HTS MCP
Skip to Content
DeploymentDocker

Docker

Run HTS MCP with Docker Compose, including PostgreSQL with pgvector.

Docker Compose

version: "3.8"
 
services:
  db:
    image: pgvector/pgvector:pg16
    environment:
      POSTGRES_DB: hts
      POSTGRES_USER: hts
      POSTGRES_PASSWORD: hts_password
    ports:
      - "5432:5432"
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U hts"]
      interval: 5s
      timeout: 5s
      retries: 5
 
  api:
    build: .
    ports:
      - "8000:8000"
    environment:
      DATABASE_URL: postgresql://hts:hts_password@db:5432/hts
      OPENAI_API_KEY: ${OPENAI_API_KEY}
      API_HOST: "0.0.0.0"
      API_PORT: "8000"
    depends_on:
      db:
        condition: service_healthy
 
volumes:
  pgdata:

Dockerfile

FROM python:3.11-slim
 
WORKDIR /app
 
# Install uv
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
 
# Copy project
COPY pyproject.toml uv.lock ./
RUN uv sync --frozen --no-dev
 
COPY src/ src/
COPY source-data/ source-data/
 
# Expose API port
EXPOSE 8000
 
# Run REST API
CMD ["uv", "run", "uvicorn", "hts.api:app", "--host", "0.0.0.0", "--port", "8000"]

Usage

Start Services

# Set your OpenAI key
export OPENAI_API_KEY=sk-...
 
# Start database and API
docker compose up -d

Run Data Pipeline

After the services are running, execute the pipeline inside the container:

# Load data
docker compose exec api uv run hts load general_tariff_data.txt
docker compose exec api uv run hts load-sections hts_sections.csv
docker compose exec api uv run hts load-chapters
 
# Enrich and embed
docker compose exec api uv run hts enrich-hts6
docker compose exec api uv run hts generate-multilevel-embeddings
 
# Build graph
docker compose exec api uv run hts generate-graph-edges
docker compose exec api uv run hts classify-graph-edges

Verify

# Check status
docker compose exec api uv run hts status
 
# Health check
curl http://localhost:8000/health
 
# Search
curl "http://localhost:8000/api/v1/search?query=steel+pipes"

pgvector Image

The pgvector/pgvector:pg16 image includes PostgreSQL 16 with the pgvector extension pre-installed. The extension is automatically available, no manual CREATE EXTENSION needed.

Volume Persistence

The pgdata volume persists database data across container restarts. To reset:

docker compose down -v  # removes volumes
docker compose up -d    # fresh start

Environment Variables

Pass all configuration via environment variables in docker-compose.yml or a .env file:

OPENAI_API_KEY=sk-...
API_KEY=your-secret-key
RATE_LIMIT_ENABLED=true

See Configuration for the complete reference.

ConfigurationAbout