Error running graph: Error building Agent : All of session_id, sender, and sender_name must be provided

[Owe1n]

Bug Description

When i try to execute : result = run_flow_from_json( flow="agent.json", input_value="message", session_id="", fallback_to_env_vars=True, tweaks=TWEAKS, )

I have the following error : {"type": "error", "error": "Error running graph: Error building Component Tool Calling Agent: \n\nAll of session_id, sender, and sender_name must be provided."}

I believe it comes from the Tool Calling Agent node.

Reproduction

result = run_flow_from_json( flow="agent.json", input_value="message", session_id="", fallback_to_env_vars=True, tweaks=TWEAKS, )

Expected behavior

Run the flow.

Who can help?

No response

Operating System

Mac OS

Langflow Version

1.1.0

Python Version

3.10

Screenshot

No response

Flow File

No response

[dosubot[bot]]

Hey @Owe1n! I'm here to help you with any bugs, questions, or contributions. Let's tackle this together!

To resolve the error "Error running graph: Error building Component Tool Calling Agent: All of session_id, sender, and sender_name must be provided," you need to ensure that all three parameters (session_id, sender, and sender_name) are provided and not empty when calling the run_flow_from_json function.

The error occurs because the store_message method in the ChatComponent class requires these parameters to be non-empty:

if not session_id or not sender or not sender_name:
    raise ValueError("All of session_id, sender, and sender_name must be provided.")

To fix this, make sure you provide non-empty values for session_id, sender, and sender_name. For example:

result = run_flow_from_json(
    flow="agent.json",
    input_value="message",
    session_id="your_session_id",  # Provide a valid session_id
    fallback_to_env_vars=True,
    tweaks=TWEAKS,
    sender="User",  # Provide a valid sender
    sender_name="Your Name"  # Provide a valid sender_name
)

Ensure that session_id, sender, and sender_name are not None or empty strings ^[1].

To continue talking to Dosu, mention @dosu.

[SavvySupport]

I switched it out for the new "Agent" component in v1.1. I'd use that.

[Owe1n]

@SavvySupport I've seen but for some reason the results were better in my flow with the ToolCalling agent.

[Owe1n]

Edit :

Actually even the Simple Agent example is no longer working when exporting with python code.

from langflow.load import run_flow_from_json
TWEAKS = {
    "Agent-jeqiW": {
        "add_current_date_tool": True,
        "agent_description": "A helpful assistant with access to the following tools:",
        "agent_llm": "OpenAI",
        "api_key": "open-ai",
        "handle_parsing_errors": True,
        "input_value": "",
        "json_mode": False,
        "max_iterations": 15,
        "max_tokens": None,
        "model_kwargs": {},
        "model_name": "gpt-4o-mini",
        "n_messages": 100,
        "openai_api_base": "",
        "order": "Ascending",
        "output_schema": {},
        "seed": 1,
        "sender": "Machine and User",
        "sender_name": "",
        "session_id": "",
        "system_prompt": "You are a helpful assistant that can use tools to answer questions and perform tasks.\nUse markdown to format your answer, properly embedding images and urls.",
        "temperature": 0.1,
        "template": "{sender_name}: {text}",
        "verbose": True,
    },
    "YahooFinanceTool-ekpEz": {"method": "get_news", "num_news": 5, "symbol": "NVDA"},
    "ChatInput-nWAHv": {
        "background_color": "",
        "chat_icon": "",
        "files": "",
        "input_value": "search news about AAPL",
        "sender": "User",
        "sender_name": "User",
        "session_id": "",
        "should_store_message": True,
        "text_color": "",
    },
    "ChatOutput-Q6TIz": {
        "background_color": "",
        "chat_icon": "",
        "data_template": "{text}",
        "input_value": "",
        "sender": "Machine",
        "sender_name": "AI",
        "session_id": "",
        "should_store_message": True,
        "text_color": "",
    },
}

result = run_flow_from_json(
    flow="Simple Agent.json",
    session_id="",  # provide a session id if you want to use session state
    fallback_to_env_vars=True,  # False by default
    tweaks=TWEAKS,
    input_value="search news about AAPL",
)

Is returning the following error code :

Traceback (most recent call last):
  File "/Users/d/projects/iagentflow_cookbook/ts.py", line 54, in <module>
    result = run_flow_from_json(
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/site-packages/langflow/load/load.py", line 171, in run_flow_from_json
    return asyncio.run(coro)
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
    return future.result()
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/site-packages/langflow/load/load.py", line 123, in arun_flow_from_json
    result = await run_graph(
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/site-packages/langflow/processing/process.py", line 108, in run_graph
    return await graph.arun(
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 840, in arun
    run_outputs = await self._run(
  File "/Users/d/miniconda3/envs/iagentflow-cookbook/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 776, in _run
    raise ValueError(msg) from exc
ValueError: Error running graph: Error building Component Agent:

User id is not set for AgentComponent

[edwinjosechittilappilly]

Hi @Owe1n, thank you for your feedback. We will debug this scenario and update you on our progress.

[elufowojud]

Hey there, I think the cause of your error is that the error message suggests that the Tool Calling Agent node in your agent.json flow requires one or more of the following parameters: session_id, sender, or sender_name, and at least one of these is missing or empty.

Here is a potential fix based on your error result = run_flow_from_json( flow="agent.json", input_value="message", session_id="user123", # Replace with a valid session ID fallback_to_env_vars=True, tweaks={ "sender": "[email protected]", "sender_name": "User Name", **TWEAKS, # Include other tweaks }, )

[roots-ai]

Using Langflow 1.1

Still gets this error in JSON parser in a sub-flow.

While the sub-flow independently works without any errors.

Error building Component Fields: 

Error running graph: Error building Component Active Domains JSON: 

All of session_id, sender, and sender_name must be provided.

Traceback (most recent call last):
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 837, in build_results
    return await self._build_with_tracing()
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 819, in _build_with_tracing
    _results, _artifacts = await self._build_results()
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 885, in _build_results
    result = await asyncio.to_thread(method)
  File "/usr/local/Cellar/[email protected]/3.10.15/Frameworks/Python.framework/Versions/3.10/lib/python3.10/asyncio/threads.py", line 25, in to_thread
    return await loop.run_in_executor(None, func_call)
  File "/usr/local/Cellar/[email protected]/3.10.15/Frameworks/Python.framework/Versions/3.10/lib/python3.10/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "<string>", line 74, in clean_json
ValueError: Invalid JSON string: Missing '{' or '}'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/vertex/base.py", line 708, in _build_results
    result = await initialize.loading.get_instance_results(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/interface/initialize/loading.py", line 68, in get_instance_results
    return await build_component(params=custom_params, custom_component=custom_component)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/interface/initialize/loading.py", line 145, in build_component
    build_results, artifacts = await custom_component.build_results()
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 848, in build_results
    self.send_error(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 1135, in send_error
    self.send_message(error_message)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 1009, in send_message
    stored_message = self._store_message(message)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 1034, in _store_message
    messages = store_message(message, flow_id=flow_id)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/memory.py", line 167, in store_message
    raise ValueError(msg)
ValueError: All of session_id, sender, and sender_name must be provided.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 771, in _run
    await self.process(start_component_id=start_component_id, fallback_to_env_vars=fallback_to_env_vars)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 1518, in process
    next_runnable_vertices = await self._execute_tasks(tasks, lock=lock)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 1570, in _execute_tasks
    raise result
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 1419, in build_vertex
    await vertex.build(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/vertex/base.py", line 818, in build
    await step(user_id=user_id, event_manager=event_manager, **kwargs)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/vertex/base.py", line 496, in _build
    await self._build_results(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/vertex/base.py", line 723, in _build_results
    raise ComponentBuildError(msg, tb) from exc
langflow.exceptions.component.ComponentBuildError: Error building Component Active Domains JSON: 

All of session_id, sender, and sender_name must be provided.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/vertex/base.py", line 708, in _build_results
    result = await initialize.loading.get_instance_results(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/interface/initialize/loading.py", line 68, in get_instance_results
    return await build_component(params=custom_params, custom_component=custom_component)
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/interface/initialize/loading.py", line 145, in build_component
    build_results, artifacts = await custom_component.build_results()
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 837, in build_results
    return await self._build_with_tracing()
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 819, in _build_with_tracing
    _results, _artifacts = await self._build_results()
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/component.py", line 883, in _build_results
    result = await method()
  File "<string>", line 101, in generate_results
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/custom/custom_component/custom_component.py", line 490, in run_flow
    return await run_flow(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/helpers/flow.py", line 123, in run_flow
    return await graph.arun(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 840, in arun
    run_outputs = await self._run(
  File "/.local/pipx/venvs/langflow/lib/python3.10/site-packages/langflow/graph/graph/base.py", line 776, in _run
    raise ValueError(msg) from exc
ValueError: Error running graph: Error building Component Active Domains JSON: 

All of session_id, sender, and sender_name must be provided.

Update : SubFlow works on removing the JSON Parser.

[edwinjosechittilappilly]

We are addressing this issue and will keep you updated on our progress. Thank you for all your feedback.

[KevinMichaelSchindler]

I have just removed the check for session_id and now it works fine. Could of course break other things but it unblocked me for now :)

src\backend\base\langflow\memory.py

    if not message.sender or not message.sender_name:
        msg = "All of session_id, sender, and sender_name must be provided."
        raise ValueError(msg)

[ArchDevData]

Error occurred: Error running graph: Error building Component File:

It looks like we're missing some important information: session_id (unique conversation identifier). Please ensure that your message includes all the required fields. facing this error...any solution???

[jmelm93]

Having the same issue. Continue to get the error It looks like we're missing some important information: session_id (unique conversation identifier). Please ensure that your message includes all the required fields. Not sure how to resolve...

[dosubot[bot]]

Hi, @Owe1n. I'm Dosu, and I'm helping the langflow team manage their backlog. I'm marking this issue as stale.

Issue Summary:

• The issue involves an error with the run_flow_from_json function due to missing parameters: session_id, sender, and sender_name.
• The error is linked to the Tool Calling Agent node in Langflow version 1.1.0 on Mac OS.
• Suggested solutions included providing the missing parameters and using a new "Agent" component, but these were not satisfactory.
• A temporary workaround was found by removing the session_id check, though it's not a permanent fix.
• Contributors @edwinjosechittilappilly and @elufowojud are working on a fix.

Next Steps:

• Please confirm if this issue is still relevant to the latest version of the langflow repository. If so, you can keep the discussion open by commenting on the issue.
• Otherwise, the issue will be automatically closed in 7 days.

Thank you for your understanding and contribution!

[RaydelMiranda]

Well?? Nothing on this? This is gaining importance since there are some companies trying to use LangFlow for production level solutions. And being able to run the flow on demand using a pure python script enable some ideas for CI and QA when it comes to agent and multi-agent systems' development.

Please, give some priority to this.

[dosubot[bot]]

Hi, @Owe1n. I'm Dosu, and I'm helping the langflow team manage their backlog. I'm marking this issue as stale.

Issue Summary:

• You reported an error with the run_flow_from_json function in Langflow version 1.1.0 on Mac OS due to missing parameters: session_id, sender, and sender_name.
• Suggestions were made to provide these parameters and use a new "Agent" component, but the issue persists.
• The Simple Agent example fails when exporting with Python code.
• A temporary workaround involves removing the session_id check, but it's not a permanent solution.
• Contributors are actively working on a fix, highlighting the importance of resolving this for production-level solutions.

Next Steps:

• Please let us know if this issue is still relevant to the latest version of the langflow repository by commenting here.
• If no updates are provided, the issue will be automatically closed in 7 days.

Thank you for your understanding and contribution!