HANAMLToolkit

class hana_ai.tools.toolkit.HANAMLToolkit(connection_context, used_tools=None, return_direct=None)

Toolkit for interacting with HANA SQL.

Parameters:

connection_contextConnectionContext: Connection context to the HANA database.
used_toolslist, optional: List of tools to use. If None or 'all', all tools are used. Default to None.

Attributes:

model_extra: Get extra fields set during validation.
model_fields_set: Returns the set of fields that have been explicitly set on this model instance.

Methods

`Config`()	Configuration for this pydantic object.
`add_custom_tool`(tool)	Add a custom tool to the toolkit.
`copy`(*[, include, exclude, update, deep])	Returns a copy of the model.
`delete_tool`(tool_name)	Delete a tool from the toolkit.
`get_tools`()	Get the tools in the toolkit.
`is_port_available`(port)	检查端口是否可用
`launch_mcp_server`([server_name, version, ...])	Launch the MCP server with the specified configuration.
`model_construct`([_fields_set])	Creates a new instance of the Model class with validated data.
`model_copy`(*[, update, deep])	!!! abstract "Usage Documentation"
`model_dump`(*[, mode, include, exclude, ...])	!!! abstract "Usage Documentation"
`model_dump_json`(*[, indent, include, ...])	!!! abstract "Usage Documentation"
`model_json_schema`([by_alias, ref_template, ...])	Generates a JSON schema for a model class.
`model_parametrized_name`(params)	Compute the class name for parametrizations of generic classes.
`model_post_init`(context, /)	Override this method to perform additional initialization after __init__ and model_construct.
`model_rebuild`(*[, force, raise_errors, ...])	Try to rebuild the pydantic-core schema for the model.
`model_validate`(obj, *[, strict, ...])	Validate a pydantic model instance.
`model_validate_json`(json_data, *[, strict, ...])	!!! abstract "Usage Documentation"
`model_validate_strings`(obj, *[, strict, ...])	Validate the given object with string data against the Pydantic model.
`set_bas`([bas])	Set the BAS mode for all tools in the toolkit.
`set_vectordb`(vectordb)	Set the vector database.

construct
dict
json
update_forward_refs

Examples

Assume cc is a connection to a SAP HANA instance:

>>> from hana_ai.tools.toolkit import HANAMLToolkit
>>> from hana_ai.agents.hanaml_agent_with_memory import HANAMLAgentWithMemory

>>> tools = HANAMLToolkit(connection_context=cc, used_tools='all').get_tools()
>>> chatbot = HANAMLAgentWithMemory(llm=llm, toos=tools, session_id='hana_ai_test', n_messages=10)

add_custom_tool(tool: BaseTool)

Add a custom tool to the toolkit.

Parameters:

toolBaseTool: Custom tool to add.

Note

The tool must be a subclass of BaseTool. Please follow the guide to create the custom tools https://python.langchain.com/docs/how_to/custom_tools/.

delete_tool(tool_name: str)

Delete a tool from the toolkit.

Parameters:

tool_namestr: Name of the tool to delete.

set_bas(bas=True): Set the BAS mode for all tools in the toolkit.

set_vectordb(vectordb)

Set the vector database.

Parameters:

vectordbHANAMLinVectorEngine: Vector database.

is_port_available(port: int) → bool: 检查端口是否可用

launch_mcp_server(server_name: str = 'HANATools', version: str = '1.0', host: str = '127.0.0.1', transport: str = 'stdio', sse_port: int = 8001, auth_token: str | None = None, max_retries: int = 5)

Launch the MCP server with the specified configuration. This method initializes the MCP server, registers all tools, and starts the server in a background thread. If the specified port is occupied, it will try the next port up to max_retries times.

Parameters:

server_namestr: Name of the server. Default is "HANATools".
versionstr: Version of the server. Default is "1.0".
hoststr: Host address for the server.
transportstr: Transport protocol to use. Default is "stdio". Can be "sse" for Server-Sent Events.
sse_portint: Port to use for SSE transport. Default is 8001.
auth_tokenstr, optional: Authentication token for the server. If provided, the server will require this token for access.
max_retriesint: Maximum number of retries to find an available port. Default is 5.

class Config: Configuration for this pydantic object.

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

get_tools() → List[BaseTool]: Get the tools in the toolkit.