pg_tokenizer

pig build pkg pg_tokenizer         # build RPM / DEB packages

pig repo add pgsql -u          # Add repo and update cache

shared_preload_libraries = 'pg_tokenizer';

CREATE EXTENSION pg_tokenizer;

CREATE EXTENSION pg_tokenizer;

-- Create a tokenizer using the LLMLingua2 model
SELECT create_tokenizer('tokenizer1', $$
model = "llmlingua2"
$$);

-- Tokenize text
SELECT tokenize('PostgreSQL is a powerful, open-source object-relational database system. It has over 15 years of active development.', 'tokenizer1');

-- English tokenizer
SELECT create_tokenizer('en_tokenizer', $$
model = "llmlingua2"
$$);

-- Chinese tokenizer
SELECT create_tokenizer('zh_tokenizer', $$
model = "jieba"
$$);

-- Japanese tokenizer
SELECT create_tokenizer('ja_tokenizer', $$
model = "lindera/ipadic"
$$);

-- Tokenize English text
SELECT tokenize('full text search in PostgreSQL', 'en_tokenizer');

-- Tokenize Chinese text
SELECT tokenize('PostgreSQL是一个强大的数据库系统', 'zh_tokenizer');

CREATE EXTENSION IF NOT EXISTS pg_tokenizer CASCADE;
CREATE EXTENSION IF NOT EXISTS vchord_bm25 CASCADE;

-- Create a tokenizer
SELECT create_tokenizer('my_tokenizer', $$
model = "llmlingua2"
$$);

-- Tokenize text into bm25vectors for indexing and search
SELECT tokenize('your search query', 'my_tokenizer');