feat: enhance chat service with documentation indexing and improved Docker configuration

scripts/start_chat.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+Startup script for chat service with documentation indexing.
+Runs indexing if needed, then starts the chat server.
+"""
+
+import asyncio
+import logging
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s"
+)
+logger = logging.getLogger(__name__)
+
+
+async def main() -> None:
+    """Main startup routine"""
+
+    logger.info("=" * 50)
+    logger.info("Datacenter Documentation Chat Service")
+    logger.info("Starting initialization...")
+    logger.info("=" * 50)
+
+    # Check if vector store needs initialization
+    vector_store_path = Path("/app/data/chroma_db")
+    index_marker = vector_store_path / ".indexed"
+
+    if not index_marker.exists():
+        logger.info("")
+        logger.info("=" * 50)
+        logger.info("First Time Setup")
+        logger.info("=" * 50)
+        logger.info("Indexing documentation into vector store...")
+        logger.info("This may take a few minutes...")
+        logger.info("")
+
+        # Run indexing script
+        try:
+            result = subprocess.run(
+                [sys.executable, "/app/scripts/index_docs.py"],
+                check=True,
+                capture_output=True,
+                text=True
+            )
+            logger.info(result.stdout)
+
+            # Create marker file
+            vector_store_path.mkdir(parents=True, exist_ok=True)
+            index_marker.touch()
+            logger.info("")
+            logger.info("✓ Documentation indexed successfully!")
+
+        except subprocess.CalledProcessError as e:
+            logger.error("")
+            logger.error(f"⚠ Warning: Documentation indexing failed: {e}")
+            logger.error(e.stdout)
+            logger.error(e.stderr)
+            logger.error("  The chat service will still start but won't have access to indexed documentation.")
+    else:
+        logger.info(f"✓ Vector store already initialized (marker: {index_marker})")
+        logger.info("  To re-index, delete the volume: docker volume rm datacenter-docs-chat-data-dev")
+
+    logger.info("")
+    logger.info("=" * 50)
+    logger.info("Starting Chat Server")
+    logger.info("=" * 50)
+    logger.info("Listening on port 8001...")
+    logger.info("")
+
+    # Start the chat server by importing and running it
+    # This keeps everything in the same process
+    os.chdir("/app")
+    sys.path.insert(0, "/app/src")
+
+    from datacenter_docs.chat import main as chat_main
+
+    # Run the chat server
+    import uvicorn
+    from datacenter_docs.chat.main import socket_app
+
+    uvicorn.run(socket_app, host="0.0.0.0", port=8001)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())