47be07f97f
* bump pg0 0.11.x and improve documentation * bump pg0 0.11.x and improve documentation * bump pg0 0.11.x and improve documentation * ci: test notebooks on ci * ci: test notebooks on ci * rm llms-full from repo * formatting * formatting
289 lines
9 KiB
Docker
289 lines
9 KiB
Docker
# Hindsight Docker Image
|
|
# Supports building API-only, Control Plane-only, or both
|
|
#
|
|
# Build args:
|
|
# INCLUDE_API=true/false - Include API (default: true)
|
|
# INCLUDE_CP=true/false - Include Control Plane (default: true)
|
|
#
|
|
# Examples:
|
|
# docker build -t hindsight . # Both (standalone)
|
|
# docker build -t hindsight-api --build-arg INCLUDE_CP=false . # API only
|
|
# docker build -t hindsight-cp --build-arg INCLUDE_API=false . # Control Plane only
|
|
|
|
ARG INCLUDE_API=true
|
|
ARG INCLUDE_CP=true
|
|
|
|
# =============================================================================
|
|
# Stage: API Builder
|
|
# =============================================================================
|
|
FROM python:3.11-slim AS api-builder
|
|
|
|
ARG INCLUDE_API
|
|
RUN if [ "$INCLUDE_API" != "true" ]; then echo "Skipping API build" && exit 0; fi
|
|
|
|
WORKDIR /app
|
|
|
|
# Install system dependencies and uv
|
|
RUN apt-get update && apt-get install -y \
|
|
gcc \
|
|
g++ \
|
|
curl \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& pip install --no-cache-dir uv
|
|
|
|
# Copy dependency files and README (required by pyproject.toml)
|
|
COPY hindsight-api/pyproject.toml ./api/
|
|
COPY hindsight-api/README.md ./api/
|
|
|
|
WORKDIR /app/api
|
|
|
|
# Sync dependencies (will create lock file if needed)
|
|
RUN uv sync
|
|
|
|
# Copy source code (alembic migrations are inside hindsight_api/)
|
|
COPY hindsight-api/hindsight_api ./hindsight_api
|
|
|
|
# Install the local package (uv sync only installed dependencies, not the package itself)
|
|
RUN uv pip install -e .
|
|
|
|
# =============================================================================
|
|
# Stage: SDK Builder (needed for Control Plane)
|
|
# =============================================================================
|
|
FROM node:20-slim AS sdk-builder
|
|
|
|
ARG INCLUDE_CP
|
|
RUN if [ "$INCLUDE_CP" != "true" ]; then echo "Skipping SDK build" && exit 0; fi
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy root package files for npm workspaces
|
|
COPY package.json package-lock.json ./
|
|
COPY hindsight-clients/typescript/ ./hindsight-clients/typescript/
|
|
|
|
# Install and build SDK using workspace (--ignore-scripts skips git hooks setup)
|
|
RUN npm ci --ignore-scripts -w @vectorize-io/hindsight-client
|
|
RUN npm run build -w @vectorize-io/hindsight-client
|
|
|
|
# =============================================================================
|
|
# Stage: Control Plane Builder
|
|
# =============================================================================
|
|
FROM node:20-slim AS cp-builder
|
|
|
|
ARG INCLUDE_CP
|
|
RUN if [ "$INCLUDE_CP" != "true" ]; then echo "Skipping CP build" && exit 0; fi
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy built SDK
|
|
COPY --from=sdk-builder /app/hindsight-clients/typescript /app/sdk
|
|
|
|
# Install Control Plane dependencies
|
|
# Only copy package.json (not package-lock.json) to ensure npm installs
|
|
# correct platform-specific native bindings for lightningcss/tailwindcss
|
|
COPY hindsight-control-plane/package.json ./
|
|
RUN npm install
|
|
|
|
# Copy Control Plane source (excluding node_modules via .dockerignore)
|
|
COPY hindsight-control-plane/ ./
|
|
# Remove package-lock.json to avoid conflicts with installed native bindings
|
|
RUN rm -f package-lock.json
|
|
|
|
# Link SDK (temporary for build)
|
|
RUN cd /app/sdk && npm link && cd /app && npm link @vectorize-io/hindsight-client
|
|
|
|
# Build Control Plane
|
|
RUN npm run build
|
|
|
|
# Create public directory if it doesn't exist
|
|
RUN mkdir -p public
|
|
|
|
# =============================================================================
|
|
# Stage: Final Image - API Only
|
|
# =============================================================================
|
|
FROM python:3.11-slim AS api-only
|
|
|
|
WORKDIR /app
|
|
|
|
# Install pg0 dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
curl \
|
|
libxml2 \
|
|
libssl3 \
|
|
libgssapi-krb5-2 \
|
|
libossp-uuid16 \
|
|
&& apt-get install -y libicu72 || apt-get install -y libicu74 || apt-get install -y libicu* \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& pip install --no-cache-dir uv
|
|
|
|
# Create non-root user (PostgreSQL cannot run as root)
|
|
RUN useradd -m -s /bin/bash hindsight
|
|
|
|
# Copy API with virtual environment from builder
|
|
COPY --from=api-builder /app/api /app/api
|
|
|
|
# Copy startup script
|
|
COPY docker/standalone/start-all.sh /app/start-all.sh
|
|
RUN chmod +x /app/start-all.sh
|
|
|
|
# Create data directory for pg0 and set ownership
|
|
RUN mkdir -p /app/data && chown -R hindsight:hindsight /app
|
|
|
|
# Switch to non-root user
|
|
USER hindsight
|
|
|
|
# Set PATH for hindsight user
|
|
ENV PATH="/app/api/.venv/bin:${PATH}"
|
|
|
|
# Pre-cache PostgreSQL binaries by starting/stopping pg0-embedded
|
|
ENV PG0_HOME=/home/hindsight/.pg0-cache
|
|
|
|
ENV PG0_HOME=/home/hindsight/.pg0
|
|
|
|
# Pre-download ML models to avoid runtime download
|
|
RUN /app/api/.venv/bin/python -c "\
|
|
from sentence_transformers import SentenceTransformer, CrossEncoder; \
|
|
print('Downloading embedding model...'); \
|
|
SentenceTransformer('BAAI/bge-small-en-v1.5'); \
|
|
print('Downloading cross-encoder model...'); \
|
|
CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2'); \
|
|
print('Models cached successfully')"
|
|
|
|
EXPOSE 8888
|
|
|
|
ENV HINDSIGHT_API_HOST=0.0.0.0
|
|
ENV HINDSIGHT_API_PORT=8888
|
|
ENV HINDSIGHT_API_LOG_LEVEL=info
|
|
ENV HINDSIGHT_ENABLE_API=true
|
|
ENV HINDSIGHT_ENABLE_CP=false
|
|
ENV PYTHONUNBUFFERED=1
|
|
|
|
CMD ["/app/start-all.sh"]
|
|
|
|
# =============================================================================
|
|
# Stage: Final Image - Control Plane Only
|
|
# =============================================================================
|
|
FROM node:20-alpine AS cp-only
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy built SDK
|
|
COPY --from=sdk-builder /app/hindsight-clients/typescript /app/sdk
|
|
|
|
# Copy Control Plane standalone build
|
|
WORKDIR /app/control-plane
|
|
COPY --from=cp-builder /app/.next/standalone ./
|
|
COPY --from=cp-builder /app/.next/static ./.next/static
|
|
COPY --from=cp-builder /app/public ./public
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy startup script
|
|
COPY docker/standalone/start-all.sh /app/start-all.sh
|
|
RUN chmod +x /app/start-all.sh
|
|
|
|
# Install curl for health checks
|
|
RUN apk add --no-cache curl bash
|
|
|
|
EXPOSE 9999
|
|
|
|
ENV NODE_ENV=production
|
|
ENV HINDSIGHT_CP_DATAPLANE_API_URL=http://localhost:8888
|
|
ENV HINDSIGHT_ENABLE_API=false
|
|
ENV HINDSIGHT_ENABLE_CP=true
|
|
|
|
CMD ["/app/start-all.sh"]
|
|
|
|
# =============================================================================
|
|
# Stage: Final Image - Standalone (both API and Control Plane)
|
|
# =============================================================================
|
|
FROM python:3.11-slim AS standalone
|
|
|
|
WORKDIR /app
|
|
|
|
# Install Node.js, curl, uv, and pg0 dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
curl \
|
|
libxml2 \
|
|
libssl3 \
|
|
libgssapi-krb5-2 \
|
|
libossp-uuid16 \
|
|
&& apt-get install -y libicu72 || apt-get install -y libicu74 || apt-get install -y libicu* \
|
|
&& curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
|
|
&& apt-get install -y nodejs \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& pip install --no-cache-dir uv
|
|
|
|
# Create non-root user (PostgreSQL cannot run as root)
|
|
RUN useradd -m -s /bin/bash hindsight
|
|
|
|
# Copy API with virtual environment from builder
|
|
COPY --from=api-builder /app/api /app/api
|
|
|
|
# Copy built SDK
|
|
COPY --from=sdk-builder /app/hindsight-clients/typescript /app/sdk
|
|
|
|
# Copy Control Plane standalone build
|
|
WORKDIR /app/control-plane
|
|
COPY --from=cp-builder /app/.next/standalone ./
|
|
COPY --from=cp-builder /app/.next/static ./.next/static
|
|
COPY --from=cp-builder /app/public ./public
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy startup script
|
|
COPY docker/standalone/start-all.sh /app/start-all.sh
|
|
RUN chmod +x /app/start-all.sh
|
|
|
|
# Create data directory for pg0 and set ownership
|
|
RUN mkdir -p /app/data && chown -R hindsight:hindsight /app
|
|
|
|
# Switch to non-root user
|
|
USER hindsight
|
|
|
|
# Set PATH for hindsight user
|
|
ENV PATH="/app/api/.venv/bin:${PATH}"
|
|
|
|
# Pre-cache PostgreSQL binaries by starting/stopping pg0-embedded
|
|
ENV PG0_HOME=/home/hindsight/.pg0-cache
|
|
RUN /app/api/.venv/bin/python -c "\
|
|
from pg0 import Pg0; \
|
|
print('Pre-caching PostgreSQL binaries...'); \
|
|
pg = Pg0(name='hindsight', port=5555, username='hindsight', password='hindsight', database='hindsight'); \
|
|
pg.start(); \
|
|
pg.stop(); \
|
|
print('PostgreSQL pre-cached to PG0_HOME')" || echo "Pre-download skipped"
|
|
|
|
ENV PG0_HOME=/home/hindsight/.pg0
|
|
|
|
# Pre-download ML models to avoid runtime download
|
|
RUN /app/api/.venv/bin/python -c "\
|
|
from sentence_transformers import SentenceTransformer, CrossEncoder; \
|
|
print('Downloading embedding model...'); \
|
|
SentenceTransformer('BAAI/bge-small-en-v1.5'); \
|
|
print('Downloading cross-encoder model...'); \
|
|
CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2'); \
|
|
print('Models cached successfully')"
|
|
|
|
EXPOSE 8888 9999
|
|
|
|
ENV HINDSIGHT_API_HOST=0.0.0.0
|
|
ENV HINDSIGHT_API_PORT=8888
|
|
ENV HINDSIGHT_API_LOG_LEVEL=info
|
|
ENV NODE_ENV=production
|
|
ENV HINDSIGHT_CP_DATAPLANE_API_URL=http://localhost:8888
|
|
ENV HINDSIGHT_ENABLE_API=true
|
|
ENV HINDSIGHT_ENABLE_CP=true
|
|
ENV PYTHONUNBUFFERED=1
|
|
|
|
CMD ["/app/start-all.sh"]
|
|
|
|
# =============================================================================
|
|
# Default target selection based on build args
|
|
# =============================================================================
|
|
FROM standalone AS default-both
|
|
FROM api-only AS default-api
|
|
FROM cp-only AS default-cp
|
|
|
|
# This selects the final stage based on INCLUDE_API and INCLUDE_CP
|
|
# Use --target to override: docker build --target api-only .
|
|
FROM standalone
|