c029807add
* feat: support for other text and vector search pg extensions * test: increase timeout for test_batch_chunking_behavior to account for VectorChord BM25 tokenization overhead * feat: support for other text and vector search pg extensions
93 lines
3.7 KiB
YAML
93 lines
3.7 KiB
YAML
name: hindsight
|
|
# Docker Compose file for Hindsight with PostgreSQL and vectorchord
|
|
# docker compose -f docker/docker-compose/docker-compose.yaml down && sleep 2 && docker compose -f docker/docker-compose/docker-compose.yaml up -d
|
|
# Make sure to set the required environment variables before running:
|
|
# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
|
|
# - Configure LLM provider variables as needed (see below in the hindsight service)
|
|
#
|
|
# Usage:
|
|
# docker compose up -d
|
|
#
|
|
# 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)
|
|
# - HINDSIGHT_DB_VERSION: PostgreSQL version (default: 18)
|
|
|
|
services:
|
|
db:
|
|
# Use a PostgreSQL-Image with vectorchord extension pre-installed
|
|
image: tensorchord/vchord-suite:pg${HINDSIGHT_DB_VERSION:-18-latest}
|
|
container_name: hindsight-db
|
|
restart: always
|
|
# Expose PostgreSQL port
|
|
ports:
|
|
- "5436:5432"
|
|
environment:
|
|
POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
|
|
POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
|
|
POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
|
|
volumes:
|
|
- pg_data:/var/lib/postgresql/${HINDSIGHT_DB_VERSION:-18}/docker
|
|
networks:
|
|
- hindsight-net
|
|
|
|
vectorchord-init:
|
|
image: tensorchord/vchord-suite:pg18-latest
|
|
#container_name: vectorchord-init
|
|
depends_on:
|
|
- db
|
|
environment:
|
|
- PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
|
|
command: >
|
|
bash -c "
|
|
echo 'Waiting for PostgreSQL to be ready...';
|
|
until pg_isready -h hindsight-db -p 5432 -U hindsight_user; do
|
|
echo 'PostgreSQL is unavailable - sleeping';
|
|
sleep 2;
|
|
done;
|
|
echo 'PostgreSQL is ready - creating hindsight_db database';
|
|
psql -h hindsight-db -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
|
|
echo 'Creating extensions in hindsight_db database';
|
|
psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vchord CASCADE;';
|
|
psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_tokenizer CASCADE;';
|
|
psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vchord_bm25 CASCADE;';
|
|
echo 'Creating llmlingua2 tokenizer';
|
|
psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c \"SELECT create_tokenizer('llmlingua2', \\$\\$ model = \\\"llmlingua2\\\" \\$\\$);\" 2>/dev/null || echo 'Tokenizer already exists or creation skipped';
|
|
echo 'Database and extensions created successfully';
|
|
"
|
|
restart: "no"
|
|
networks:
|
|
- hindsight-net
|
|
|
|
hindsight:
|
|
image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
|
|
container_name: hindsight-app
|
|
ports:
|
|
- "8888:8888"
|
|
- "9999:9999"
|
|
environment:
|
|
# LLM Configuration (uses OpenAI for testing vchord)
|
|
# 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}
|
|
|
|
# Vector and Text Search Extensions
|
|
HINDSIGHT_API_VECTOR_EXTENSION: vchord
|
|
HINDSIGHT_API_TEXT_SEARCH_EXTENSION: vchord
|
|
|
|
depends_on:
|
|
- db
|
|
networks:
|
|
- hindsight-net
|
|
|
|
|
|
networks:
|
|
hindsight-net:
|
|
driver: bridge
|
|
|
|
volumes:
|
|
pg_data:
|