chatbot / evaluation /last_report.json
anris05's picture
bot
8a2dcce
Raw
History Blame Contribute Delete
7.74 kB
{
"summary": {
"total_questions": 20,
"route_accuracy": 1.0,
"avg_topic_recall": 1.0,
"retrieval_latency_ms_avg": 46.26,
"retrieval_latency_ms_p95": 101.1
},
"results": [
{
"id": "q01",
"query": "Explain how binary search works",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Binary Search"
],
"retrieved_topics": [
"Binary Search"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 144.79
},
{
"id": "q02",
"query": "What is the time complexity of merge sort?",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Merge Sort"
],
"retrieved_topics": [
"Merge Sort"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 30.63
},
{
"id": "q03",
"query": "Explain quick sort with an example",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Quick Sort"
],
"retrieved_topics": [
"Quick Sort"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 33.24
},
{
"id": "q04",
"query": "What is a Trie used for?",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Trie"
],
"retrieved_topics": [
"Trie"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 31.99
},
{
"id": "q05",
"query": "What is a doubly linked list?",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Doubly Linked List"
],
"retrieved_topics": [
"Doubly Linked List"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 34.44
},
{
"id": "q06",
"query": "Explain how a stack works",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Stack"
],
"retrieved_topics": [
"Stack"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 28.98
},
{
"id": "q07",
"query": "What is topological sort used for?",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Topological Sort"
],
"retrieved_topics": [
"Topological Sort"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 33.71
},
{
"id": "q08",
"query": "Explain Dijkstra's Algorithm",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Dijkstra's Algorithm"
],
"retrieved_topics": [
"Dijkstra's Algorithm"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 27.78
},
{
"id": "q09",
"query": "What is a segment tree?",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Segment Tree"
],
"retrieved_topics": [
"Segment Tree"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 35.57
},
{
"id": "q10",
"query": "Explain the sliding window technique",
"expected_route": "single_topic",
"predicted_route": "single_topic",
"route_correct": true,
"expected_topics": [
"Sliding Window Technique"
],
"retrieved_topics": [
"Sliding Window Technique"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 34.67
},
{
"id": "q11",
"query": "What is the difference between BFS and DFS?",
"expected_route": "comparison",
"predicted_route": "comparison",
"route_correct": true,
"expected_topics": [
"Breadth-First Search",
"Depth-First Search"
],
"retrieved_topics": [
"Breadth-First Search",
"Depth-First Search"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 51.73
},
{
"id": "q12",
"query": "Compare merge sort vs quick sort",
"expected_route": "comparison",
"predicted_route": "comparison",
"route_correct": true,
"expected_topics": [
"Merge Sort",
"Quick Sort"
],
"retrieved_topics": [
"Merge Sort",
"Quick Sort"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 63.2
},
{
"id": "q13",
"query": "Difference between a stack and a queue",
"expected_route": "comparison",
"predicted_route": "comparison",
"route_correct": true,
"expected_topics": [
"Stack",
"Queue"
],
"retrieved_topics": [
"Queue",
"Stack"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 66.79
},
{
"id": "q14",
"query": "Which one is better, Prim's Algorithm or Kruskal's Algorithm, for MST?",
"expected_route": "comparison",
"predicted_route": "comparison",
"route_correct": true,
"expected_topics": [
"Prim's Algorithm (MST)",
"Kruskal's Algorithm (MST)"
],
"retrieved_topics": [
"Kruskal's Algorithm (MST)",
"Prim's Algorithm (MST)"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 98.8
},
{
"id": "q15",
"query": "Compare AVL Tree and Binary Search Tree",
"expected_route": "comparison",
"predicted_route": "comparison",
"route_correct": true,
"expected_topics": [
"AVL Tree",
"Binary Search Tree"
],
"retrieved_topics": [
"AVL Tree",
"Binary Search",
"Binary Search Tree"
],
"topic_recall": 1.0,
"retrieval_latency_ms": 84.79
},
{
"id": "q16",
"query": "Who won the football World Cup in 2022?",
"expected_route": "out_of_scope",
"predicted_route": "out_of_scope",
"route_correct": true,
"expected_topics": [],
"retrieved_topics": [],
"topic_recall": 1.0,
"retrieval_latency_ms": 23.85
},
{
"id": "q17",
"query": "What's a good recipe for chocolate cake?",
"expected_route": "out_of_scope",
"predicted_route": "out_of_scope",
"route_correct": true,
"expected_topics": [],
"retrieved_topics": [],
"topic_recall": 1.0,
"retrieval_latency_ms": 16.91
},
{
"id": "q18",
"query": "What is the capital of France?",
"expected_route": "out_of_scope",
"predicted_route": "out_of_scope",
"route_correct": true,
"expected_topics": [],
"retrieved_topics": [],
"topic_recall": 1.0,
"retrieval_latency_ms": 14.83
},
{
"id": "q19",
"query": "Can you explain that again?",
"expected_route": "followup",
"predicted_route": "followup",
"route_correct": true,
"expected_topics": [],
"retrieved_topics": [],
"topic_recall": 1.0,
"retrieval_latency_ms": 44.24
},
{
"id": "q20",
"query": "Give me another example",
"expected_route": "followup",
"predicted_route": "followup",
"route_correct": true,
"expected_topics": [],
"retrieved_topics": [],
"topic_recall": 1.0,
"retrieval_latency_ms": 24.32
}
]
}