Crew.kickoff() got an unexpected keyword argument 'inputs'

[lijinta1984]

Got this error while running the script:

Traceback (most recent call last): File "/home/lijin/crew.py", line 75, in result = crew.kickoff(inputs={'topic': 'AMD Ryzen 7 Mini PCs'}) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: Crew.kickoff() got an unexpected keyword argument 'inputs'

This is the full code:

Traceback (most recent call last): import os from crewai import Task from crewai import Crew, Process from crewai import Agent from crewai_tools import SerperDevTool

os.environ["SERPER_API_KEY"] = "xxxxx" # serper.dev API key os.environ["OPENAI_API_KEY"] = "xxxxxxx"

search_tool = SerperDevTool()

Creating a senior researcher agent with memory and verbose mode

researcher = Agent( role='Senior Researcher', goal='Uncover groundbreaking technologies in {topic}', verbose=True, memory=True, backstory=( "Driven by curiosity, you're at the forefront of" "innovation, eager to explore and share knowledge that could change" "the world." ), tools=[search_tool], allow_delegation=True )

Creating a writer agent with custom tools and delegation capability

writer = Agent( role='Writer', goal='Narrate compelling tech stories about {topic}', verbose=True, memory=True, backstory=( "With a flair for simplifying complex topics, you craft" "engaging narratives that captivate and educate, bringing new" "discoveries to light in an accessible manner." ), tools=[search_tool], allow_delegation=False )

Research task

research_task = Task( description=( "Identify the next big trend in {topic}." "Focus on identifying pros and cons and the overall narrative." "Your final report should clearly articulate the key points" "its market opportunities, and potential risks." ), expected_output='A comprehensive 3 paragraphs long report on the latest innovations.', tools=[search_tool], agent=researcher, )

Writing task with language model configuration

write_task = Task( description=( "Compose an insightful article on {topic}." "Focus on the latest trends and how it's impacting the industry." "This article should be easy to understand, engaging, and positive." ), expected_output='A 4 paragraph article on {topic} advancements formatted as markdown.', tools=[search_tool], agent=writer, async_execution=False, output_file='new-blog-post.md' # Example of output customization )

Forming the tech-focused crew with enhanced configurations

crew = Crew( agents=[researcher, writer], tasks=[research_task, write_task], process=Process.sequential # Optional: Sequential task execution is default )

Starting the task execution process with enhanced feedback

result = crew.kickoff(inputs={'topic': 'AMD Ryzen 7 Mini PCs'}) print(result)

[jayma777]

Had the exact same issue. Upgraded pip to latest (0.28.8 as of right this second) Cured issue.

[kartik1225]

Got same issue!

[theCyberTech]

Try upgrading crewai - pip install crewai --upgrade

[kartik1225]

Hey thanks for the quick reply.

I am already in the latest version

crewai==0.28.8
crewai-tools==0.1.7

from the docs I am testing this main.py

from crewai import Crew, Process, Task

from tasks import Tasks
from agents import Agents

from dotenv import load_dotenv
load_dotenv()

from crewai import Agent
from crewai_tools import SerperDevTool
search_tool = SerperDevTool()

# Creating a senior researcher agent with memory and verbose mode
researcher = Agent(
  role='Senior Researcher',
  goal='Uncover groundbreaking technologies in {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "Driven by curiosity, you're at the forefront of"
    "innovation, eager to explore and share knowledge that could change"
    "the world."
  ),
  tools=[search_tool],
  allow_delegation=True
)

# Creating a writer agent with custom tools and delegation capability
writer = Agent(
  role='Writer',
  goal='Narrate compelling tech stories about {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "With a flair for simplifying complex topics, you craft"
    "engaging narratives that captivate and educate, bringing new"
    "discoveries to light in an accessible manner."
  ),
  tools=[search_tool],
  allow_delegation=False
)

research_task = Task(
  description=(
    "Identify the next big trend in {topic}."
    "Focus on identifying pros and cons and the overall narrative."
    "Your final report should clearly articulate the key points,"
    "its market opportunities, and potential risks."
  ),
  expected_output='A comprehensive 3 paragraphs long report on the latest AI trends.',
  tools=[search_tool],
  agent=researcher,
)

# Writing task with language model configuration
write_task = Task(
  description=(
    "Compose an insightful article on {topic}."
    "Focus on the latest trends and how it's impacting the industry."
    "This article should be easy to understand, engaging, and positive."
  ),
  expected_output='A 4 paragraph article on {topic} advancements formatted as markdown.',
  tools=[search_tool],
  agent=writer,
  async_execution=False,
  output_file='new-blog-post.md'  # Example of output customization
)

crew = Crew(
  agents=[researcher, writer],
  tasks=[research_task, write_task],
  process=Process.sequential,  # Optional: Sequential task execution is default
  memory=True,
  cache=True,
  max_rpm=100,
  share_crew=True
)

result = crew.kickoff(inputs={'topic': 'AI in healthcare'})
print(result)

and I am trying to use lama3 in local here is the env for that

OPENAI_API_BASE=http://localhost:11434/v1
OPENAI_MODEL_NAME=crewai-llama3
OPENAI_API_KEY=NA

I have build the crewai-llama3 locally

and when I try to run I am getting following error

Traceback (most recent call last):
  File "/Users/kartik/Code/experiments/ai/learning_pyenv/main.py", line 79, in <module>
    result = crew.kickoff(inputs={'topic': 'AI in healthcare'})
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/crew.py", line 252, in kickoff
    result = self._run_sequential_process()
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/crew.py", line 293, in _run_sequential_process
    output = task.execute(context=task_output)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/task.py", line 173, in execute
    result = self._execute(
             ^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/task.py", line 182, in _execute
    result = agent.execute_task(
             ^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/agent.py", line 207, in execute_task
    memory = contextual_memory.build_context_for_task(task, context)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/memory/contextual/contextual_memory.py", line 22, in build_context_for_task
    context.append(self._fetch_stm_context(query))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/memory/contextual/contextual_memory.py", line 31, in _fetch_stm_context
    stm_results = self.stm.search(query)
                  ^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/memory/short_term/short_term_memory.py", line 23, in search
    return self.storage.search(query=query, score_threshold=score_threshold)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/memory/storage/rag_storage.py", line 90, in search
    else self.app.search(query, limit)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/embedchain/embedchain.py", line 635, in search
    return [{"context": c[0], "metadata": c[1]} for c in self.db.query(**params)]
                                                         ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/embedchain/vectordb/chroma.py", line 220, in query
    result = self.collection.query(
             ^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/chromadb/api/models/Collection.py", line 327, in query
    valid_query_embeddings = self._embed(input=valid_query_texts)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/chromadb/api/models/Collection.py", line 633, in _embed
    return self._embedding_function(input=input)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/chromadb/api/types.py", line 193, in __call__
    result = call(self, input)
             ^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/chromadb/utils/embedding_functions.py", line 188, in __call__
    embeddings = self._client.create(
                 ^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/openai/resources/embeddings.py", line 114, in create
    return self._post(
           ^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/openai/_base_client.py", line 1232, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/openai/_base_client.py", line 921, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/openai/_base_client.py", line 1012, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: 404 page not found
Exception in thread Thread-1:
Traceback (most recent call last):
  File "/opt/homebrew/opt/python@3.12/lib/python3.12/threading.py", line 1073, in _bootstrap_inner
    self.run()
  File "/opt/homebrew/opt/python@3.12/lib/python3.12/threading.py", line 1431, in run
    self.function(*self.args, **self.kwargs)
  File "/Users/kartik/.local/share/virtualenvs/learning_pyenv-snJKqLZa/lib/python3.12/site-packages/crewai/utilities/rpm_controller.py", line 59, in _reset_request_count
    self._timer.start()
  File "/opt/homebrew/opt/python@3.12/lib/python3.12/threading.py", line 992, in start
    _start_new_thread(self._bootstrap, ())
RuntimeError: can't create new thread at interpreter shutdown

My project use pip env I can share my project for testing if required let me know.

Thanks @theCyberTech

[kartik1225]

Any update on this?

[contractorwolf]

hey @kartik1225 I think i hit the same issue and removed the "imputs=" so that my kickoff works like this:

crew.kickoff({"topic": topic})

[venkatganesh96]

same issue i also get.even after changing to crew.kickoff({"topic": topic}) it gives same error

[ChoonLeng773]

Same issue, checked input to be of type Dict[Str : Any] and it still gave the error.

[jwilliams1454]

Same problem. No answer yet.

[joaomdmoura]

It seems some people got it fixed by using a more up to date version, for the folks that are still experiencing this could you share what version you are using?

[thallys-dnx]

I've tried like this: crew.kickoff(inputs={"topic": topic}) and works for me.

[thallys-dnx]

Or you can try also: crew.kickoff({"topic": topic}), without inputs parameter. Also works!

[ranvier2d2]

I uninstalled Crew, updated to the latest version and applied this suggestion by thallys and it worked:

crew.kickoff(inputs={"topic": topic}) .

It was driving me crazy :D

[AkshataDM]

i am on crewai==-0.1.7. tried a bunch of things. still complains about unexpected keyword argument 'inputs'. this is very frustrating.

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

[ze1313]

Consegui resolver o problema da seguinte maneira:

from crewai import Crew, Process, Task

from tasks import Tasks
from agents import Agents

from dotenv import load_dotenv
load_dotenv()

from crewai import Agent
from crewai_tools import SerperDevTool
search_tool = SerperDevTool()

# Creating a senior researcher agent with memory and verbose mode
researcher = Agent(
  role='Senior Researcher',
  goal='Uncover groundbreaking technologies in {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "Driven by curiosity, you're at the forefront of"
    "innovation, eager to explore and share knowledge that could change"
    "the world."
  ),
  tools=[search_tool],
  allow_delegation=True
)

# Input
topics = "AI in healthcare"

# Creating a writer agent with custom tools and delegation capability
writer = Agent(
  role='Writer',
  goal='Narrate compelling tech stories about {topic}',
  verbose=True,
  memory=True,
  backstory=(
    "With a flair for simplifying complex topics, you craft"
    "engaging narratives that captivate and educate, bringing new"
    "discoveries to light in an accessible manner."
  ),
  tools=[search_tool],
  allow_delegation=False
)

research_task = Task(
  description=(
f"""
    Identify the next big trend in {topic}.
    Focus on identifying pros and cons and the overall narrative.
    Your final report should clearly articulate the key points,
    its market opportunities, and potential risks.
"""
  ),
  expected_output='A comprehensive 3 paragraphs long report on the latest AI trends.',
  tools=[search_tool],
  agent=researcher,
)

# Writing task with language model configuration
write_task = Task(
  description=(
  f """ Compose an insightful article on {topic}.
    Focus on the latest trends and how it's impacting the industry.
    This article should be easy to understand, engaging, and positive.
  """),
  expected_output=f'A 4 paragraph article on {topic} advancements formatted as markdown.',
  tools=[search_tool],
  agent=writer,
  async_execution=False,
  output_file='new-blog-post.md'  # Example of output customization
)

crew = Crew(
  agents=[researcher, writer],
  tasks=[research_task, write_task],
  process=Process.sequential,  # Optional: Sequential task execution is default
  memory=True,
  cache=True,
  max_rpm=100,
  share_crew=True
)

result = crew.kickoff()
print(result)