PromptPressure Evaluation Report

Date: {{ timestamp }}

Config: {{ config.get('config_file', 'N/A') }}

Model: {{ config.get('model_name') }} (Adapter: {{ config.get('adapter') }})

{{ total_evals }}
Total Prompts
{% if metrics.get('average_response_time') %}
{{ "%.2f"|format(metrics['average_response_time']) }}s
Avg Latency
{% endif %} {% if metrics.get('errors') %}
{{ metrics['errors'] }}
Errors
{% endif %}

Detailed Results

{% for item in results %} {% endfor %}
ID Prompt Response Scores/Criteria
{{ item.get('id', '-') }}{% if item.get('multi_turn') %}
{{ item.get('turns_completed', 0) }}/{{ item.get('turns_total', 0) }} turns{% endif %}		 {% if item.get('multi_turn') and item.get('turn_responses') %}{% for tr in item.get('turn_responses', []) %}
Turn {{ tr.turn }}: {{ tr.user[:120] }}{% if tr.user|length > 120 %}...{% endif %}
{% endfor %}{% else %}{{ item.get('prompt') }}{% endif %}
{% if item.get('multi_turn') and item.get('turn_responses') %}{% for tr in item.get('turn_responses', []) %}[Turn {{ tr.turn }}] {{ tr.assistant or '[ERROR]' }} {% endfor %}{% else %}{{ item.get('response') }}{% endif %}
 {% if item.get('scores') %} {% for criterion, passed in item.get('scores').items() %} {{ criterion }}: {{ 'PASS' if passed else 'FAIL' if passed is sameas false else 'N/A' }}
{% endfor %} {% else %} No automated scoring available {% if item.get('eval_criteria') %}
Criteria: {{ item.get('eval_criteria')|list|join(', ') }} {% endif %} {% endif %}