diff --git a/docker-compose.yml b/docker-compose.yml
index d29f5e96..51814edf 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -193,6 +193,44 @@ services:
       timeout: 10s
       retries: 3
 
+  # PARSER Service (Document OCR using dots.ocr)
+  parser-service:
+    build:
+      context: ./services/parser-service
+      dockerfile: Dockerfile
+      target: cpu
+    container_name: dagi-parser-service
+    ports:
+      - "9400:9400"
+    environment:
+      - PARSER_MODEL_NAME=${PARSER_MODEL_NAME:-rednote-hilab/dots.ocr}
+      - DOTS_OCR_MODEL_ID=${DOTS_OCR_MODEL_ID:-rednote-hilab/dots.ocr}
+      - PARSER_DEVICE=${PARSER_DEVICE:-cpu}
+      - DEVICE=${DEVICE:-cpu}
+      - RUNTIME_TYPE=${RUNTIME_TYPE:-local}
+      - USE_DUMMY_PARSER=${USE_DUMMY_PARSER:-false}
+      - ALLOW_DUMMY_FALLBACK=${ALLOW_DUMMY_FALLBACK:-true}
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://ollama:11434}
+      - PARSER_MAX_PAGES=${PARSER_MAX_PAGES:-100}
+      - MAX_FILE_SIZE_MB=${MAX_FILE_SIZE_MB:-50}
+      - PDF_DPI=${PDF_DPI:-200}
+      - IMAGE_MAX_SIZE=${IMAGE_MAX_SIZE:-2048}
+    volumes:
+      - parser-model-cache:/root/.cache/huggingface
+      - ./logs:/app/logs
+    networks:
+      - dagi-network
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9400/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+volumes:
+  parser-model-cache:
+    driver: local
+
 networks:
   dagi-network:
     driver: bridge
diff --git a/services/parser-service/.dockerignore b/services/parser-service/.dockerignore
new file mode 100644
index 00000000..447735bb
--- /dev/null
+++ b/services/parser-service/.dockerignore
@@ -0,0 +1,25 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.so
+*.egg
+*.egg-info
+dist
+build
+.env
+.venv
+venv/
+ENV/
+.pytest_cache
+.coverage
+htmlcov/
+*.log
+.DS_Store
+.git
+.gitignore
+README.md
+tests/
+*.md
+
diff --git a/services/parser-service/DEPLOYMENT.md b/services/parser-service/DEPLOYMENT.md
new file mode 100644
index 00000000..11b58c25
--- /dev/null
+++ b/services/parser-service/DEPLOYMENT.md
@@ -0,0 +1,245 @@
+# PARSER Service - Deployment Guide
+
+Інструкції з розгортання PARSER-сервісу з dots.ocr моделлю.
+
+## Варіанти розгортання
+
+### 1. Docker Compose (рекомендовано)
+
+Найпростіший спосіб - використовувати готовий `docker-compose.yml`:
+
+```bash
+cd services/parser-service
+
+# CPU версія (за замовчуванням)
+docker-compose up -d
+
+# Або з GPU (якщо є NVIDIA GPU)
+# Спочатку встановіть nvidia-container-toolkit
+# Потім розкоментуйте GPU секцію в docker-compose.yml
+docker-compose up -d
+```
+
+**Environment variables** (через `.env` або `docker-compose.yml`):
+
+```bash
+# Модель
+PARSER_MODEL_NAME=rednote-hilab/dots.ocr
+DOTS_OCR_MODEL_ID=rednote-hilab/dots.ocr
+PARSER_DEVICE=cpu  # або cuda, mps
+
+# Runtime
+RUNTIME_TYPE=local  # або ollama
+USE_DUMMY_PARSER=false
+ALLOW_DUMMY_FALLBACK=true
+
+# Ollama (якщо RUNTIME_TYPE=ollama)
+OLLAMA_BASE_URL=http://ollama:11434
+```
+
+### 2. Локальне розгортання (Python venv)
+
+#### Крок 1: Створити venv
+
+```bash
+cd services/parser-service
+python3.11 -m venv venv
+source venv/bin/activate  # Linux/Mac
+# або
+venv\Scripts\activate  # Windows
+```
+
+#### Крок 2: Встановити залежності
+
+**CPU версія:**
+```bash
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+pip install -r requirements.txt
+```
+
+**CUDA версія (якщо є NVIDIA GPU):**
+```bash
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+pip install -r requirements.txt
+```
+
+**MPS версія (Apple Silicon):**
+```bash
+pip install torch torchvision torchaudio
+pip install -r requirements.txt
+```
+
+#### Крок 3: Налаштувати environment
+
+Створити `.env` файл:
+
+```bash
+# .env
+PARSER_MODEL_NAME=rednote-hilab/dots.ocr
+DOTS_OCR_MODEL_ID=rednote-hilab/dots.ocr
+PARSER_DEVICE=cpu  # або cuda, mps
+RUNTIME_TYPE=local
+USE_DUMMY_PARSER=false
+ALLOW_DUMMY_FALLBACK=true
+```
+
+#### Крок 4: Запустити сервіс
+
+```bash
+uvicorn app.main:app --host 0.0.0.0 --port 9400 --reload
+```
+
+### 3. Ollama Runtime (альтернатива)
+
+Якщо не хочете встановлювати transformers/torch локально:
+
+#### Крок 1: Встановити Ollama
+
+```bash
+# Linux/Mac
+curl -fsSL https://ollama.ai/install.sh | sh
+
+# Windows
+# Завантажити з https://ollama.ai/download
+```
+
+#### Крок 2: Завантажити dots-ocr модель
+
+```bash
+ollama pull dots-ocr
+# Або якщо модель називається інакше:
+# ollama pull <model-name>
+```
+
+#### Крок 3: Налаштувати parser-service
+
+```bash
+export RUNTIME_TYPE=ollama
+export OLLAMA_BASE_URL=http://localhost:11434
+export PARSER_MODEL_NAME=dots-ocr
+```
+
+#### Крок 4: Запустити сервіс
+
+```bash
+uvicorn app.main:app --host 0.0.0.0 --port 9400
+```
+
+## Модель dots.ocr
+
+### Варіанти отримання моделі
+
+1. **HuggingFace Hub** (автоматично):
+   - Модель завантажиться автоматично при першому використанні
+   - Кешується в `~/.cache/huggingface/`
+
+2. **Локальний шлях**:
+   ```bash
+   export PARSER_MODEL_NAME=/opt/models/dots.ocr
+   ```
+
+3. **Git clone**:
+   ```bash
+   git clone https://huggingface.co/rednote-hilab/dots.ocr /opt/models/dots.ocr
+   export PARSER_MODEL_NAME=/opt/models/dots.ocr
+   ```
+
+### Розмір моделі та вимоги
+
+- **Розмір:** Залежить від конкретної версії dots.ocr (зазвичай 1-7GB)
+- **RAM:** Мінімум 4GB для CPU, 8GB+ для GPU
+- **GPU:** Опційно, значно прискорює обробку
+
+## Перевірка роботи
+
+### Health check
+
+```bash
+curl http://localhost:9400/health
+```
+
+Очікуваний відповідь:
+```json
+{
+  "status": "healthy",
+  "service": "parser-service",
+  "model": "rednote-hilab/dots.ocr",
+  "device": "cpu",
+  "version": "1.0.0"
+}
+```
+
+### Тестовий запит
+
+```bash
+curl -X POST http://localhost:9400/ocr/parse \
+  -F "file=@test.pdf" \
+  -F "output_mode=raw_json"
+```
+
+## Troubleshooting
+
+### Помилка: "CUDA not available"
+
+**Рішення:**
+- Перевірте, чи встановлено CUDA: `nvidia-smi`
+- Встановіть правильну версію PyTorch з CUDA підтримкою
+- Або використовуйте `PARSER_DEVICE=cpu`
+
+### Помилка: "Model not found"
+
+**Рішення:**
+- Перевірте правильність `PARSER_MODEL_NAME`
+- Переконайтеся, що є доступ до HuggingFace Hub
+- Або вкажіть локальний шлях до моделі
+
+### Помилка: "Out of memory"
+
+**Рішення:**
+- Зменште `PARSER_MAX_PAGES`
+- Використовуйте CPU замість GPU
+- Або використовуйте Ollama runtime
+
+### Модель завантажується повільно
+
+**Рішення:**
+- Перший раз модель завантажується з HuggingFace (може бути повільно)
+- Наступні запуски використовують кеш
+- Можна попередньо завантажити: `python -c "from transformers import AutoModelForVision2Seq; AutoModelForVision2Seq.from_pretrained('rednote-hilab/dots.ocr')"`
+
+## Інтеграція з docker-compose.yml (основний проект)
+
+Додати в основний `docker-compose.yml`:
+
+```yaml
+services:
+  parser-service:
+    build:
+      context: ./services/parser-service
+      dockerfile: Dockerfile
+      target: cpu
+    container_name: dagi-parser-service
+    ports:
+      - "9400:9400"
+    environment:
+      - PARSER_MODEL_NAME=${PARSER_MODEL_NAME:-rednote-hilab/dots.ocr}
+      - PARSER_DEVICE=${PARSER_DEVICE:-cpu}
+      - RUNTIME_TYPE=local
+      - USE_DUMMY_PARSER=${USE_DUMMY_PARSER:-false}
+    volumes:
+      - parser-model-cache:/root/.cache/huggingface
+    networks:
+      - dagi-network
+    depends_on:
+      - city-db
+    restart: unless-stopped
+```
+
+## Production рекомендації
+
+1. **GPU:** Використовуйте GPU для кращої продуктивності
+2. **Model caching:** Зберігайте модель в volume для швидшого старту
+3. **Resource limits:** Встановіть memory limits в docker-compose
+4. **Monitoring:** Додайте логування та метрики
+5. **Scaling:** Можна запускати кілька інстансів за load balancer
+
diff --git a/services/parser-service/Dockerfile b/services/parser-service/Dockerfile
index 67a2dda0..2b9fb7c9 100644
--- a/services/parser-service/Dockerfile
+++ b/services/parser-service/Dockerfile
@@ -1,4 +1,6 @@
-FROM python:3.11-slim
+# Multi-stage build for PARSER Service
+# Stage 1: Base with system dependencies
+FROM python:3.11-slim as base
 
 WORKDIR /app
 
@@ -7,17 +9,23 @@ RUN apt-get update && apt-get install -y \
     poppler-utils \
     libgl1-mesa-glx \
     libglib2.0-0 \
+    git \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements and install dependencies
+# Stage 2: CPU-only build
+FROM base as cpu
+
+# Copy requirements and install CPU-only dependencies
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir \
+    torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu && \
+    pip install --no-cache-dir -r requirements.txt
 
 # Copy application code
 COPY . .
 
-# Create temp directory
-RUN mkdir -p /tmp/parser
+# Create temp directory and model cache
+RUN mkdir -p /tmp/parser /root/.cache/huggingface
 
 # Expose port
 EXPOSE 9400
@@ -25,3 +33,32 @@ EXPOSE 9400
 # Run application
 CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "9400"]
 
+# Stage 3: CUDA build (optional, use --target=cuda)
+FROM base as cuda
+
+# Install CUDA dependencies
+RUN apt-get update && apt-get install -y \
+    nvidia-cuda-toolkit \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements and install CUDA dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir \
+    torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 && \
+    pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Create temp directory and model cache
+RUN mkdir -p /tmp/parser /root/.cache/huggingface
+
+# Expose port
+EXPOSE 9400
+
+# Run application
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "9400"]
+
+# Default to CPU build
+FROM cpu
+
diff --git a/services/parser-service/app/core/config.py b/services/parser-service/app/core/config.py
index a6909abc..3865ff99 100644
--- a/services/parser-service/app/core/config.py
+++ b/services/parser-service/app/core/config.py
@@ -15,8 +15,8 @@ class Settings(BaseSettings):
     API_PORT: int = 9400
     
     # PARSER Model
-    PARSER_MODEL_NAME: str = os.getenv("PARSER_MODEL_NAME", "rednote-hilab/dots.ocr")
-    PARSER_DEVICE: Literal["cuda", "cpu", "mps"] = os.getenv("PARSER_DEVICE", "cpu")
+    PARSER_MODEL_NAME: str = os.getenv("PARSER_MODEL_NAME", os.getenv("DOTS_OCR_MODEL_ID", "rednote-hilab/dots.ocr"))
+    PARSER_DEVICE: Literal["cuda", "cpu", "mps"] = os.getenv("PARSER_DEVICE", os.getenv("DEVICE", "cpu"))
     PARSER_MAX_PAGES: int = int(os.getenv("PARSER_MAX_PAGES", "100"))
     PARSER_MAX_RESOLUTION: str = os.getenv("PARSER_MAX_RESOLUTION", "4096x4096")
     PARSER_BATCH_SIZE: int = int(os.getenv("PARSER_BATCH_SIZE", "1"))
diff --git a/services/parser-service/app/runtime/model_loader.py b/services/parser-service/app/runtime/model_loader.py
index ee0dbcc4..d6fa8906 100644
--- a/services/parser-service/app/runtime/model_loader.py
+++ b/services/parser-service/app/runtime/model_loader.py
@@ -37,56 +37,94 @@ def load_model() -> Optional[object]:
     
     try:
         # Load dots.ocr model
-        # Note: Adjust imports and model class based on actual dots.ocr implementation
-        # This is a template that should work with most Vision-Language models
+        # dots.ocr is a Vision-Language Model for document OCR and layout parsing
         
         try:
             from transformers import AutoModelForVision2Seq, AutoProcessor
             import torch
-        except ImportError:
-            logger.error("transformers or torch not installed. Install with: pip install transformers torch")
+        except ImportError as e:
+            logger.error(f"transformers or torch not installed: {e}")
+            logger.error("Install with: pip install transformers torch")
             if not settings.ALLOW_DUMMY_FALLBACK:
                 raise
             return None
         
-        logger.info(f"Loading model from: {settings.PARSER_MODEL_NAME}")
+        model_name = settings.PARSER_MODEL_NAME
+        logger.info(f"Loading dots.ocr model from: {model_name}")
+        logger.info(f"Target device: {settings.PARSER_DEVICE}")
         
-        # Load processor
-        processor = AutoProcessor.from_pretrained(
-            settings.PARSER_MODEL_NAME,
-            trust_remote_code=True  # If model has custom code
-        )
+        # Load processor (handles image preprocessing and text tokenization)
+        try:
+            processor = AutoProcessor.from_pretrained(
+                model_name,
+                trust_remote_code=True  # dots.ocr may have custom code
+            )
+            logger.info("Processor loaded successfully")
+        except Exception as e:
+            logger.error(f"Failed to load processor: {e}")
+            if not settings.ALLOW_DUMMY_FALLBACK:
+                raise
+            return None
         
         # Determine device and dtype
         device = settings.PARSER_DEVICE
-        if device == "cuda" and not torch.cuda.is_available():
-            logger.warning("CUDA not available, falling back to CPU")
-            device = "cpu"
-        elif device == "mps" and not hasattr(torch.backends, "mps") or not torch.backends.mps.is_available():
-            logger.warning("MPS not available, falling back to CPU")
-            device = "cpu"
         
-        dtype = torch.float16 if device != "cpu" else torch.float32
+        # Check CUDA availability
+        if device == "cuda":
+            if not torch.cuda.is_available():
+                logger.warning("CUDA requested but not available, falling back to CPU")
+                device = "cpu"
+            else:
+                logger.info(f"Using CUDA device: {torch.cuda.get_device_name(0)}")
+        
+        # Check MPS availability (Apple Silicon)
+        elif device == "mps":
+            if not hasattr(torch.backends, "mps") or not torch.backends.mps.is_available():
+                logger.warning("MPS requested but not available, falling back to CPU")
+                device = "cpu"
+            else:
+                logger.info("Using MPS (Apple Silicon)")
+        
+        # Determine dtype based on device
+        if device == "cpu":
+            dtype = torch.float32
+        else:
+            dtype = torch.float16  # Use half precision for GPU to save memory
+        
+        logger.info(f"Loading model with dtype: {dtype}")
         
         # Load model
-        model = AutoModelForVision2Seq.from_pretrained(
-            settings.PARSER_MODEL_NAME,
-            device_map=device if device != "cpu" else None,
-            torch_dtype=dtype,
-            trust_remote_code=True
-        )
-        
-        if device == "cpu":
-            model = model.to("cpu")
+        try:
+            model = AutoModelForVision2Seq.from_pretrained(
+                model_name,
+                device_map=device if device != "cpu" else None,
+                torch_dtype=dtype,
+                trust_remote_code=True,
+                low_cpu_mem_usage=True  # Optimize memory usage
+            )
+            
+            # Explicitly move to device if CPU
+            if device == "cpu":
+                model = model.to("cpu")
+                model.eval()  # Set to evaluation mode
+            
+            logger.info(f"Model loaded successfully on device: {device}")
+            
+        except Exception as e:
+            logger.error(f"Failed to load model: {e}", exc_info=True)
+            if not settings.ALLOW_DUMMY_FALLBACK:
+                raise
+            return None
         
         # Store model and processor
         _model = {
             "model": model,
             "processor": processor,
-            "device": device
+            "device": device,
+            "dtype": dtype
         }
         
-        logger.info(f"Model loaded successfully on device: {device}")
+        logger.info(f"dots.ocr model ready on {device}")
         
     except ImportError as e:
         logger.error(f"Required packages not installed: {e}")
diff --git a/services/parser-service/docker-compose.yml b/services/parser-service/docker-compose.yml
new file mode 100644
index 00000000..c90468cc
--- /dev/null
+++ b/services/parser-service/docker-compose.yml
@@ -0,0 +1,93 @@
+version: '3.8'
+
+services:
+  parser-service:
+    build:
+      context: .
+      dockerfile: Dockerfile
+      target: cpu  # Use 'cuda' for GPU support
+    container_name: dagi-parser-service
+    ports:
+      - "9400:9400"
+    environment:
+      # Model configuration
+      - PARSER_MODEL_NAME=${PARSER_MODEL_NAME:-rednote-hilab/dots.ocr}
+      - DOTS_OCR_MODEL_ID=${DOTS_OCR_MODEL_ID:-rednote-hilab/dots.ocr}
+      - PARSER_DEVICE=${PARSER_DEVICE:-cpu}
+      - DEVICE=${DEVICE:-cpu}
+      
+      # Runtime configuration
+      - RUNTIME_TYPE=${RUNTIME_TYPE:-local}
+      - USE_DUMMY_PARSER=${USE_DUMMY_PARSER:-false}
+      - ALLOW_DUMMY_FALLBACK=${ALLOW_DUMMY_FALLBACK:-true}
+      
+      # Ollama (if RUNTIME_TYPE=ollama)
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://ollama:11434}
+      
+      # Processing limits
+      - PARSER_MAX_PAGES=${PARSER_MAX_PAGES:-100}
+      - MAX_FILE_SIZE_MB=${MAX_FILE_SIZE_MB:-50}
+      - PDF_DPI=${PDF_DPI:-200}
+      - IMAGE_MAX_SIZE=${IMAGE_MAX_SIZE:-2048}
+      
+      # Service
+      - API_HOST=0.0.0.0
+      - API_PORT=9400
+      - TEMP_DIR=/tmp/parser
+    volumes:
+      # Model cache (persist between restarts)
+      - parser-model-cache:/root/.cache/huggingface
+      # Temp files
+      - parser-temp:/tmp/parser
+      # Logs
+      - ./logs:/app/logs
+    networks:
+      - dagi-network
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9400/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    # Uncomment for GPU support
+    # deploy:
+    #   resources:
+    #     reservations:
+    #       devices:
+    #         - driver: nvidia
+    #           count: 1
+    #           capabilities: [gpu]
+
+  # Optional: Ollama service (if using Ollama runtime)
+  ollama:
+    image: ollama/ollama:latest
+    container_name: dagi-ollama
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama-data:/root/.ollama
+    networks:
+      - dagi-network
+    restart: unless-stopped
+    # Uncomment for GPU support
+    # deploy:
+    #   resources:
+    #     reservations:
+    #       devices:
+    #         - driver: nvidia
+    #           count: 1
+    #           capabilities: [gpu]
+
+volumes:
+  parser-model-cache:
+    driver: local
+  parser-temp:
+    driver: local
+  ollama-data:
+    driver: local
+
+networks:
+  dagi-network:
+    external: true
+    name: dagi-network
+