Refactor: enhance graphrag - part 2 (#14972)

### What problem does this PR solve?
1. expose batch_chunk_token_size for configuration
2. retrieve chunks when build subgraph for the doc, not retreive all
docs chunks at the begining
3. get all chunks for a document, used to be hard coded 10000
4. delete not used method run_graphrag

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring

Follow on: #14617

api/utils/api_utils.py

@@ -439,6 +439,7 @@ def get_parser_config(chunk_method, parser_config):
                     "category",
                 ],
                 "method": "light",
+                "batch_chunk_token_size": 4096,
             },
             "parent_child": {
                 "use_parent_child": False,