fix(llm): configurable per-call litellm params instead of mutating the global

llm_completion / llm_acompletion (pageindex/utils.py and
pageindex/index/utils.py) set `litellm.drop_params = True` on the litellm
module. litellm is a process-wide singleton, so this leaked into every other
library sharing it (e.g. a host app like OpenKB that exposes its own litellm
config) and could not be turned off.

Replace the hardcoded `temperature=0` + global `drop_params` with a single
PageIndex-owned per-call kwargs mechanism (config._LLM_PARAMS):

- defaults preserve behavior: {"temperature": 0, "drop_params": True};
- passed per call via **get_llm_params(), never writing litellm's globals, so
  nothing leaks into other litellm users in the same process;
- externally configurable: pageindex.set_llm_params(drop_params=False,
  temperature=1, num_retries=5, ...) or the PAGEINDEX_DROP_PARAMS env shortcut;
- model/messages are reserved (PageIndex supplies them) and rejected.

pageindex/__init__.py

@@ -6,7 +6,7 @@ from .retrieve import get_document, get_document_structure, get_page_content
 
 # SDK exports
 from .client import PageIndexClient, LocalClient, CloudClient
-from .config import IndexConfig
+from .config import IndexConfig, set_llm_params
 from .collection import Collection
 from .parser.protocol import ContentNode, ParsedDocument, DocumentParser
 from .storage.protocol import StorageEngine
@@ -26,6 +26,7 @@ __all__ = [
     "LocalClient",
     "CloudClient",
     "IndexConfig",
+    "set_llm_params",
     "Collection",
     "ContentNode",
     "ParsedDocument",