{% extends "base.html" %} {% block title %}{{ project.name }} — evalkit{% endblock %} {% block content %}

Projects / {{ project.name }}

{{ project.name }}

{% if project.description %}

{{ project.description }}

{% endif %}
Evaluations Traces
{% if total > 0 %} {% if completed | length >= 2 %}

Score Timeline

{% endif %}
Compare Selected
{% for ev in evaluations %} {% endfor %}
ID Suite Status Score Date
{% if ev.status.value == 'complete' %} {% endif %} #{{ ev.id }} {{ ev.suite_name }} {{ ev.status.value }} {% if ev.average_score is not none %} {% set score = (ev.average_score * 100) | int %} {{ score }}% {% else %}—{% endif %} {{ ev.created_at.strftime('%Y-%m-%d %H:%M') }} View
{% if total_pages > 1 %}
{{ total }} evaluation{{ 's' if total != 1 }} — page {{ page }} of {{ total_pages }}
{% if page > 1 %} Prev {% endif %} {% for p in range(1, total_pages + 1) %} {% if p == page %} {{ p }} {% elif p == 1 or p == total_pages or (p >= page - 1 and p <= page + 1) %} {{ p }} {% elif p == 2 or p == total_pages - 1 %} {% endif %} {% endfor %} {% if page < total_pages %} Next {% endif %}
{% endif %} {% else %}

🏃

No evaluations yet

Use the API or CLI to run your first evaluation.

{% endif %}

Run via REST API

curl -X POST http://localhost:8000/api/v1/evaluate \
  -H "Content-Type: application/json" \
  -d '{
    "project_id": {{ project.id }},
    "suite": "rag_qa",
    "judge_provider": "openai",
    "test_cases": [
      {"question": "...", "context": ["..."], "answer": "..."}
    ]
  }'
{% endblock %}