Add JSON support for neo4j via llamaindex rag integration

[AgentGenie]

Why are these changes needed?

This PR add JSON file support to Neo4j via Llamaindex integration.
This is a prerequisite for RAG on PDF file support. As we plan to use JSON to store the structured meta data for the parsed PDF files.

Related issue number

Related to #68

Checks

pytest -v test/agentchat/contrib/graph_rag/test_neo4j_graph_rag.py::test_neo4j_json_auto
============================================================================================ test session starts =============================================================================================
platform linux -- Python 3.11.10, pytest-7.4.4, pluggy-1.5.0 -- /usr/local/bin/python3.11
cachedir: .pytest_cache
rootdir: /workspaces/ag2
configfile: pyproject.toml
plugins: xdist-3.6.1, cov-6.0.0, anyio-4.6.2.post1, asyncio-0.23.8
asyncio: mode=Mode.STRICT
collected 1 item                                                                                                                                                                                             

test/agentchat/contrib/graph_rag/test_neo4j_graph_rag.py::test_neo4j_json_auto PASSED  

• I've included any doc changes needed for https://docs.ag2.ai/. See https://docs.ag2.ai/docs/contributor-guide/documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[Eric-Shang]

LGTM