Refactor document handling and update Milvus collection settings

- Removed multiple failed document entries from `documents.json`.
- Added a new document entry with updated metadata and changed the index name to `regulations_dense_1024_v2`.
- Updated architecture documentation to reflect changes in the Milvus collection name.
- Adjusted requirements by removing the sqlalchemy dependency.
- Modified test cases to align with new document structure and naming conventions.
- Introduced a new test file for Milvus vector index runtime recovery and error handling.
- Updated assertions in various test files to ensure compatibility with the new schema.

backend/app/shared/errors.py

@@ -0,0 +1,30 @@
+"""Define shared backend exception types."""
+
+from __future__ import annotations
+
+
+class VectorStoreSchemaError(RuntimeError):
+    """Signal that the active vector store schema does not match backend expectations."""
+
+    def __init__(
+        self,
+        *,
+        message: str,
+        host: str,
+        db_name: str,
+        collection_name: str,
+        expected_fields: list[str],
+        actual_fields: list[str],
+    ) -> None:
+        """Initialize the vector store schema error details."""
+        self.host = host
+        self.db_name = db_name
+        self.collection_name = collection_name
+        self.expected_fields = expected_fields
+        self.actual_fields = actual_fields
+        # Keep the message self-contained so runtime logs show the full mismatch context.
+        details = (
+            f"{message} | host={host} db={db_name} collection={collection_name} "
+            f"expected_fields={expected_fields} actual_fields={actual_fields}"
+        )
+        super().__init__(details)