{{ title }}

Generated on {{ timestamp }}

Summary

{{ total_items }}
Total Items
{{ successful }}
Successful
{{ failed }}
Failed
{% if overall_score is not none %}
{{ "%.4f"|format(overall_score) }}
Overall Score
{% endif %}
{% if metrics %}

Metrics

{% for name, score in metrics|dictsort %} {% endfor %}
Metric Average Score
{{ name }} {% if score >= 0.8 %} {{ "%.4f"|format(score) }} {% elif score >= 0.5 %} {{ "%.4f"|format(score) }} {% else %} {{ "%.4f"|format(score) }} {% endif %}
{% endif %} {% if errors %}

Error Analysis

{% for err_type, count in errors|dictsort %} {% endfor %}
Error Type Count
{{ err_type }} {{ count }}
{% endif %} {% if results %}

Sample Results

{% for item in results %}

Result #{{ loop.index }}

{{ item.question }}
{% if item.answer %}
Answer: {{ item.answer }}
{% endif %} {% if item.metrics %}
{% for metric_name, score in item.metrics|dictsort %} {{ metric_name }}: {{ "%.4f"|format(score) }} {% endfor %}
{% endif %}
{% endfor %}
{% endif %}

Configuration

Dataset{{ config.dataset.path }}
LLM Provider{{ config.llm.provider }}/{{ config.llm.model }}
Retriever{{ config.retriever.provider }}
Output Format{{ config.report.output.value }}