Update docker example & relevant docs

docs/installation.md

@@ -75,14 +75,23 @@ See [Remote processing](remote-processing.md) for setup instructions and [Docume
 
 ## Docker
 
+Two Docker images are available:
+
+### Full Image (Self-contained)
+
+Includes all features and document processing built-in:
+
 ```bash
 docker pull ghcr.io/ggozad/haiku.rag:latest
+docker run -p 8001:8001 -v $(pwd)/data:/data ghcr.io/ggozad/haiku.rag:latest
 ```
 
-Run the container with all services:
+### Slim Image (Minimal)
+
+Minimal dependencies - use with external docling-serve for document processing:
 
 ```bash
-docker run -p 8000:8000 -p 8001:8001 -v $(pwd)/data:/data ghcr.io/ggozad/haiku.rag:latest
+docker pull ghcr.io/ggozad/haiku.rag-slim:latest
 ```
 
-This starts the MCP server on port 8001, with data persisted to `./data`.
+See `examples/docker/docker-compose.yml` for a complete setup with docling-serve.

docs/remote-processing.md

@@ -30,7 +30,11 @@ docling-serve is a REST API service that provides:
 
 ## Setup
 
-### Running docling-serve
+### Docker Compose (Recommended)
+
+The easiest way to use haiku.rag with docling-serve is using the slim Docker image with docker-compose. See `examples/docker/docker-compose.yml` for a complete setup that includes both services.
+
+### Running docling-serve Manually
 
 See the [official docling-serve repository](https://github.com/docling-project/docling-serve) for installation options. The quickest way is using Docker:
 

examples/docker/README.md

@@ -1,6 +1,15 @@
 # haiku.rag Docker Compose Example
 
-Run haiku.rag with file monitoring and MCP server.
+Run haiku.rag with docling-serve for remote document processing, file monitoring, and MCP server.
+
+## Architecture
+
+This example demonstrates remote processing with two services:
+
+- **docling-serve** - Document conversion and chunking service
+- **haiku-rag** - MCP server and file monitoring (using slim image)
+
+This setup showcases the minimal haiku.rag-slim image combined with external document processing, ideal for production deployments.
 
 ## Quick Start
 
@@ -27,13 +36,24 @@ docker compose exec haiku-rag haiku-rag ask "What is haiku.rag?"
 
 ## Ports
 
+- `5001` - docling-serve API (with UI enabled)
 - `8001` - MCP server
 
 ## Configuration
 
-Edit `haiku.rag.yaml` to configure providers, embeddings, and other settings. See the [Configuration documentation](https://ggozad.github.io/haiku.rag/configuration/) for all options.
+The setup uses `haiku.rag-slim` image configured to use docling-serve for document processing:
 
-Default setup uses Ollama on the host (`host.docker.internal:11434`).
+```yaml
+processing:
+  converter: docling-serve
+  chunker: docling-serve
+
+providers:
+  docling_serve:
+    base_url: http://docling-serve:5001
+```
+
+Edit `haiku.rag.yaml` to configure providers, embeddings, and other settings. See the [Configuration documentation](https://ggozad.github.io/haiku.rag/configuration/) for all options.
 
 For API keys (OpenAI, Anthropic, etc.), set them as environment variables:
 
@@ -45,6 +65,7 @@ docker compose up -d
 
 ## Documentation
 
+- [Remote Processing](https://ggozad.github.io/haiku.rag/remote-processing/)
 - [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/)

examples/docker/docker-compose.yml

@@ -1,8 +1,24 @@
 services:
+  docling-serve:
+    image: quay.io/docling-project/docling-serve:latest
+    container_name: docling-serve
+    ports:
+      - "5001:5001"
+    environment:
+      - DOCLING_SERVE_ENABLE_UI=1
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:5001/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+      start_interval: 5s
+
   haiku-rag:
     build:
       context: ../..
-      dockerfile: docker/Dockerfile
+      dockerfile: docker/Dockerfile.slim
     container_name: haiku-rag
     ports:
       - "8001:8001"  # MCP server
@@ -16,5 +32,7 @@ services:
       - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
       - VOYAGE_API_KEY=${VOYAGE_API_KEY}
       - CO_API_KEY=${CO_API_KEY}
-
+    depends_on:
+      docling-serve:
+        condition: service_healthy
     restart: unless-stopped

examples/docker/haiku.rag.yaml.example

@@ -5,21 +5,29 @@ environment: production
 
 storage:
   data_dir: /data
-  monitor_directories:
+
+monitor:
+  directories:
     - /docs
 
-embeddings:
-  provider: ollama
-  model: nomic-embed-text
-  vector_dim: 768
-
-qa:
-  provider: ollama
-  model: qwen3
+# Remote document processing with docling-serve
+processing:
+  converter: docling-serve
+  chunker: docling-serve
+  chunk_size: 256
+  chunker_type: hybrid
+  chunking_tokenizer: "Qwen/Qwen3-Embedding-0.6B"
+  chunking_merge_peers: true
+  chunking_use_markdown_tables: false
 
 providers:
+  docling_serve:
+    base_url: http://docling-serve:5001
+    api_key: ""
+    timeout: 300
   ollama:
     base_url: http://host.docker.internal:11434
 
+
 # For other providers (OpenAI, Anthropic, VoyageAI, etc.),
 # see: https://ggozad.github.io/haiku.rag/configuration/