[Feature Request]: Dynamically set the default vector database

[pengjunfeng11]

Do you need to file a feature request?

• I have searched the existing feature request and this feature request is not already filed.
• I believe this is a legitimate feature request, not just a question or bug.

Feature Request Description

When I follow official example to initializing light_rag, if I only fill in the parameters of graph_storage, even though my graph_storage supports vector db's functionality (such as age), light_rag still uses the default nano_vector as entities_db for low_level_keyword query.This is unfriendly to users because it will directly report an error

Additional Context

No response

[danielaskdd]

Try to use the API Server and follow the README to select storage implementation of： KV、vector、graph and doc_status. You can explore the lightrag-server.py for how to setup storage if you like to integrate LightRAG core in your project.

https://github.com/HKUDS/LightRAG/blob/main/lightrag/api/README.md