WatsonxToolkit#

class langchain_ibm.agent_toolkits.utility.toolkit.WatsonxToolkit[source]#

Bases: BaseToolkit

IBM watsonx.ai Toolkit.

???+ info “Setup”

To use, you should have langchain_ibm python package installed, and the environment variable WATSONX_APIKEY set with your API key, or pass it as a named parameter apikey to the constructor.

```bash pip install -U langchain-ibm

# or using uv uv add langchain-ibm ```

`bash export WATSONX_APIKEY="your-api-key" `

??? info “Instantiate”

IBM watsonx.ai for IBM Cloud:

```python from langchain_ibm.agent_toolkits.utility import WatsonxToolkit

watsonx_toolkit = WatsonxToolkit(
url=”https://us-south.ml.cloud.ibm.com”, project_id=”*”, # or space_id apikey=”*”, # not needed if WATSONX_APIKEY is set

IBM watsonx.ai software: ```python from langchain_ibm.agent_toolkits.utility import WatsonxToolkit

watsonx_toolkit = WatsonxToolkit(
url=”<CPD_URL>”, project_id=”*”, # or space_id username=”*”, password=”*”, instance_id=”*”, version=”*”, # optional

??? info “Invoke”

```python tools = watsonx_toolkit.get_tools()

google_search = watsonx_toolkit.get_tool(tool_name=”GoogleSearch”)

tool_config = {
“maxResults”: 3,

} google_search.set_tool_config(tool_config) input = {

“input”: “Search IBM”,

} search_result = google_search.invoke(input) ```

??? info “Run”

```python rag_query = watsonx_toolkit.get_tool(tool_name=”RAGQuery”)

rag_query.set_tool_config(

{
“vectorIndexId”: “<vector-index-id>”, “projectId”: “<project-id>”,

}

)

res = rag_query.run(“How to initialize APIClient?”) ```

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param apikey: SecretStr | None [Optional]#: API key to the watsonx.ai Runtime.

param instance_id: SecretStr | None [Optional]#: Instance_id of the CPD instance.

param password: SecretStr | None [Optional]#: Password to the CPD instance.

param project_id: str | None = None#: ID of the watsonx.ai Studio project.

param space_id: str | None = None#: ID of the watsonx.ai Studio space.

param token: SecretStr | None [Optional]#: Token to the watsonx.ai Runtime.

param url: SecretStr [Optional]#: URL to the watsonx.ai Runtime.

param username: SecretStr | None [Optional]#: Username to the CPD instance.

param verify: str | bool | None = None#: You can pass one of following as verify: * the path to a CA_BUNDLE file * the path of directory with certificates of trusted CAs * True - default path to truststore will be taken * False - no verification will be made

param version: SecretStr | None = None#: Version of the CPD instance.

param watsonx_client: APIClient | None = None#

get_tool( tool_name: str, ) → WatsonxTool[source]#

Get the tool with a given name.

Parameters:: tool_name (str)
Return type:: WatsonxTool

get_tools() → list[WatsonxTool][source]#

Get the tools in the toolkit.

Return type:: list[WatsonxTool]