Merge pull request #100 from ggozad/feat/docker

Support for docker & docker-compose with examples.

.dockerignore

@@ -0,0 +1,55 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments (uv best practice)
+.venv/
+venv/
+env/
+
+# Data
+*.lancedb/
+data/
+docs/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Git
+.git/
+.gitignore
+
+# Development
+tests/
+.pytest_cache/
+.coverage
+htmlcov/
+
+# Examples
+examples/

docker/Dockerfile

@@ -0,0 +1,36 @@
+# syntax=docker/dockerfile:1
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim AS builder
+
+WORKDIR /app
+
+# Enable bytecode compilation for faster startup
+ENV UV_COMPILE_BYTECODE=1 \
+    UV_LINK_MODE=copy
+
+# Install dependencies into a venv
+COPY pyproject.toml uv.lock ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-install-project --extra voyageai --extra mxbai --extra a2a
+
+# Install the project itself
+COPY . .
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-editable --extra voyageai --extra mxbai --extra a2a
+
+# Final layer
+FROM python:3.13-slim
+WORKDIR /app
+COPY --from=builder /app/.venv /app/.venv
+COPY --from=builder /app /app
+
+# Set default data directory
+RUN mkdir -p /data
+ENV DEFAULT_DATA_DIR=/data
+
+ENV PATH="/app/.venv/bin:$PATH"
+
+# Expose ports for MCP and A2A
+EXPOSE 8000 8001
+
+# Run all services (monitoring, MCP, A2A)
+CMD ["python", "-m", "haiku.rag.cli", "serve", "--monitor", "--mcp", "--mcp-port", "8001", "--a2a", "--a2a-host", "0.0.0.0", "--a2a-port", "8000", "--db", "/data/haiku.rag.lancedb"]

docker/README.md

@@ -0,0 +1,27 @@
+# haiku.rag Docker Image
+
+Dockerfile for building haiku.rag with all extras (voyageai, mxbai, a2a).
+
+## Building
+
+```bash
+docker build -f docker/Dockerfile -t haiku-rag .
+```
+
+## Running
+
+```bash
+docker run -p 8000:8000 -p 8001:8001 \
+  -v $(pwd)/data:/data \
+  -e EMBEDDINGS_PROVIDER=ollama \
+  -e EMBEDDINGS_MODEL=nomic-embed-text \
+  -e QA_PROVIDER=ollama \
+  -e QA_MODEL=qwen3\
+  haiku-rag
+```
+
+Note: The environment variables above override the defaults. See [Configuration docs](https://ggozad.github.io/haiku.rag/configuration/) for all options.
+
+## Docker Compose
+
+See `examples/docker/` for a complete setup example.

examples/README.md

@@ -2,6 +2,17 @@
 
 This directory contains example scripts demonstrating various features of haiku.rag.
 
+## Docker Example
+
+**Directory:** `docker/`
+
+Complete Docker setup for running haiku.rag with all services:
+- File monitoring for automatic document indexing
+- MCP server for AI assistant integration
+- A2A agent for conversational interactions
+
+See `docker/README.md` for setup instructions.
+
 ## A2A Security Examples
 
 **Directory:** `a2a-security/`

examples/docker/.env.example

@@ -0,0 +1,16 @@
+# Database directory
+DEFAULT_DATA_DIR=/data
+
+# File monitoring
+MONITOR_DIRECTORIES=/docs
+
+# Default: Ollama on host
+EMBEDDINGS_PROVIDER=ollama
+EMBEDDINGS_MODEL=nomic-embed-text
+QA_PROVIDER=ollama
+QA_MODEL=qwen3
+OLLAMA_BASE_URL=http://host.docker.internal:11434
+
+# For other providers, see: https://ggozad.github.io/haiku.rag/configuration/
+
+ENV=production

examples/docker/.gitignore

@@ -0,0 +1,8 @@
+# Data directory
+data/
+
+# Documents directory
+docs/
+
+# Environment file with secrets
+.env

examples/docker/README.md

@@ -0,0 +1,47 @@
+# haiku.rag Docker Compose Example
+
+Run haiku.rag with file monitoring, MCP server, and A2A agent.
+
+## Quick Start
+
+```bash
+mkdir -p data docs
+cp .env.example .env  # Edit if needed
+docker compose up -d
+```
+
+Place documents in `docs/` for automatic indexing.
+
+## Usage
+
+```bash
+# List documents
+docker compose exec haiku-rag haiku-rag list
+
+# Search
+docker compose exec haiku-rag haiku-rag search "your query"
+
+# Ask questions
+docker compose exec haiku-rag haiku-rag ask "What is haiku.rag?"
+
+# A2A interactive client
+docker compose exec haiku-rag haiku-rag a2aclient --url http://localhost:8000
+```
+
+## Ports
+
+- `8000` - A2A agent
+- `8001` - MCP server
+
+## Configuration
+
+Edit `.env` or `docker-compose.yml` to configure providers. See the [Configuration documentation](https://ggozad.github.io/haiku.rag/configuration/) for all options.
+
+Default setup uses Ollama on the host (`host.docker.internal:11434`).
+
+## Documentation
+
+- [Configuration](https://ggozad.github.io/haiku.rag/configuration/)
+- [CLI Commands](https://ggozad.github.io/haiku.rag/cli/)
+- [MCP Server](https://ggozad.github.io/haiku.rag/mcp/)
+- [A2A Agent](https://ggozad.github.io/haiku.rag/a2a/)

examples/docker/docker-compose.yml

@@ -0,0 +1,60 @@
+services:
+  haiku-rag:
+    build:
+      context: ../..
+      dockerfile: docker/Dockerfile
+    container_name: haiku-rag
+    ports:
+      - "8000:8000"  # A2A server
+      - "8001:8001"  # MCP server
+    volumes:
+      - ./data:/data  # Persist database
+      - ./docs:/docs  # Mount documents directory for monitoring
+    environment:
+      # Database directory
+      - DEFAULT_DATA_DIR=/data
+
+      # File monitoring
+      - MONITOR_DIRECTORIES=/docs
+
+      # Set the Ollama base url for Ollama defaults
+      - OLLAMA_BASE_URL=http://host.docker.internal:11434
+
+      # Embeddings provider (choose one)
+      # For OpenAI:
+      # - EMBEDDINGS_PROVIDER=openai
+      # - EMBEDDINGS_MODEL=text-embedding-3-small
+      # - OPENAI_API_KEY=your-key-here
+
+      # For VoyageAI:
+      # - EMBEDDINGS_PROVIDER=voyageai
+      # - EMBEDDINGS_MODEL=voyage-3
+      # - VOYAGE_API_KEY=your-key-here
+
+      # QA provider (uses Pydantic AI)
+      # - QA_PROVIDER=ollama
+
+      # For OpenAI:
+      # - QA_PROVIDER=openai
+      # - QA_MODEL=gpt-4o-mini
+      # - OPENAI_API_KEY=your-key-here
+
+      # Reranking (optional)
+      # - RERANKING_PROVIDER=mxbai
+      # - RERANKING_MODEL=mixedbread-ai/mxbai-rerank-large-v1
+      # - RERANKING_BASE_URL=http://host.docker.internal:11434
+
+      # Research agent (optional, defaults to QA provider/model)
+      # - RESEARCH_PROVIDER=openai
+      # - RESEARCH_MODEL=gpt-4o
+
+      # Environment
+      - ENV=production
+
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s

pyproject.toml

@@ -50,7 +50,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [tool.hatch.build]
-exclude = ["/docs", "/examples", "/tests", "/.github"]
+exclude = ["/docs", "/examples", "/tests", "/docker", "/.github"]
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/haiku"]