ObjectDiscoveryTool

class hana_ai.tools.hana_ml_tools.graph_tools.ObjectDiscoveryTool(connection_context: ConnectionContext, return_direct: bool = False)

Tool for discovering HANA objects via knowledge graph.

Parameters:

connection_contextConnectionContext

Connection context to the HANA database.

Returns:

str

The discovery result as a string.

name: str

The unique name of the tool that clearly communicates its purpose.

description: str

Used to tell the model how/when/why to use the tool.

You can provide few-shot examples as a part of the description.

connection_context: ConnectionContext

Connection context to the HANA database.

configure(remote_source_name: str = None, rag_schema_name: str = None, rag_table_name: str = None, knowledge_graph_name: str = None, schema_name: str = 'SYS', procedure_name: str | None = 'AI_OBJECT_RETRIEVAL', metadata_schema_name: str | None = None, metadata_object_prefix: str | None = None)

Configure the additional settings for Object Discovery.

Parameters:

remote_source_namestr

The name of the remote source to connect to AI Core.

rag_schema_namestr

The schema name where RAG tables are stored.

rag_table_namestr

The table name where RAG data is stored.

knowledge_graph_namestr

The name of the knowledge graph to use.

schema_namestr, optional

The schema name where the Object Discovery stored procedure is located, by default "SYS".

procedure_namestr | None, optional

The name of the Object Discovery stored procedure, by default "AI_OBJECT_RETRIEVAL".

metadata_schema_namestr | None, optional

Value for the procedure's AI_METADATA_SCHEMA_NAME IN parameter (no-wrapper deployments only). When set together with metadata_object_prefix, the CALL switches to named-parameter syntax. Leave unset for customer wrapper procedures.

metadata_object_prefixstr | None, optional

Value for AI_METADATA_OBJECT_PREFIX.