bhancockio/crew-ai-local-llm

crew-ai-local-llm's Issues

clarification requested

In your video: How To Connect Local LLMs to CrewAI [Ollama, Llama2, Mistral], you describe a few steps to be taken prior to running the main.py file from either the "simple" or "advanced" folders in the repository that goes along with this video. To wit:

1. ollama pull
2. ollama create -f ../setup/Llama2Modelfile
3. ollama run simpleLLama

Q#1: are all 3 steps required every time I run one of your above examples?
I'm using Windows 10, in an Anaconda environment. Even without setting the environment that I've set up for crewAI, when I type: ollama list, it shows models I had previously pulled.

Q#2: without running those 3 steps, I get the following error:
openai.NotFoundError: Error code: 404 - {'error': {'message': "model 'crewai-llama2' not found, try pulling it first", 'type': 'api_error', 'param': None, 'code': None}}

I've named my model in Step #2 above: simpleLLama, and used that name in the .env file: OPENAI_MODEL_NAME=simpleLLama.
? What am I doing wrong?
Thank you in advance for your help.
Baruch Bashan
[email protected]