fix(package): review pass on the PyPI package

- docsgpt api binds 127.0.0.1 by default, like gunicorn and uvicorn do;
  --host 0.0.0.0 exposes it. The docs say so.
- The embedded Milvus and LanceDB defaults derive from the data home, so
  they follow DOCSGPT_HOME like the faiss indexes and uploads do. A checkout
  run from its root and the Docker image resolve to the same paths as before.
- The docs and the pyproject comment describe the CPU torch install as two
  steps (torch and torchvision from the PyTorch CPU index first, then the
  docling extra): pip picks the highest version across indexes, so
  --extra-index-url only yields the CPU build while that index keeps pace
  with PyPI.
- AGENTS.md separates DOCSGPT_HOME (moves the data home) from
  DOCSGPT_ENV_FILE (selects the .env file); the docs example uses a password
  placeholder.

docsgpt/cli.py

@@ -14,7 +14,7 @@ from typing import Optional, Sequence
 
 from docsgpt.version import __version__
 
-DEFAULT_HOST = "0.0.0.0"
+DEFAULT_HOST = "127.0.0.1"
 DEFAULT_PORT = 7091
 DEFAULT_QUEUES = "docsgpt,parsing,embeddings"
 
@@ -105,7 +105,7 @@ def build_parser() -> argparse.ArgumentParser:
     commands = parser.add_subparsers(dest="command", metavar="<command>")
 
     api = commands.add_parser("api", help="serve the HTTP API")
-    api.add_argument("--host", default=DEFAULT_HOST)
+    api.add_argument("--host", default=DEFAULT_HOST, help="interface to listen on (default: localhost; 0.0.0.0 for all)")
     api.add_argument("--port", type=int, default=DEFAULT_PORT)
     api.add_argument("--workers", type=int, default=1, help="gunicorn worker processes (default: 1)")
     api.add_argument("--reload", action="store_true", help="development mode: uvicorn with auto-reload")