fleet-memory/docker/docker-compose/timescale/docker-compose.yaml
Nicolò Boschi 95c4220477
feat: support for pgvectorscale (DiskANN) (#378)
* feat: support for pgvectorscale (DiskANN)

* feat: support for pgvectorscale (DiskANN)
2026-02-16 14:19:56 +01:00

108 lines
4 KiB
YAML

name: hindsight
# Docker Compose file for Hindsight with Timescale extensions
# - pgvectorscale: DiskANN vector search (disk-based, scalable)
# - pg_textsearch: BM25 text search (high-performance keyword retrieval)
#
# Quick start:
# docker compose -f docker/docker-compose/timescale/docker-compose.yaml up -d --build
#
# Required environment variables:
# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
# - OPENAI_API_KEY (or configure another LLM provider)
#
# Optional environment variables with defaults:
# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
services:
db:
# Custom PostgreSQL image with Timescale extensions (pgvectorscale + pg_textsearch)
build:
context: .
dockerfile: Dockerfile
container_name: hindsight-db-timescale
restart: always
# Expose PostgreSQL port (using 5438 to avoid conflicts with other setups)
ports:
- "5438:5432"
environment:
POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
volumes:
- pg_data:/var/lib/postgresql/data
networks:
- hindsight-net
# Health check to ensure database is ready
healthcheck:
test: ["CMD-SHELL", "pg_isready -U hindsight_user"]
interval: 5s
timeout: 5s
retries: 5
timescale-init:
build:
context: .
dockerfile: Dockerfile
depends_on:
db:
condition: service_healthy
environment:
- PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
command: >
bash -c "
echo 'PostgreSQL is ready - creating hindsight_db database';
psql -h hindsight-db-timescale -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
echo 'Installing Timescale extensions...';
echo '1/3: Installing pgvector (required by pgvectorscale)...';
psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vector CASCADE;';
echo '2/3: Installing pgvectorscale (DiskANN vector search)...';
psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vectorscale CASCADE;';
echo '3/3: Installing pg_textsearch (BM25 text search)...';
psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE;';
echo '';
echo '✅ Timescale extensions installed successfully';
echo '';
echo 'Installed extensions:';
psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c \"\\dx\" | grep -E '(vector|vectorscale|pg_textsearch)';
"
restart: "no"
networks:
- hindsight-net
hindsight:
image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
container_name: hindsight-app-timescale
ports:
- "8888:8888"
- "9999:9999"
environment:
# LLM Configuration
HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
# Database Configuration
HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
# Timescale Extensions
# pgvectorscale: DiskANN algorithm for disk-based scalable vector search
HINDSIGHT_API_VECTOR_EXTENSION: pgvectorscale
# pg_textsearch: High-performance BM25 text search
HINDSIGHT_API_TEXT_SEARCH_EXTENSION: pg_textsearch
depends_on:
db:
condition: service_healthy
timescale-init:
condition: service_completed_successfully
networks:
- hindsight-net
networks:
hindsight-net:
driver: bridge
volumes:
pg_data: