'str' object has no attribute 'raise_error'

[chaima-bd]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

#Setup
%%capture --no-stderr
%pip install -U langchain langchain_openai langsmith pandas langchain_experimental matplotlib langgraph langchain_core langchain_anthropic

from langchain_anthropic import ChatAnthropic
import getpass
import os

os.environ["ANTHROPIC_API_KEY"] = getpass.getpass()
# Stat 
from typing_extensions import TypedDict
from typing import Literal, Optional
from pydantic import BaseModel, field_validator
from typing import Annotated, Sequence
import operator
from langchain_core.messages import BaseMessage

class PydanticState(BaseModel):
    M_Options: Optional[Literal["Single LLM", " Mix Cost Optimized LLM", "Perfromance Optimized"]] = None
    AI_llm_model: Optional[Literal["Gemenie", "OpenAI", "FireWorks AI", "Anthropic", "Grok AI"]] = None
    messages: Annotated[Sequence[BaseMessage], operator.add] = []

    @field_validator('M_Options', mode='before')
    @classmethod
    def validate_M_Options(cls, value):
        # Ensure the M_Options is either the specified options or None
        if value not in ["Single LLM", " Mix Cost Optimized LLM", "Perfromance Optimized", None]:
            raise ValueError("Each M_Options must be either 'Single LLM', ' Mix Cost Optimized LLM', or 'Perfromance Optimized'")
        return value

    @field_validator('AI_llm_model', mode='before')
    @classmethod
    def validate_AI_llm_model(cls, value):
        # Ensure the AI_llm_model is either the specified options or None
        if value not in ["Gemenie", "OpenAI", "FireWorks AI", "Anthropic", "Grok AI", None]:
            raise ValueError("Each AI_llm_model must be either Gemenie, OpenAI, FireWorks AI, Anthropic, or Grok AI")
        return value
# Tool 
import json
from typing import List
# Import things that are needed generically
from langchain.tools import BaseTool, StructuredTool, tool


@tool
def create_model_configuration(option_models: str, list_models: List[str]) :
    """
    Create a JSON configuration for AI models.

    Args:
        option_models: The selected model option.
        list_models: A list of available model choices.

    Returns:
        A JSON string with the model configuration.
    """
    data = {
        "model_options": option_models,
        "llm_choices": list_models
    }
    return data


# Example usage
#option = "Single LLM"
#models = ["OpenAI", "Anthropic", "Grok AI"]

#result = create_model_configuration(option, models)
#print(result)

tools = [create_model_configuration]
# We can now wrap these tools in a simple tool-calling node.
from langgraph.prebuilt import ToolNode

tool_node = ToolNode(tools)
model = ChatAnthropic(model="claude-3-5-sonnet-20240620", callbacks=None)
llm_with_tools = model.bind_tools(tools)
#llm_with_tools = model.bind_tools([ToolNode(create_model_configuration)])


# Define the function that processes the state based on all human messages
def should_continue(state):
    # Extract attributes from the state
    m_options = state.M_Options
    ai_llm_models = state.AI_llm_model if isinstance(state.AI_llm_model, list) else []  # Ensure it's a list
    messages = state.messages

    # Check all human messages for inputs
    for message in messages:
        if isinstance(message, HumanMessage):
            content = message.content.lower()  # Normalize content for comparison
            
            # Check for M_Options
            if not m_options:
                if "single llm" in content:
                    state.M_Options = "Single LLM"
                elif "mix cost optimized llm" in content:
                    state.M_Options = "Mix Cost Optimized LLM"
                elif "performance optimized" in content:
                    state.M_Options = "Performance Optimized"

            # Check for AI_llm_model
            if "gemenie" in content and "Gemenie" not in ai_llm_models:
                ai_llm_models.append("Gemenie")
            elif "openai" in content and "OpenAI" not in ai_llm_models:
                ai_llm_models.append("OpenAI")
            elif "fireworks ai" in content and "FireWorks AI" not in ai_llm_models:
                ai_llm_models.append("FireWorks AI")
            elif "anthropic" in content and "Anthropic" not in ai_llm_models:
                ai_llm_models.append("Anthropic")
            elif "grok ai" in content and "Grok AI" not in ai_llm_models:
                ai_llm_models.append("Grok AI")

    # Update state with the AI_llm_models list
    state.AI_llm_model = ai_llm_models

    # Determine if both attributes are filled
    if state.M_Options and ai_llm_models:
        # Call the tool function (assuming it’s defined)
        result = create_model_configuration(state.M_Options, ai_llm_models)
        return "continue"  # Proceed to the next step
    else:
        return "reask"  # Prompt for more input


from langgraph.graph import MessagesState
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage

# System message
sys_msg = SystemMessage(content=

                "Ask your to select AI settings options from for LLM model options. Option 1. Single LLM Option 2. Mix Cost Optimized LLM option3. Perfromance Optimized Please select which option you preffer ? IF user selects Options 1 Response . Please let me know which LLm models you preffer. List - Gemenie, OpenAI, FireWorks AI, Anthropic, Grok AI etc. You have access to the following tools: {create_model_configuration} after the user provied you with option models and the llms ."
)
# Node
def call_model(state: PydanticState):
   return {"messages": [llm_with_tools.invoke([sys_msg] + state.messages)]}

from langgraph.graph import END, StateGraph, START

# Define a new graph
workflow = StateGraph(PydanticState)

# Define the two nodes we will cycle between
workflow.add_node("agent", call_model)
workflow.add_node("action", tool_node)

# Set the entrypoint as `agent`
# This means that this node is the first one called
workflow.add_edge(START, "agent")

# We now add a conditional edge
workflow.add_conditional_edges(
    # First, we define the start node. We use `agent`.
    # This means these are the edges taken after the `agent` node is called.
    "agent",
    # Next, we pass in the function that will determine which node is called next.
    should_continue,
    # Finally we pass in a mapping.
    # The keys are strings, and the values are other nodes.
    # END is a special node marking that the graph should finish.
    # What will happen is we will call `should_continue`, and then the output of that
    # will be matched against the keys in this mapping.
    # Based on which one it matches, that node will then be called.
    {
        # If `tools`, then we call the tool node.
        "continue": "action",
        # Otherwise we finish.
       # "reask": "agent",
        "end": END,
    },
)

# We now add a normal edge from `tools` to `agent`.
# This means that after `tools` is called, `agent` node is called next.
workflow.add_edge("action", "agent")

# Finally, we compile it!
# This compiles it into a LangChain Runnable,
# meaning you can use it as you would any other runnable
app = workflow.compile()

from IPython.display import Image, display

display(Image(app.get_graph().draw_mermaid_png()))


from langchain_core.messages import HumanMessage

inputs = {"messages": [HumanMessage(content="i want single llm and use and use Gemenie model  ")]}
for chunk in app.stream(inputs, stream_mode="values"):
    chunk["messages"][-1].pretty_print()

Description

I am trying to create an agent using langChain and LangGraph but I get thies error message when i try to execute this part of code to print all messages
from langchain_core.messages import HumanMessage

inputs = {"messages": [HumanMessage(content="i want single llm and use and use Gemenie model ")]}
for chunk in app.stream(inputs, stream_mode="values"):
chunk["messages"][-1].pretty_print()

System Info

================================ Human Message =================================

i want single llm and use and use Gemenie model
:40: LangChainDeprecationWarning: The method BaseTool.__call__ was deprecated in langchain-core 0.1.47 and will be removed in 1.0. Use :meth:~invoke instead.
result = create_model_configuration(state.M_Options, ai_llm_models)
WARNING:langchain_core.callbacks.manager:Error in str.on_tool_start callback: AttributeError("'str' object has no attribute 'ignore_agent'")

AttributeError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/langchain_core/callbacks/manager.py in handle_event(handlers, event_name, ignore_condition_name, *args, **kwargs)
260 try:
--> 261 if ignore_condition_name is None or not getattr(
262 handler, ignore_condition_name

AttributeError: 'str' object has no attribute 'ignore_agent'

During handling of the above exception, another exception occurred:

AttributeError Traceback (most recent call last)
13 frames
/usr/local/lib/python3.10/dist-packages/langchain_core/callbacks/manager.py in handle_event(handlers, event_name, ignore_condition_name, *args, **kwargs)
289 f" {repr(e)}"
290 )
--> 291 if handler.raise_error:
292 raise e
293 finally:

AttributeError: 'str' object has no attribute 'raise_error'

[dosubot[bot]]

Hey there, @chaima-bd! How can I assist you today?

Hey @chaima-bd! It looks like you're asking about an error related to 'str' object has no attribute 'raise_error'. Unfortunately, I can't help with this specific request.

I'm a bot designed to help solve bugs, answer technical questions, and gather engineering knowledge. If you think I should have answered this request, you can reach out to the Dosu Team.

Feel free to ask me anything else within my scope!

To continue talking to Dosu, mention @dosu.

[iamthephd]

@chaima-bd I was also facing similar problem. Are you using jupyter or running it as a script?
I was facing the problem in jupyter notebook, and when I restarted the kernel, the issue got fixed.