feat: add PageIndex SDK with local/cloud dual-mode support (#207)

pageindex/storage/protocol.py

@@ -0,0 +1,18 @@
+from __future__ import annotations
+from typing import Protocol, runtime_checkable
+
+
+@runtime_checkable
+class StorageEngine(Protocol):
+    def create_collection(self, name: str) -> None: ...
+    def get_or_create_collection(self, name: str) -> None: ...
+    def list_collections(self) -> list[str]: ...
+    def delete_collection(self, name: str) -> None: ...
+    def save_document(self, collection: str, doc_id: str, doc: dict) -> None: ...
+    def find_document_by_hash(self, collection: str, file_hash: str) -> str | None: ...
+    def get_document(self, collection: str, doc_id: str) -> dict: ...
+    def get_document_structure(self, collection: str, doc_id: str) -> list: ...
+    def get_pages(self, collection: str, doc_id: str) -> list | None: ...
+    def list_documents(self, collection: str) -> list[dict]: ...
+    def delete_document(self, collection: str, doc_id: str) -> None: ...
+    def close(self) -> None: ...