Replies: 5 comments 12 replies
-
|
The warning you're encountering suggests there's an issue with how runs are linked, especially in the context of managing chat message histories. Here's a focused approach to address this:
Ensure that the configurations and identifiers are consistently used and correctly passed to each run to avoid such warnings. If the issue persists, providing more details about how you're using
|
Beta Was this translation helpful? Give feedback.
-
|
@dosu This warning in langchain/libs/core/langchain_core/tracers/base.py Lines 113 to 116 in af875cf |
Beta Was this translation helpful? Give feedback.
-
|
The warning you're encountering is due to the LangChain framework's tracing functionality, specifically when a child run is initiated with a To resolve this, ensure that:
Here's a focused approach to correct the issue:
This process involves closely managing the timing and order of run starts to maintain the correct parent-child relationships. For implementation specifics, consider reviewing the handling of runs in the
|
Beta Was this translation helpful? Give feedback.
-
|
I have exactly the same error message when running a similar code, which is an example from the documentation: from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai.chat_models import ChatOpenAI
from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.chat_history import BaseChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory
model = ChatOpenAI()
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"You're an assistant who's good at {ability}. Respond in 20 words or fewer",
),
MessagesPlaceholder(variable_name="history"),
("human", "{input}"),
]
)
runnable = prompt | model
store = {}
def get_session_history(session_id: str) -> BaseChatMessageHistory:
if session_id not in store:
store[session_id] = ChatMessageHistory()
return store[session_id]
with_message_history = RunnableWithMessageHistory(
runnable,
get_session_history,
input_messages_key="input",
history_messages_key="history",
)
with_message_history.invoke(
{"ability": "math", "input": "What does cosine mean?"},
config={"configurable": {"session_id": "abc123"}},
)VSC tells me that there is a problem: Argument 1 to "RunnableWithMessageHistory" has incompatible type "RunnableSerializable[dict[Any, Any], BaseMessage]"; expected "Runnable[Sequence[BaseMessage] | dict[str, Any], str | BaseMessage | Sequence[BaseMessage] | dict[str, Any]] | Runnable[PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]], BaseMessage | str]" Maybe that is the reason behind the "Parent run XXXX..." error. @ging-dev No idea how to fix this. Any help is highly appreciated. |
Beta Was this translation helpful? Give feedback.
-
|
you can fix all the problems by following way: import logging
logging.getLogger().setLevel(logging.ERROR) # hide warning log
from langchain_core.runnables import Runnable
runnable: Runable = prompt | model # fix incompatible typeCommit 47ce8d5#diff-7586f46732e8fe5d465e09b6de20cdbb46dec24fb9625ba1d8e567259d60c428L123-R113 moved |
Beta Was this translation helpful? Give feedback.
-
|
To address the warning related to changing the parameter to "chat_model" in the Here's how you can fix it:
By following these steps, you can ensure that the |
Beta Was this translation helpful? Give feedback.
-
@ging-dev |
Beta Was this translation helpful? Give feedback.
-
|
Has anyone figured out what is causing this warning or how to resolve it? Adding the type hint didn't work, and I'm not sure how this could fix it. |
Beta Was this translation helpful? Give feedback.
-
The main reason is because the contributor raised logging from |
Beta Was this translation helpful? Give feedback.
-
|
@ging-dev do you know what is causing the warning? I understand it is because they changed logging from debug to warning, but in the code you linked to it says So there is something wrong with the tracer, but what exactly is causing there to be an issue with it? |
Beta Was this translation helpful? Give feedback.
-
|
@Conj43 jumping on this too. I would prefer not to change this warning level as well. Did you find anything? |
Beta Was this translation helpful? Give feedback.
-
|
Now that I'm using Also, I've confirmed in LangSmith that the warnings are indeed mistaken: the parent runs that it says it can't find are indeed there, and the child runs properly show within the parent runs (so the "Treating as a root run" part of the warning is, thankfully, not accurate when it comes to LangSmith). |
Beta Was this translation helpful? Give feedback.
-
|
Never found anything. The memory with LangGraph seems much better and I do not get these errors. |
Beta Was this translation helpful? Give feedback.
-
|
Hello, I'm also seeing the same error messages. In my case, I'm not using chains but rather using a AzureChatOpenAI client and calling the 'invoke' method myself. Everything worked just fine until I added a second AzureChatOpenAI client (the first one had tool bindings but for some calls I want to run without tools) which is when I started getting these errors. I tried to generate my own session_id and set it in both clients, in the app when running and in the invoke calls but this doesn't seem to help. How do I make this work with two different clients making calls? Here is my client init code: run_config = RunnableConfig(
run_name = run_id,
configurable = {
"session_id": run_id
}
)
model = AzureChatOpenAI(
azure_deployment=os.getenv("AZURE_MODEL"),
api_version="2024-03-01-preview",
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
max_retries=15,
temperature=0).with_config(
{
'callbacks': [ConsoleCallbackHandler()],
'configurable': {
'session_id': run_id
}
})
model_with_tools = AzureChatOpenAI(
azure_deployment=os.getenv("AZURE_MODEL"),
api_version="2024-03-01-preview",
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
max_retries=15,
temperature=0).with_config(
{
'callbacks': [ConsoleCallbackHandler()],
'configurable': {
'session_id': run_id
}
}).bind_tools(log_tools)And an invoke example: response = model_with_tools.invoke(messages, run_config)
response = model.invoke(messages, run_config)The app run: for event in app.stream(
{
"messages": [],
"history": []
},
config={
"configurable": {
"thread_id": 42,
"session_id": run_id
},
"recursion_limit": 1000,
"run_name": run_id
}
):
passThanks! |
Beta Was this translation helpful? Give feedback.
-
|
Hello, I am also seeing the same error. I did not run into this issue for the first few times, and then it started showing up. Now every single run gives me this error. Session history function My prompt: Defining the chain invoking the chain Using Llama3.1 70B-instruct model. Its strange that i wasnt getting this error for the initial few ones, but now i get it, even if i change the session ID every single run. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Checked other resources
Commit to Help
Example Code
Description
Got warning:
Parent run ba1dc312-a394-4d5c-a5eb-75a1bafabc5c not found for run e438a895-7be4-4224-a4da-fb155abb0203. Treating as a root run.when usingRunnableWithMessageHistorywithStreamingStdOutCallbackHandler.System Info
System Information
Package Information
Beta Was this translation helpful? Give feedback.
All reactions