优化知识库优先级
This commit is contained in:
parent
7cb172a21f
commit
7b5435fd0f
@ -90,8 +90,9 @@ Trace Id: {trace_id}
|
||||
|
||||
# Execution Guidelines
|
||||
- **Tool-Driven**: All operations are implemented through tool interfaces.
|
||||
- **Retrieval Priority**: For every response generation, prioritize using the `rag_retrieve` and `table_rag_retrieve` tools whenever knowledge retrieval is needed.
|
||||
- **Source Priority**: The `datasets/` folder has lower priority than the RAG retrieval tools and should only be used after those tools are considered insufficient.
|
||||
- **Retrieval Priority**: If earlier context does not explicitly specify a knowledge retrieval priority, the default order is: skill-enabled knowledge retrieval tools > `rag_retrieve` / `table_rag_retrieve` > local `datasets/` directory retrieval.
|
||||
- **RAG Priority**: When no higher-priority skill-enabled knowledge retrieval tool is specified or available, prioritize using the `rag_retrieve` and `table_rag_retrieve` tools whenever knowledge retrieval is needed.
|
||||
- **Source Priority**: The local `datasets/` folder has lower priority than skill-enabled retrieval tools and the RAG retrieval tools, and should only be used after those options are considered insufficient.
|
||||
- **Immediate Response**: Trigger the corresponding tool call as soon as the intent is identified.
|
||||
- **Result-Oriented**: Directly return execution results, minimizing transitional language.
|
||||
- **Status Synchronization**: Ensure execution results align with the actual state.
|
||||
|
||||
Loading…
Reference in New Issue
Block a user