Passing metadata to tools

[agarwalakshat]

Hi,

Suppose I want to pass some metadata (eg. API keys) to my tool, I thought of passing it as a RunnableConfig in the example here. However, functions in the example which invoke the tool dont get the config and cant pass onto the tool. What is the recommended way of achieving this ?

Thanks!

[hinthornw]

You could probably pass it via configurable params within the runnable config

[agarwalakshat]

@hinthornw : This code snippet from the example only has the state object when calling the tool. It is unclear to me how to populate runnable config into the state object when calling workflow.invoke()

`def call_tool(state):
messages = state['messages']
# Based on the continue condition
# we know the last message involves a function call
last_message = messages[-1]
# We construct an ToolInvocation from the function_call
action = ToolInvocation(
tool=last_message.additional_kwargs["function_call"]["name"],
tool_input=json.loads(last_message.additional_kwargs["function_call"]["arguments"]),
)
# We call the tool_executor and get back a response
response = tool_executor.invoke(action) # Dont have config here
# We use the response to create a FunctionMessage
function_message = FunctionMessage(content=str(response), name=action.tool)
# We return a list, because this will get added to the existing list
return {"messages": [function_message]}
....
inputs = {"messages": [HumanMessage(content="what is the weather in sf")]}
app.invoke(inputs) # How does a runnable config passed here get passed to call_tool ?

`