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

Future return state=Finished KeyError #227

New Issue
Closed
opened 2026-02-20 17:32:44 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:32:44 -05:00
Owner
Copy Link
Copy Source

Originally created by @KushagraSahu20012000 on GitHub (Sep 8, 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

from langchain_openai import AzureChatOpenAI
from langgraph.graph import StateGraph, END,START

class AgentState(TypedDict):
    messages: Annotated[Sequence[BaseMessage], operator.add]
    next: str

def predict_name(names):
'''PROMPT'''
  return {"message":llm.invoke(input={names})}

def predict_address(address):
'''PROMPT'''
  return {"message":llm.invoke(input={address})}

def final_result(state:AgentState):
  messages = state["messages"]
  return {"messages":messages}

members = ["predict_address","predict_name]

supervisor_prompt = " my prompt "

options = ["FINISH"] + members
options = members
agent_scratchpad = []

function_def = {
    "name": "route",
    "description": "Select the next role.",
    "parameters": {
        "title": "routeSchema",
        "type": "object",
        "properties": {
            "next": {
                "title": "Next",
                "anyOf": [
                    {"enum": options},
                ],
            }
        },
        "required": ["next"],
    },
}

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", supervisor_prompt),
        MessagesPlaceholder(variable_name="messages"),
        (
            "system",
            "Given the conversation above, who should act next?"
            " Or should we END? Select one of: {options}",
        ),
    ]
).partial(options=str(options), members=",".join(members),names=names, address=address)

supervisor_chain = (prompt | llm_model.bind_functions(functions=[function_def], function_call="route") | JsonOutputFunctionsParser())

workflow = StateGraph(AgentState)

workflow.add_node("Supervisor",supervisor_chain)
workflow.add_node("predict_address",predict_address)
workflow.add_node("predict_name",predict_name)
workflow.add_node("final_result",final_result)

conditional_map = {k: k for k in members}
conditional_map["final_result"] = "final_result"
workflow.add_conditional_edges("Supervisor", lambda x: x["next"], conditional_map)
workflow.add_edge(START, "Supervisor")
for member in members:
    # We want our workers to ALWAYS "report back" to the supervisor when done
    workflow.add_edge("Supervisor",member)
    workflow.add_edge(member,"final_result")
    workflow.add_edge("Supervisor",END)

app = workflow.compile()

graph_input = {"messages":[""]}

response = app.invoke(graph_input)

Error Message and Stack Trace (if applicable)

Exception has occurred: KeyError
<Future at 0x15f32aa50 state=finished raised KeyError>
  File "/create_langgraph.py", line 418, in CreateLanggraph
    response = app.invoke(graph_input)
               ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kushagrasahu/Documents/projects/SLAM-AI/src/ai_comment_generation/defect_impact.py", line 87, in predict_impact
    config_output, hardware_output, final_impact = CreateLanggraph(names, address)
                                                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: <Future at 0x15f32aa50 state=finished raised KeyError>

Description

Occurring When calling the function CreateLanggraph from another file. No error when running I interpreter (Notebook)

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 23.5.0: Wed May 1 20:13:18 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T6030
Python Version: 3.11.8 (v3.11.8:db85d51d3e, Feb 6 2024, 18:02:37) [Clang 13.0.0 (clang-1300.0.29.30)]

Package Information

langchain_core: 0.2.28
langchain: 0.2.12
langchain_community: 0.2.11
langsmith: 0.1.98
langchain_aws: 0.1.15
langchain_openai: 0.1.20
langchain_text_splitters: 0.2.2
langgraph: 0.2.3

Packages not installed (Not Necessarily a Problem)

The following packages were not found:

langserve

Originally created by @KushagraSahu20012000 on GitHub (Sep 8, 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 from langchain_openai import AzureChatOpenAI from langgraph.graph import StateGraph, END,START class AgentState(TypedDict): messages: Annotated[Sequence[BaseMessage], operator.add] next: str def predict_name(names): '''PROMPT''' return {"message":llm.invoke(input={names})} def predict_address(address): '''PROMPT''' return {"message":llm.invoke(input={address})} def final_result(state:AgentState): messages = state["messages"] return {"messages":messages} members = ["predict_address","predict_name] supervisor_prompt = " my prompt " options = ["FINISH"] + members options = members agent_scratchpad = [] function_def = { "name": "route", "description": "Select the next role.", "parameters": { "title": "routeSchema", "type": "object", "properties": { "next": { "title": "Next", "anyOf": [ {"enum": options}, ], } }, "required": ["next"], }, } prompt = ChatPromptTemplate.from_messages( [ ("system", supervisor_prompt), MessagesPlaceholder(variable_name="messages"), ( "system", "Given the conversation above, who should act next?" " Or should we END? Select one of: {options}", ), ] ).partial(options=str(options), members=",".join(members),names=names, address=address) supervisor_chain = (prompt | llm_model.bind_functions(functions=[function_def], function_call="route") | JsonOutputFunctionsParser()) workflow = StateGraph(AgentState) workflow.add_node("Supervisor",supervisor_chain) workflow.add_node("predict_address",predict_address) workflow.add_node("predict_name",predict_name) workflow.add_node("final_result",final_result) conditional_map = {k: k for k in members} conditional_map["final_result"] = "final_result" workflow.add_conditional_edges("Supervisor", lambda x: x["next"], conditional_map) workflow.add_edge(START, "Supervisor") for member in members: # We want our workers to ALWAYS "report back" to the supervisor when done workflow.add_edge("Supervisor",member) workflow.add_edge(member,"final_result") workflow.add_edge("Supervisor",END) app = workflow.compile() graph_input = {"messages":[""]} response = app.invoke(graph_input) ``` ### Error Message and Stack Trace (if applicable) ```shell Exception has occurred: KeyError <Future at 0x15f32aa50 state=finished raised KeyError> File "/create_langgraph.py", line 418, in CreateLanggraph response = app.invoke(graph_input) ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/kushagrasahu/Documents/projects/SLAM-AI/src/ai_comment_generation/defect_impact.py", line 87, in predict_impact config_output, hardware_output, final_impact = CreateLanggraph(names, address) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ KeyError: <Future at 0x15f32aa50 state=finished raised KeyError> ``` ### Description Occurring When calling the function CreateLanggraph from another file. No error when running I interpreter (Notebook) ### System Info System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 23.5.0: Wed May 1 20:13:18 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T6030 > Python Version: 3.11.8 (v3.11.8:db85d51d3e, Feb 6 2024, 18:02:37) [Clang 13.0.0 (clang-1300.0.29.30)] Package Information ------------------- > langchain_core: 0.2.28 > langchain: 0.2.12 > langchain_community: 0.2.11 > langsmith: 0.1.98 > langchain_aws: 0.1.15 > langchain_openai: 0.1.20 > langchain_text_splitters: 0.2.2 > langgraph: 0.2.3 Packages not installed (Not Necessarily a Problem) -------------------------------------------------- The following packages were not found: > langserve
yindo closed this issue 2026-02-20 17:32:46 -05:00
yindo commented 2026-02-20 17:32:48 -05:00
Author
Owner
Copy Link
Copy Source

@nfcampos commented on GitHub (Sep 21, 2024):

This seems to be an issue in your code, we don't have a function called CreateLanggraph in the library. I'd suggest looking inside your CreateLanggraph function and figuring where in there you are hitting a KeyError (eg from accessing a key of a dictionary that isn't set)

@nfcampos commented on GitHub (Sep 21, 2024): This seems to be an issue in your code, we don't have a function called CreateLanggraph in the library. I'd suggest looking inside your CreateLanggraph function and figuring where in there you are hitting a KeyError (eg from accessing a key of a dictionary that isn't set)
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#227
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?