lucisearch 0.8.1

Embeddable, in-process search engine — the SQLite/DuckDB of search
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156

//! Exit criteria integration tests for Milestone 5: Hybrid Search & RRF.

use luci::index::Index;
use luci::mapping::{FieldType, Mapping};
use serde_json::json;

fn search(
    index: &mut Index,
    query: serde_json::Value,
    size: usize,
) -> luci::search::results::SearchResults {
    let expr = luci::search::expression::parse_search(query, size).unwrap();
    index.search(&expr).unwrap()
}

fn test_dir(name: &str) -> std::path::PathBuf {
    let dir =
        std::env::temp_dir().join(format!("luci_m5_integration_{}_{name}", std::process::id()));
    let _ = std::fs::remove_dir_all(&dir);
    dir
}

fn cleanup(path: &std::path::Path) {
    let _ = std::fs::remove_dir_all(path);
}

fn build_hybrid_index(name: &str) -> (std::path::PathBuf, Index) {
    let path = test_dir(name);
    let schema = Mapping::builder()
        .field("title", FieldType::Text)
        .field("tag", FieldType::Keyword)
        .field("embedding", FieldType::dense_vector(4))
        .build();
    let index = Index::create_with_mapping(&path, schema).unwrap();

    index.bulk(vec![
        json!({"title": "search engine design", "tag": "tech", "embedding": [0.9, 0.1, 0.0, 0.0]}),
        json!({"title": "search algorithms", "tag": "tech", "embedding": [0.1, 0.9, 0.0, 0.0]}),
        json!({"title": "cute cats", "tag": "animal", "embedding": [0.8, 0.2, 0.0, 0.0]}),
        json!({"title": "search optimization", "tag": "tech", "embedding": [0.0, 0.0, 0.9, 0.1]}),
        json!({"title": "happy dog", "tag": "animal", "embedding": [0.0, 0.0, 0.0, 1.0]}),
    ]).unwrap();

    (path, index)
}

#[test]
fn hybrid_search_rrf() {
    let (path, mut index) = build_hybrid_index("hybrid");

    let results = search(
        &mut index,
        json!({
            "query": {"fusion": {
                "sources": [
                    {"match": {"title": "search engine"}},
                    {"knn": {
                        "field": "embedding",
                        "query_vector": [1.0, 0.0, 0.0, 0.0],
                        "k": 5,
                        "num_candidates": 10
                    }}
                ],
                "method": "rrf"
            }},
            "size": 5
        }),
        5,
    );

    assert!(!results.is_empty());
    assert_eq!(results.hit(0).unwrap().doc_id().as_u32(), 0);

    let ids: Vec<u32> = results.iter().map(|h| h.doc_id().as_u32()).collect();
    assert!(ids.contains(&1));
    assert!(ids.contains(&2));

    cleanup(&path);
}

#[test]
fn text_only_structured() {
    let (path, mut index) = build_hybrid_index("text_only");

    let results = search(
        &mut index,
        json!({
            "query": {"match": {"title": "search"}},
            "size": 10
        }),
        10,
    );

    assert!(results.total_hits().value >= 3);

    cleanup(&path);
}

#[test]
fn knn_only_structured() {
    let (path, mut index) = build_hybrid_index("knn_only");

    let results = search(
        &mut index,
        json!({
            "query": {"knn": {
                "field": "embedding",
                "query_vector": [1.0, 0.0, 0.0, 0.0],
                "k": 3,
                "num_candidates": 10
            }},
            "size": 3
        }),
        3,
    );

    assert_eq!(results.len(), 3);
    assert_eq!(results.hit(0).unwrap().doc_id().as_u32(), 0);
    assert_eq!(results.hit(1).unwrap().doc_id().as_u32(), 2);

    cleanup(&path);
}

#[test]
fn rrf_rank_based_scores() {
    let (path, mut index) = build_hybrid_index("rrf_scores");

    let results = search(
        &mut index,
        json!({
            "query": {"fusion": {
                "sources": [
                    {"match": {"title": "search"}},
                    {"knn": {
                        "field": "embedding",
                        "query_vector": [1.0, 0.0, 0.0, 0.0],
                        "k": 5,
                        "num_candidates": 10
                    }}
                ],
                "method": "rrf"
            }},
            "size": 5
        }),
        5,
    );

    for i in 0..results.len().saturating_sub(1) {
        assert!(results.hit(i).unwrap().score() >= results.hit(i + 1).unwrap().score());
    }
    for hit in results.iter() {
        assert!(hit.score() > 0.0);
    }

    cleanup(&path);
}