feat: complete RAG pipeline integration (ingest + query + Memory)

Parser Service:
- Add /ocr/ingest endpoint (PARSER → RAG in one call)
- Add RAG_BASE_URL and RAG_TIMEOUT to config
- Add OcrIngestResponse schema
- Create file_converter utility for PDF/image → PNG bytes
- Endpoint accepts file, dao_id, doc_id, user_id
- Automatically parses with dots.ocr and sends to RAG Service

Router Integration:
- Add _handle_rag_query() method in RouterApp
- Combines Memory + RAG → LLM pipeline
- Get Memory context (facts, events, summaries)
- Query RAG Service for documents
- Build prompt with Memory + RAG documents
- Call LLM provider with combined context
- Return answer with citations

Clients:
- Create rag_client.py for Router (query RAG Service)
- Create memory_client.py for Router (get Memory context)

E2E Tests:
- Create e2e_rag_pipeline.sh script for full pipeline test
- Test ingest → query → router query flow
- Add E2E_RAG_README.md with usage examples

Docker:
- Add RAG_SERVICE_URL and MEMORY_SERVICE_URL to router environment

services/parser-service/app/utils/file_converter.py

@@ -0,0 +1,59 @@
+"""
+Helper functions for file conversion (PDF/image → PNG bytes)
+"""
+
+import logging
+from typing import Tuple, Optional
+from io import BytesIO
+
+from PIL import Image
+from app.runtime.preprocessing import convert_pdf_to_images, load_image, detect_file_type
+
+logger = logging.getLogger(__name__)
+
+
+async def pdf_or_image_to_png_bytes(
+    filename: Optional[str],
+    file_bytes: bytes
+) -> Tuple[bytes, int]:
+    """
+    Convert PDF or image file to PNG bytes
+    
+    Args:
+        filename: Original filename (for type detection)
+        file_bytes: File content as bytes
+    
+    Returns:
+        Tuple of (PNG bytes, number of pages)
+    
+    Raises:
+        ValueError: If file type is not supported or conversion fails
+    """
+    # Detect file type
+    doc_type = detect_file_type(file_bytes, filename)
+    
+    if doc_type == "pdf":
+        # Convert PDF to images
+        images = convert_pdf_to_images(file_bytes)
+        
+        if not images:
+            raise ValueError("PDF conversion produced no images")
+        
+        # Convert first page to PNG bytes (for single-page processing)
+        # For multi-page, we'll process all pages separately
+        first_image = images[0]
+        buf = BytesIO()
+        first_image.convert("RGB").save(buf, format="PNG")
+        png_bytes = buf.getvalue()
+        
+        return png_bytes, len(images)
+        
+    else:
+        # Load image and convert to PNG
+        image = load_image(file_bytes)
+        buf = BytesIO()
+        image.convert("RGB").save(buf, format="PNG")
+        png_bytes = buf.getvalue()
+        
+        return png_bytes, 1
+