langchain_community OllamaEndpointNotFoundError when trying to access...

cafe_carl

I have my ollama service running in a container. If I query it from the terminal like: curl -X POST http://localhost:11434/v1/completions \ -H "Content-Type: application/json" \ -d '{ "model": "phi3:mini", "prompt": "Test query" }' it works and I get a response. I also verified the model exists in my Ollama service. But when I try to send a request from my python app with from langchain_community.llms.ollama import Ollama model =...

Originally asked by KZiovas on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

Ok I tracked down the issue after I noticed a warning that was lost in all the logs of my app during start-up. I noticed this warning: LangChainDeprecationWarning: The class Ollama was deprecated in LangChain 0.3.1 and will be removed in 1.0.0. An updated version of the class exists in the :class:~langchain-ollama package and should be used instead. To use it run pip install -U :class:~langchain-ollama and import as from :class:~langchain_ollama import OllamaLLM`. What I assume happened is that in the past i had older version of ollama container and also I was using older models like llama2 . But probably the latest ollama server and the phi LLM model were not compatible with is as the...

Full answer by KZiovas: https://stackoverflow.stackexchange.com/a/79393566 (CC BY-SA 4.0).

Need it done for your business? UphillTech.