Full-Text Index

CREATE INDEX ON Article (title, body) FULL_TEXT
  METADATA {
    "analyzer": "org.apache.lucene.analysis.standard.StandardAnalyzer",
    "title_analyzer": "org.apache.lucene.analysis.en.EnglishAnalyzer"
  }

SELECT * FROM Article
WHERE SEARCH_INDEX('Article[content]', 'java programming')

SELECT * FROM Article
WHERE SEARCH_FIELDS(['title', 'body'], 'database tutorial')

-- Requires both terms
SELECT * FROM Article WHERE SEARCH_INDEX('Article[content]', '+java +programming')

-- Excludes documents about python
SELECT * FROM Article WHERE SEARCH_INDEX('Article[content]', 'java -python')

SELECT * FROM Article WHERE SEARCH_INDEX('Article[content]', '"machine learning"')

SELECT * FROM Article WHERE SEARCH_INDEX('Article[content]', 'data*')

SELECT * FROM Article WHERE SEARCH_INDEX('Article[content]', 'database~')
-- also matches terms within edit distance 2 (Lucene default), e.g. "databaSe", "databasee"

-- Only match "database" in the title field
SELECT * FROM Article WHERE SEARCH_INDEX('Article[title,body]', 'title:database')

-- Combine field-specific and general terms
SELECT * FROM Article WHERE SEARCH_INDEX('Article[title,body]', '+title:"multi model" -nosql')

-- Make "java" count three times as much as "database" in the ranking
SELECT title, $score FROM Article
WHERE SEARCH_INDEX('Article[content]', 'java^3 database') ORDER BY $score DESC

-- Boost a field-qualified term, combined with a required term
SELECT title, $score FROM Article
WHERE SEARCH_INDEX('Article[title,body]', '+database title:java^5') ORDER BY $score DESC

-- Boost a whole OR group
SELECT title, $score FROM Article
WHERE SEARCH_INDEX('Article[title,body]', '(title:java OR title:python)^3 body:cooking') ORDER BY $score DESC

-- BM25 with tuned parameters
CREATE INDEX ON Article (content) FULL_TEXT
  METADATA { "similarity": "BM25", "bm25_k1": 1.2, "bm25_b": 0.75 }

-- Keep the legacy match-count scoring
CREATE INDEX ON Article (content) FULL_TEXT
  METADATA { "similarity": "CLASSIC" }

CREATE INDEX ON Article (title, body) FULL_TEXT
  METADATA { "similarity": "BM25", "title_boost": 3.0 }

database.getSchema().buildTypeIndex("Article", new String[] { "title", "body" })
    .withType(Schema.INDEX_TYPE.FULL_TEXT).withFullTextType()
    .withBM25(1.2f, 0.75f)          // similarity = BM25, k1, b
    .withFieldBoost("title", 3.0f)  // per-field boost
    .create();

SELECT title, $score
FROM Article
WHERE SEARCH_INDEX('Article[content]', 'java programming')
ORDER BY $score DESC

SELECT title, $score AS relevance
FROM Article
WHERE SEARCH_FIELDS(['content'], 'java programming')
ORDER BY relevance DESC
LIMIT 10

EXPLAIN SELECT title, $score FROM Article
WHERE SEARCH_INDEX('Article[content]', 'java database') = true

SELECT title, $score, $similarity
FROM Article
WHERE `fulltext.searchIndexMore`('Article[content]', [#10:3])
ORDER BY $similarity DESC

SELECT title, $similarity
FROM Article
WHERE `fulltext.searchFieldsMore`(['content'], [#10:3])
ORDER BY $similarity DESC

SELECT title, $similarity
FROM Article
WHERE SEARCH_INDEX_MORE('Article[content]', [#10:3, #10:4])
ORDER BY $similarity DESC

SELECT title, $score, $similarity
FROM Article
WHERE SEARCH_INDEX_MORE('Article[content]', [#10:3])
ORDER BY $similarity DESC
LIMIT 5

SELECT title, $similarity
FROM Article
WHERE `fulltext.searchFieldsMore`(['title', 'content'], [#10:3], {
  minTermFreq: 1,
  minDocFreq: 3,
  maxQueryTerms: 50,
  excludeSource: false
})

SELECT title, author, $score AS relevance
FROM BlogPost
WHERE SEARCH_INDEX('BlogPost[title,body]', '+java +spring -legacy')
ORDER BY relevance DESC
LIMIT 20

SELECT title
FROM Product
WHERE SEARCH_INDEX('Product[name]', 'micro*')

CREATE INDEX ON Article (content) FULL_TEXT
  METADATA { "analyzer": "org.apache.lucene.analysis.en.EnglishAnalyzer" }

SELECT * FROM Article WHERE SEARCH_INDEX('Article[content]', 'running')
-- also returns documents containing "run", "runs", "ran"

SELECT title, $similarity AS score
FROM Article
WHERE SEARCH_INDEX_MORE('Article[title,body]', [#10:42], {
  "minTermFreq": 1,
  "minDocFreq": 2,
  "maxQueryTerms": 30
})
ORDER BY score DESC
LIMIT 5

SELECT title, $similarity
FROM Article
WHERE SEARCH_INDEX_MORE('Article[content]', [#10:1, #10:7, #10:12])
ORDER BY $similarity DESC
LIMIT 10

SELECT title, caseNumber, score
FROM (
  SELECT expand(`vector.fuse`(
      `vector.neighbors`('Case[dense]', :denseVec, 100),
      `vector.sparseNeighbors`('Case[tokens,weights]', :qIdx, :qVal, 100),
      (SELECT @rid, $score FROM Case WHERE SEARCH_INDEX('Case[content]', :keywords) = true),
      { fusion: 'RRF', k: 60 }
  ))
)
ORDER BY score DESC
LIMIT 10

SELECT caseNumber, title
FROM (
  SELECT expand(out('RELATED_TO'))
  FROM (
    SELECT expand(`vector.fuse`(
        `vector.neighbors`('Case[dense]', :denseVec, 100),
        (SELECT @rid, $score FROM Case WHERE SEARCH_INDEX('Case[content]', :keywords) = true),
        { fusion: 'RRF' }
    )) LIMIT 10
  )
)