0
0

Written by

Oliver Wilms
Integration Engineer at Cognosante
Follow
Question Oliver Wilms · Apr 27

I want to use ollama and IRIS for my AI use case - How do I connect to ollama?

#InterSystems IRIS #Artificial Intelligence (AI) #Containerization #Docker #Generative AI (GenAI) #Large Language Model (LLM) #Python

I combined @Rodolfo Pscheidt https://github.com/RodolfoPscheidtJr/ollama-ai-iris with some files from @Guillaume Rongier https://openexchange.intersystems.com/package/iris-rag-demo.

My own project is https://github.com/oliverwilms/ollama-ai-iris

I can run load_data.py and it connects to IRIS (same container).

When I try to run query_data.py https://github.com/oliverwilms/ollama-ai-iris/blob/main/query_data.py , it cannot connect to ollama:

ConnectionError: Failed to connect to Ollama. Please check that Ollama is downloaded, running and accessible.

I wonder if I need to add in query_data.py, how it can "find" ollama which is  in docker-compose.yml?

https://github.com/oliverwilms/ollama-ai-iris/blob/main/docker-compose…

Discussion (0)0
Log in or sign up to continue

Comments

Oliver Wilms · Apr 27

I see that @Guillaume Rongier has this in a Business Operation:

def on_init(self):
        self.model = Ollama(base_url="http://ollama:11434",model="orca-mini")

 

0
Oliver Wilms · Apr 27

I was able to connect to ollama with this:

Settings.llm = Ollama(
     base_url="http://ollama:11434", # tell it to connect to the Ollama container
     model="llama3.2",
     request_timeout=360.0
 )

0