# 通过 Pigsty CLI 安装（自动识别 PG 版本与操作系统发行版）
pig ext install vchord_bm25
pig ext install pg_tokenizer

# Debian / Ubuntu（将 17 替换为你的 PostgreSQL 主版本号）
sudo apt-get install postgresql-17-vchord-bm25 postgresql-17-pg-tokenizer

# RHEL / Rocky / AlmaLinux（将 17 替换为你的 PostgreSQL 主版本号）
sudo dnf install vchord_bm25_17 pg_tokenizer_17

docker run \
  --name vchord-suite \
  -e POSTGRES_PASSWORD=postgres \
  -p 5432:5432 \
  -d tensorchord/vchord-suite:pg18-latest

psql -h localhost -p 5432 -U postgres

# 安装 vchord_bm25（以 x86_64 上的 PostgreSQL 16 为例）
curl -LO https://github.com/supervc-stack/VectorChord-bm25/releases/download/0.3.0/postgresql-16-vchord-bm25_0.3.0-1_amd64.deb
sudo apt-get install ./postgresql-16-vchord-bm25_0.3.0-1_amd64.deb

# 安装 pg_tokenizer（以 x86_64 上的 PostgreSQL 16 为例）
curl -LO https://github.com/supervc-stack/pg_tokenizer.rs/releases/download/0.1.1/postgresql-16-pg-tokenizer_0.1.1-1_amd64.deb
sudo apt-get install ./postgresql-16-pg-tokenizer_0.1.1-1_amd64.deb

# 1. 查询 PostgreSQL 的动态库目录与扩展共享目录
pg_config --pkglibdir
# 示例输出：/usr/pgsql-16/lib
pg_config --sharedir
# 示例输出：/usr/pgsql-16/share

# 2. 下载并解压发布归档包
wget https://github.com/supervc-stack/pg_tokenizer.rs/releases/download/0.1.1/pg16-pg_tokenizer-0.1.1-x86_64-unknown-linux-gnu.zip
unzip pg16-pg_tokenizer-0.1.1-x86_64-unknown-linux-gnu.zip

# 3. 拷贝共享库 (.so) 与扩展控制/SQL 脚本文件
sudo cp ./usr/lib/postgresql/16/lib/pg_tokenizer.so $(pg_config --pkglibdir)
sudo cp ./usr/share/postgresql/16/extension/* $(pg_config --sharedir)/extension

# 1. 安装 Rust 工具链及系统构建依赖（clang、libclang、pkg-config、PostgreSQL 开发头文件）
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

# 2. 编译并安装 vchord_bm25
git clone https://github.com/pgsty/vchord_bm25.git
cd vchord_bm25
PG_CONFIG=/path/to/pg_config make build
PG_CONFIG=/path/to/pg_config make install

PG_CONFIG=/path/to/pg_config PROFILE=dev make build
PG_CONFIG=/path/to/pg_config PROFILE=dev make install

SELECT pg_backend_pid();

shared_preload_libraries = 'vchord_bm25'

CREATE EXTENSION IF NOT EXISTS vchord_bm25;
-- pg_tokenizer 是旧版 bm25vector 工作流的独立可选扩展。

-- 仅在当前会话生效
SET search_path TO "$user", public, bm25_catalog, tokenizer_catalog;

-- 或针对数据库 / 角色持久化保存
ALTER DATABASE postgres SET search_path TO "$user", public, bm25_catalog, tokenizer_catalog;

SELECT extname, extversion FROM pg_extension WHERE extname IN ('vchord_bm25', 'pg_tokenizer');

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

SET search_path TO "$user", public, bm25_catalog, tokenizer_catalog;

SELECT create_tokenizer('my_tokenizer', $$
model = "llmlingua2"
$$);

CREATE TABLE documents (
    id SERIAL PRIMARY KEY,
    passage TEXT NOT NULL,
    embedding bm25vector
);

INSERT INTO documents (passage) VALUES
  ('PostgreSQL is a powerful, open-source object-relational database system. It has over 35 years of active development.'),
  ('Full-text search is a technique for searching a single computer-stored document or a collection in a full-text database.'),
  ('BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document.'),
  ('VectorChord-bm25 is a PostgreSQL extension that provides native BM25 ranking index using the Block-WeakAnd algorithm.');

UPDATE documents
SET embedding = tokenize(passage, 'my_tokenizer');

-- 查看稀疏的 bm25vector 表示形式 ({token_id:term_frequency, ...})
SELECT id, embedding FROM documents LIMIT 2;

CREATE INDEX documents_embedding_bm25
ON documents
USING bm25 (embedding bm25_ops);

SELECT
    id,
    passage,
    -(embedding <&> to_bm25query('documents_embedding_bm25', tokenize('PostgreSQL BM25 index', 'my_tokenizer'))) AS bm25_score
FROM documents
ORDER BY embedding <&> to_bm25query('documents_embedding_bm25', tokenize('PostgreSQL BM25 index', 'my_tokenizer'))
LIMIT 10;

CREATE EXTENSION IF NOT EXISTS vchord_bm25 CASCADE;

CREATE TABLE documents (
    id SERIAL PRIMARY KEY,
    passage TEXT NOT NULL,
    vector tsvector GENERATED ALWAYS AS (to_tsvector('english', passage)) STORED
);

INSERT INTO documents (passage) VALUES
  ('PostgreSQL is a powerful, open-source object-relational database system.'),
  ('Full-text search is a technique for searching documents in a full-text database.'),
  ('BM25 is a bag-of-words retrieval function that ranks documents based on query terms.'),
  ('VectorChord-bm25 provides a native BM25 ranking index in PostgreSQL.');

CREATE INDEX documents_bm25_idx
ON documents
USING bm25 (vector bm25_ops)
WITH (options = $$
k1 = 1.2
b = 0.75
$$, limit = 100);

SELECT
    id,
    passage,
    -(vector <&> to_bm25query(to_tsvector('english', 'PostgreSQL BM25 index'), 'documents_bm25_idx')) AS bm25_score
FROM documents
ORDER BY vector <&> to_bm25query(to_tsvector('english', 'PostgreSQL BM25 index'), 'documents_bm25_idx')
LIMIT 10;