langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

Error: 'ToolNode' object is not iterable #127

New Issue
Closed
opened 2026-02-20 17:28:00 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:28:00 -05:00
Owner
Copy Link
Copy Source

Originally created by @zsitvat on GitHub (Jun 27, 2024).

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the LangGraph/LangChain documentation with the integrated search.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangGraph/LangChain rather than my code.
  • I am sure this is better as an issue rather than a GitHub discussion, since this is a LangGraph bug and not a design question.

Example Code

tools = [retriever_tool, my_tool]

def agent(state):
    """
    Invokes the agent model to generate a response based on the current state. Given
    the question, it will decide to retrieve using the retriever tool, or simply end.

    Args:
        state (messages): The current state

    Returns:
        dict: The updated state with the agent response appended to messages
    """
    
    prompt = hub.pull("placeholder for the prompt")
    
    print("---CALL AGENT---")
    messages = state["messages"]
    model = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0125",streaming=True)
    model = model.bind_tools(tools=tools)
    agent = prompt | model
    response = agent.invoke({"question": messages[-1].content,"chat_history": str(messages[:-1]),"varos":"","context":""})
 
    return {"messages": [response]}

*****

from langgraph.graph import END, StateGraph
from langgraph.prebuilt import ToolNode

# Define a new graph
workflow = StateGraph(AgentState)

# Define the nodes we will cycle between
workflow.add_node("topic_validator",topic_validator)  # topic validator
workflow.add_node("router", chain)  # agent
workflow.add_node("agent", agent)  # agent

tools = ToolNode(tools=[retriever_tool, my_tool])
workflow.add_node("tools_node", tools) 

workflow.add_node("standalone", standalone)  # Re-writing the question

workflow.add_node("chains", chain)


workflow.set_entry_point("topic_validator")
workflow.add_edge("topic_validator", "router")
workflow.add_edge("router", "standalone")
workflow.add_edge("standalone", "agent")

workflow.add_conditional_edges(
    "agent",
    should_continue
)


workflow.add_edge("tools_node", "chains")
workflow.add_edge("chains", END)

# Compile
graph = workflow.compile(debug=True)

*****

inputs = {
    "messages": [
        ("user", "Question?"),
    ]
}

try:
    graph_result = graph.stream(inputs)
    for output in graph_result:
        print("OUTPUT:")
        for key, value in output.items():
            print(f"Output from node '{key}':")
            print(value)
        print("\n---\n")
except Exception as e:
    print(f"Error: {e}")

Error Message and Stack Trace (if applicable)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[163], line 1
----> 1 await graph.ainvoke(inputs)

File ~/.local/lib/python3.10/site-packages/langgraph/pregel/__init__.py:1606, in Pregel.ainvoke(self, input, config, stream_mode, output_keys, input_keys, interrupt_before, interrupt_after, debug, **kwargs)
   1604 else:
   1605     chunks = []
-> 1606 async for chunk in self.astream(
   1607     input,
   1608     config,
   1609     stream_mode=stream_mode,
   1610     output_keys=output_keys,
   1611     input_keys=input_keys,
   1612     interrupt_before=interrupt_before,
   1613     interrupt_after=interrupt_after,
   1614     debug=debug,
   1615     **kwargs,
   1616 ):
   1617     if stream_mode == "values":
   1618         latest = chunk

File ~/.local/lib/python3.10/site-packages/langgraph/pregel/__init__.py:1431, in Pregel.astream(self, input, config, stream_mode, output_keys, input_keys, interrupt_before, interrupt_after, debug)
   1428         del fut, task
   1430 # panic on failure or timeout
-> 1431 _panic_or_proceed(done, inflight, step)
   1432 # don't keep futures around in memory longer than needed
   1433 del done, inflight, futures

File ~/.local/lib/python3.10/site-packages/langgraph/pregel/__init__.py:1639, in _panic_or_proceed(done, inflight, step)
   1637             inflight.pop().cancel()
   1638         # raise the exception
-> 1639         raise exc
   1641 if inflight:
   1642     # if we got here means we timed out
   1643     while inflight:
   1644         # cancel all pending tasks

File ~/.local/lib/python3.10/site-packages/langgraph/pregel/retry.py:120, in arun_with_retry(task, retry_policy, stream)
    118         pass
    119 else:
--> 120     await task.proc.ainvoke(task.input, task.config)
    121 # if successful, end
    122 break

File ~/.local/lib/python3.10/site-packages/langchain_core/runnables/base.py:2543, in RunnableSequence.ainvoke(self, input, config, **kwargs)
   2539 config = patch_config(
   2540     config, callbacks=run_manager.get_child(f"seq:step:{i+1}")
   2541 )
   2542 if i == 0:
-> 2543     input = await step.ainvoke(input, config, **kwargs)
   2544 else:
   2545     input = await step.ainvoke(input, config)

File ~/.local/lib/python3.10/site-packages/langgraph/utils.py:121, in RunnableCallable.ainvoke(self, input, config, **kwargs)
    117         ret = await asyncio.create_task(
    118             self.afunc(input, **kwargs), context=context
    119         )
    120     else:
--> 121         ret = await self.afunc(input, **kwargs)
    122 if isinstance(ret, Runnable) and self.recurse:
    123     return await ret.ainvoke(input, config)

File ~/.local/lib/python3.10/site-packages/langchain_core/runnables/config.py:557, in run_in_executor(executor_or_config, func, *args, **kwargs)
    553         raise RuntimeError from exc
    555 if executor_or_config is None or isinstance(executor_or_config, dict):
    556     # Use default executor with context copied from current context
--> 557     return await asyncio.get_running_loop().run_in_executor(
    558         None,
    559         cast(Callable[..., T], partial(copy_context().run, wrapper)),
    560     )
    562 return await asyncio.get_running_loop().run_in_executor(executor_or_config, wrapper)

File /usr/lib/python3.10/concurrent/futures/thread.py:58, in _WorkItem.run(self)
     55     return
     57 try:
---> 58     result = self.fn(*self.args, **self.kwargs)
     59 except BaseException as exc:
     60     self.future.set_exception(exc)

File ~/.local/lib/python3.10/site-packages/langchain_core/runnables/config.py:548, in run_in_executor.<locals>.wrapper()
    546 def wrapper() -> T:
    547     try:
--> 548         return func(*args, **kwargs)
    549     except StopIteration as exc:
    550         # StopIteration can't be set on an asyncio.Future
    551         # it raises a TypeError and leaves the Future pending forever
    552         # so we need to convert it to a RuntimeError
    553         raise RuntimeError from exc

Cell In[155], line 20
     18 messages = state["messages"]
     19 model = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0125",streaming=True)
---> 20 model = model.bind_tools(tools=tools)
     21 agent = prompt | model
     22 response = agent.invoke({"question": messages[-1].content,"chat_history": str(messages[:-1]),"varos":"","context":""})

File ~/.local/lib/python3.10/site-packages/langchain_openai/chat_models/base.py:892, in BaseChatOpenAI.bind_tools(self, tools, tool_choice, **kwargs)
    859 def bind_tools(
    860     self,
    861     tools: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]],
   (...)
    866     **kwargs: Any,
    867 ) -> Runnable[LanguageModelInput, BaseMessage]:
    868     """Bind tool-like objects to this chat model.
    869 
    870     Assumes model is compatible with OpenAI tool-calling API.
   (...)
    889             :class:`~langchain.runnable.Runnable` constructor.
    890     """
--> 892     formatted_tools = [convert_to_openai_tool(tool) for tool in tools]
    893     if tool_choice:
    894         if isinstance(tool_choice, str):
    895             # tool_choice is a tool/function name

TypeError: 'ToolNode' object is not iterable

Description

I'm using langgraph with a tool user llm, but i get error Error: 'ToolNode' object is not iterable. I provided the part of the code.

System Info

%pip install -U langgraph langchain openai langchain_openai langchain_community

Originally created by @zsitvat on GitHub (Jun 27, 2024). ### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the [LangGraph](https://langchain-ai.github.io/langgraph/)/LangChain documentation with the integrated search. - [X] I used the GitHub search to find a similar question and didn't find it. - [X] I am sure that this is a bug in LangGraph/LangChain rather than my code. - [X] I am sure this is better as an issue [rather than a GitHub discussion](https://github.com/langchain-ai/langgraph/discussions/new/choose), since this is a LangGraph bug and not a design question. ### Example Code ```python tools = [retriever_tool, my_tool] def agent(state): """ Invokes the agent model to generate a response based on the current state. Given the question, it will decide to retrieve using the retriever tool, or simply end. Args: state (messages): The current state Returns: dict: The updated state with the agent response appended to messages """ prompt = hub.pull("placeholder for the prompt") print("---CALL AGENT---") messages = state["messages"] model = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0125",streaming=True) model = model.bind_tools(tools=tools) agent = prompt | model response = agent.invoke({"question": messages[-1].content,"chat_history": str(messages[:-1]),"varos":"","context":""}) return {"messages": [response]} ***** from langgraph.graph import END, StateGraph from langgraph.prebuilt import ToolNode # Define a new graph workflow = StateGraph(AgentState) # Define the nodes we will cycle between workflow.add_node("topic_validator",topic_validator) # topic validator workflow.add_node("router", chain) # agent workflow.add_node("agent", agent) # agent tools = ToolNode(tools=[retriever_tool, my_tool]) workflow.add_node("tools_node", tools) workflow.add_node("standalone", standalone) # Re-writing the question workflow.add_node("chains", chain) workflow.set_entry_point("topic_validator") workflow.add_edge("topic_validator", "router") workflow.add_edge("router", "standalone") workflow.add_edge("standalone", "agent") workflow.add_conditional_edges( "agent", should_continue ) workflow.add_edge("tools_node", "chains") workflow.add_edge("chains", END) # Compile graph = workflow.compile(debug=True) ***** inputs = { "messages": [ ("user", "Question?"), ] } try: graph_result = graph.stream(inputs) for output in graph_result: print("OUTPUT:") for key, value in output.items(): print(f"Output from node '{key}':") print(value) print("\n---\n") except Exception as e: print(f"Error: {e}") ``` ### Error Message and Stack Trace (if applicable) ```shell --------------------------------------------------------------------------- TypeError Traceback (most recent call last) Cell In[163], line 1 ----> 1 await graph.ainvoke(inputs) File ~/.local/lib/python3.10/site-packages/langgraph/pregel/__init__.py:1606, in Pregel.ainvoke(self, input, config, stream_mode, output_keys, input_keys, interrupt_before, interrupt_after, debug, **kwargs) 1604 else: 1605 chunks = [] -> 1606 async for chunk in self.astream( 1607 input, 1608 config, 1609 stream_mode=stream_mode, 1610 output_keys=output_keys, 1611 input_keys=input_keys, 1612 interrupt_before=interrupt_before, 1613 interrupt_after=interrupt_after, 1614 debug=debug, 1615 **kwargs, 1616 ): 1617 if stream_mode == "values": 1618 latest = chunk File ~/.local/lib/python3.10/site-packages/langgraph/pregel/__init__.py:1431, in Pregel.astream(self, input, config, stream_mode, output_keys, input_keys, interrupt_before, interrupt_after, debug) 1428 del fut, task 1430 # panic on failure or timeout -> 1431 _panic_or_proceed(done, inflight, step) 1432 # don't keep futures around in memory longer than needed 1433 del done, inflight, futures File ~/.local/lib/python3.10/site-packages/langgraph/pregel/__init__.py:1639, in _panic_or_proceed(done, inflight, step) 1637 inflight.pop().cancel() 1638 # raise the exception -> 1639 raise exc 1641 if inflight: 1642 # if we got here means we timed out 1643 while inflight: 1644 # cancel all pending tasks File ~/.local/lib/python3.10/site-packages/langgraph/pregel/retry.py:120, in arun_with_retry(task, retry_policy, stream) 118 pass 119 else: --> 120 await task.proc.ainvoke(task.input, task.config) 121 # if successful, end 122 break File ~/.local/lib/python3.10/site-packages/langchain_core/runnables/base.py:2543, in RunnableSequence.ainvoke(self, input, config, **kwargs) 2539 config = patch_config( 2540 config, callbacks=run_manager.get_child(f"seq:step:{i+1}") 2541 ) 2542 if i == 0: -> 2543 input = await step.ainvoke(input, config, **kwargs) 2544 else: 2545 input = await step.ainvoke(input, config) File ~/.local/lib/python3.10/site-packages/langgraph/utils.py:121, in RunnableCallable.ainvoke(self, input, config, **kwargs) 117 ret = await asyncio.create_task( 118 self.afunc(input, **kwargs), context=context 119 ) 120 else: --> 121 ret = await self.afunc(input, **kwargs) 122 if isinstance(ret, Runnable) and self.recurse: 123 return await ret.ainvoke(input, config) File ~/.local/lib/python3.10/site-packages/langchain_core/runnables/config.py:557, in run_in_executor(executor_or_config, func, *args, **kwargs) 553 raise RuntimeError from exc 555 if executor_or_config is None or isinstance(executor_or_config, dict): 556 # Use default executor with context copied from current context --> 557 return await asyncio.get_running_loop().run_in_executor( 558 None, 559 cast(Callable[..., T], partial(copy_context().run, wrapper)), 560 ) 562 return await asyncio.get_running_loop().run_in_executor(executor_or_config, wrapper) File /usr/lib/python3.10/concurrent/futures/thread.py:58, in _WorkItem.run(self) 55 return 57 try: ---> 58 result = self.fn(*self.args, **self.kwargs) 59 except BaseException as exc: 60 self.future.set_exception(exc) File ~/.local/lib/python3.10/site-packages/langchain_core/runnables/config.py:548, in run_in_executor.<locals>.wrapper() 546 def wrapper() -> T: 547 try: --> 548 return func(*args, **kwargs) 549 except StopIteration as exc: 550 # StopIteration can't be set on an asyncio.Future 551 # it raises a TypeError and leaves the Future pending forever 552 # so we need to convert it to a RuntimeError 553 raise RuntimeError from exc Cell In[155], line 20 18 messages = state["messages"] 19 model = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0125",streaming=True) ---> 20 model = model.bind_tools(tools=tools) 21 agent = prompt | model 22 response = agent.invoke({"question": messages[-1].content,"chat_history": str(messages[:-1]),"varos":"","context":""}) File ~/.local/lib/python3.10/site-packages/langchain_openai/chat_models/base.py:892, in BaseChatOpenAI.bind_tools(self, tools, tool_choice, **kwargs) 859 def bind_tools( 860 self, 861 tools: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]], (...) 866 **kwargs: Any, 867 ) -> Runnable[LanguageModelInput, BaseMessage]: 868 """Bind tool-like objects to this chat model. 869 870 Assumes model is compatible with OpenAI tool-calling API. (...) 889 :class:`~langchain.runnable.Runnable` constructor. 890 """ --> 892 formatted_tools = [convert_to_openai_tool(tool) for tool in tools] 893 if tool_choice: 894 if isinstance(tool_choice, str): 895 # tool_choice is a tool/function name TypeError: 'ToolNode' object is not iterable ``` ### Description I'm using langgraph with a tool user llm, but i get error Error: 'ToolNode' object is not iterable. I provided the part of the code. ### System Info %pip install -U langgraph langchain openai langchain_openai langchain_community
yindo closed this issue 2026-02-20 17:28:01 -05:00
yindo commented 2026-02-20 17:28:02 -05:00
Author
Owner
Copy Link
Copy Source

@hwchase17 commented on GitHub (Jun 27, 2024):

you have two separate definintions of tools:

tools = [retriever_tool, my_tool]
...
tools = ToolNode(tools=[retriever_tool, my_tool])

and its trying to use one in a place where the other should be used

@hwchase17 commented on GitHub (Jun 27, 2024): you have two separate definintions of tools: ``` tools = [retriever_tool, my_tool] ... tools = ToolNode(tools=[retriever_tool, my_tool]) ``` and its trying to use one in a place where the other should be used
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#127
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?