MasciocchiReply
commented
1 week ago I'm in a similar situation, if you use "create_tool_calling_agent(...)", I think you should use "ChatBedrockConverse", instead of "ChatBedrock". But at the moment it gives me this error: "This model doesn't support tool use in streaming mode."
from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_aws import ChatBedrock from langchain_core.prompts import ChatPromptTemplate
prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), ("placeholder", "{chat_history}"), ("human", "{input}"), ("placeholder", "{agent_scratchpad}"), ] ) model = ChatBedrock( model_id="meta.llama3-70b-instruct-v1:0" )
@tool def magic_function(input: int) -> int: """Applies a magic function to an input.""" return input + 2
tools = [magic_function]
agent = create_tool_calling_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "what is the value of magic_function(3)?"})
Error Message and Stack Trace (if applicable)
File "/MVP/mvp/lib/python3.12/site-packages/langchain_core/messages/ai.py", line 243, in add response_metadata = merge_dicts( ^^^^^^^^^^^^ File "/MVP/mvp/lib/python3.12/site-packages/langchain_core/utils/_merge.py", line 40, in merge_dicts raise TypeError( TypeError: Additional kwargs key generation_token_count already exists in left dict and value has unsupported type <class 'int'>.
Description
I am trying out the example from the langchain website and it is giving me error as TypeError: Additional kwargs key generation_token_count already exists in left dict and value has unsupported type <class 'int'>.
I cannot solve the error, and don't understand it. can you please resolve it?
System Info
langchain==0.2.6 langchain-aws==0.1.9 langchain-community==0.2.6 langchain-core==0.2.11 langchain-text-splitters==0.2.2 Mac Python 3.12