ loop.index }} of {{ documents_data|length }}
{% set outer_loop_index = loop.index %} {% set input_char_limit = 1000 %}
Input Document
{% if doc_data.content is mapping %}{% for key, value in doc_data.content.items() %}
{% if doc_data.content is not mapping and doc_data.content|length > input_char_limit %}
{{ key|e }}: {{ value|e }}
{% endfor %}{% elif doc_data.content|length > input_char_limit %}{{ doc_data.content[:input_char_limit]|e }}...{% else %}{{ doc_data.content|e }}{% endif %}
Showing first {{ input_char_limit }} characters of {{
doc_data.content|length }}
Show Full Document
{% endif %} {% if doc_data.metadata %}
View Metadata
{% endif %} {% if doc_data.attachments %}
{% if doc_data.attachments|length == 1 %}
{% set att = doc_data.attachments[0] %}
{% set att_url = att.url if att.url else ('data:' ~ (att.mime_type or 'image/jpeg') ~ ';base64,' ~ att.data if att.data else '') %}
{% if att_url and 'application/pdf' not in att_url[:30] %}
✓ Expected Output
{% if doc_data.expected_value is not none %}{{ doc_data.expected_value }}{% else %}No expected output for this task{% endif %}
{% for model_result in doc_data.model_results %}
{% set status = 'neutral' if model_result.is_correct is none else ('correct' if model_result.is_correct else 'incorrect') %}
{% if status == 'correct' %}✓ CORRECT{% elif status == 'incorrect' %}✗ INCORRECT{% else %}{{ 'SCORED' if model_result.task_scores else 'NO GROUND TRUTH' }}{% endif %}
{% if model_result.example_score is not none %}(Score: {{ "%.2f"|format(model_result.example_score) }}){% endif %}
{% endfor %}
{{ model_result.model }}
{{ model_result.predicted_value }}
Time:
{{ "%.3f"|format(model_result.response_time) }}s
Cost:
${{ "%.6f"|format(model_result.llm_cost) }}