Local LLM -> ERROR:root:Failed to get supported params: argument of type 'NoneType' is not iterable

CrewAI Community Support
1

Hi there, what if I am using local LLM such as:

llm_deepseek = Ollama(
    model="deepseek-r1:1.5b",
    base_url="http://localhost:11434",
    temperature=0.7,
)

… and got the error when addressing the llm to the agent:

ERROR:root:Failed to get supported params: argument of type 'NoneType' is not iterable

2

Do you have more details?
I also have problems. It worked only once, and later gave me an error.

3

This this:

from crewai import Agent, Crew, Process, Task, LLM

…

agent_1 = Agent(
    role="Trump",
    goal="Analyze America, make it great again.",
    backstory="""
        You are an expert in everything, like a lot
    """,
    tools=[MyCustomDuckDuckGoTool(), ScrapeWebsiteTool()],
    👉🏻 llm=LLM(model="ollama/deepseek-r1:7b", temperature=0.3),
    l
4

Is this working? It never worked for me.

5

Are you using a single file crew (MyAwesomeCrew.py)?
OR
Are you using a multi-file setup (peomcrew.py, main.py, agents.yaml, tasks.yaml, etc.)?

6

I am now integrating the LLM into the agent, and it is like this:

sales_rep_agent = Agent(
    role="Sales Representative",
    goal="Identify high-value leads that match "
         "our ideal customer profile",
    backstory=(
        "As a part of the dynamic sales team at CrewAI, "
        "your mission is to scour "
        "the digital landscape for potential leads. "
        "Armed with cutting-edge tools "
        "and a strategic mindset, you analyze data, "
        "trends, and interactions to "
        "unearth opportunities that others might overlook. "
        "Your work is crucial in paving the way "
        "for meaningful engagements and driving the company's growth."
    ),
    allow_delegation=False,
    verbose=True,
    llm=LLM(model="ollama/deepseek-r1:1.5b", base_url="http://localhost:11434")
)

However, the output is not as accurate as I would like, likely because I am using the smallest available model.