Do you need to file a feature request?
Feature Request Description
DeepTutor currently integrates LightRAG capabilities directly within its core backend execution stack. While this tightly coupled approach is convenient for standalone deployments, it introduces resource overhead and creates data silos for environments that already run a dedicated, standalone LightRAG container shared across multiple independent local agent architectures.
Related Module
Knowledge Base Management
Use Case
Exposing an option to bypass the internal LightRAG implementation and offload all graph/vector operations to an external LightRAG API instance would drastically improve modularity and resource efficiency.
Additional Context
No response
Do you need to file a feature request?
Feature Request Description
DeepTutor currently integrates LightRAG capabilities directly within its core backend execution stack. While this tightly coupled approach is convenient for standalone deployments, it introduces resource overhead and creates data silos for environments that already run a dedicated, standalone LightRAG container shared across multiple independent local agent architectures.
Related Module
Knowledge Base Management
Use Case
Exposing an option to bypass the internal LightRAG implementation and offload all graph/vector operations to an external LightRAG API instance would drastically improve modularity and resource efficiency.
Additional Context
No response