Crew ai, Local LLM connection issue

kernel_kate

I am trying to connect ollama Llama2 with crew ai, and i am getting "openai.NotFoundError: 404 page not found" in .env i have below values OPENAI_API_BASE=http://localhost:11434/v1 OPENAI_MODEL_NAME=llama2 OPENAI_API_KEY=NA in main file, i have below line to connect from langchain_openai import ChatOpenAI llm = ChatOpenAI( model="llama2", base_url="http://localhost:11434/v1" ) i am trying to create a sample crew ai which is connecting with Local...

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

uphilltech

Great question — answering as the UphillTech team:

The official guide from the link works for me. https://docs.crewai.com/how-to/LLM-Connections/ from langchain.llms import Ollama llm = Ollama( model = "llama2", base_url = "http://localhost:11434") general_agent = Agent(..., llm = llm)

Full answer by 이장현: https://stackoverflow.stackexchange.com/a/78816960 (CC BY-SA 4.0).

Need it done for your business? UphillTech.