Feat: Add pg_bigm for keyword search in pgvector (#13876)

Signed-off-by: Yuichiro Utsumi <utsumi.yuichiro@fujitsu.com>

docker/.env.example

@@ -431,6 +431,8 @@ PGVECTOR_PASSWORD=difyai123456
 PGVECTOR_DATABASE=dify
 PGVECTOR_MIN_CONNECTION=1
 PGVECTOR_MAX_CONNECTION=5
+PGVECTOR_PG_BIGM=false
+PGVECTOR_PG_BIGM_VERSION=1.2-20240606
 
 # pgvecto-rs configurations, only available when VECTOR_STORE is `pgvecto-rs`
 PGVECTO_RS_HOST=pgvecto-rs

docker/docker-compose-template.yaml

@@ -322,8 +322,13 @@ services:
       POSTGRES_DB: ${PGVECTOR_POSTGRES_DB:-dify}
       # postgres data directory
       PGDATA: ${PGVECTOR_PGDATA:-/var/lib/postgresql/data/pgdata}
+      # pg_bigm module for full text search
+      PG_BIGM: ${PGVECTOR_PG_BIGM:-false}
+      PG_BIGM_VERSION: ${PGVECTOR_PG_BIGM_VERSION:-1.2-20240606}
     volumes:
       - ./volumes/pgvector/data:/var/lib/postgresql/data
+      - ./pgvector/docker-entrypoint.sh:/docker-entrypoint.sh
+    entrypoint: [ '/docker-entrypoint.sh' ]
     healthcheck:
       test: [ 'CMD', 'pg_isready' ]
       interval: 1s

docker/docker-compose.yaml

@@ -157,6 +157,8 @@ x-shared-env: &shared-api-worker-env
   PGVECTOR_DATABASE: ${PGVECTOR_DATABASE:-dify}
   PGVECTOR_MIN_CONNECTION: ${PGVECTOR_MIN_CONNECTION:-1}
   PGVECTOR_MAX_CONNECTION: ${PGVECTOR_MAX_CONNECTION:-5}
+  PGVECTOR_PG_BIGM: ${PGVECTOR_PG_BIGM:-false}
+  PGVECTOR_PG_BIGM_VERSION: ${PGVECTOR_PG_BIGM_VERSION:-1.2-20240606}
   PGVECTO_RS_HOST: ${PGVECTO_RS_HOST:-pgvecto-rs}
   PGVECTO_RS_PORT: ${PGVECTO_RS_PORT:-5432}
   PGVECTO_RS_USER: ${PGVECTO_RS_USER:-postgres}
@@ -741,8 +743,13 @@ services:
       POSTGRES_DB: ${PGVECTOR_POSTGRES_DB:-dify}
       # postgres data directory
       PGDATA: ${PGVECTOR_PGDATA:-/var/lib/postgresql/data/pgdata}
+      # pg_bigm module for full text search
+      PG_BIGM: ${PGVECTOR_PG_BIGM:-false}
+      PG_BIGM_VERSION: ${PGVECTOR_PG_BIGM_VERSION:-1.2-20240606}
     volumes:
       - ./volumes/pgvector/data:/var/lib/postgresql/data
+      - ./pgvector/docker-entrypoint.sh:/docker-entrypoint.sh
+    entrypoint: [ '/docker-entrypoint.sh' ]
     healthcheck:
       test: [ 'CMD', 'pg_isready' ]
       interval: 1s

docker/pgvector/docker-entrypoint.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+PG_MAJOR=16
+
+if [ "${PG_BIGM}" = "true" ]; then
+  # install pg_bigm
+  apt-get update
+  apt-get install -y curl make gcc postgresql-server-dev-${PG_MAJOR}
+
+  curl -LO https://github.com/pgbigm/pg_bigm/archive/refs/tags/v${PG_BIGM_VERSION}.tar.gz
+  tar xf v${PG_BIGM_VERSION}.tar.gz
+  cd pg_bigm-${PG_BIGM_VERSION} || exit 1
+  make USE_PGXS=1 PG_CONFIG=/usr/bin/pg_config
+  make USE_PGXS=1 PG_CONFIG=/usr/bin/pg_config install
+
+  cd - || exit 1
+  rm -rf v${PG_BIGM_VERSION}.tar.gz pg_bigm-${PG_BIGM_VERSION}
+
+  # enable pg_bigm
+  sed -i -e 's/^#\s*shared_preload_libraries.*/shared_preload_libraries = '\''pg_bigm'\''/' /var/lib/postgresql/data/pgdata/postgresql.conf
+fi
+
+# Run the original entrypoint script
+exec /usr/local/bin/docker-entrypoint.sh postgres