Crewai create crew demo with 6.Ollama and llama3.2:latest model not startable

[Evert_Smit]

HI all

after using “crewai create crew demo” it creates the scaffold with all the data

Adjust the model to llama3.2 in the .env
crewai install
crewai run

Results in Running the Crew

LLM value is None

Error instantiating LLM from environment/fallback: TypeError: LLM.init() got an unexpected keyword argument ‘api_base’

ollama is running llama3.2:latest
Name: crewai Version: 0.98.0

Any thoughts on this?

[Evert_Smit]

I tried the same code with the OpenAI configuration. this works as intended with the relevant OpenAI API key in the .env

using the llama configuration
MODEL=ollama/llama3.2
API_BASE=http://localhost:11434

it causes to break. Running a test script to check if the llmlite package works, it does return some warnings but seems to work
UserWarning: Valid config keys have changed in V2: * ‘fields’ has been removed

Any suggestions are welcome.

[TarekM]

Error at running crewai using Ollama LLM

The error occurs because the LLM class in the crewai package expects a BASE_URL key for Ollama’s base URL, but the ENV_VARS in constants.py currently provides API_BASE instead. This mismatch is likely due to a recent update in the LLM class, which changed the expected key from API_BASE to BASE_URL. Cause: In the file crewai/cli/constants.py, line 49, the ollama configuration specifies an API_BASE key for the base URL. However, the LLM class being initialized in agent.py (line 195) expects BASE_…

[Evert_Smit]

the workaround can be found here

Error at running crewai using Ollama LLM

I am stuck at the same point.

[DaveN]

I’m struck with similar situation. Using llama3.2:1B, no error but don’t get any output