I am currently working on a project that involves setting up the Ollama server with LLMs like Mistral and Llama2, along with a Next.js server to interact with it. This project is aimed at helping me learn more about Docker, but I've run into a problem.
To begin, I've created a Dockerfile for Nextjs as follows:
FROM node:18-alpine
WORKDIR /usr/src/app
COPY package*.json ./
RUN npm install
COPY . .
RUN npm run build
CMD ["npm", "start"]
In addition to this, I want to run a llama server with cached dependencies. To accomplish this, I tried creating a docker-compose file:
version: '3.8'
services:
ollama:
image: ollama/ollama
ports:
- "11434:11434"
volumes:
- ollama:/root/.ollama
command: ollama pull llama2
ollama-ui:
build:
context: .
dockerfile: Dockerfile
ports:
- "3000:3000"
The aim here is to execute a command called ollama pull llama2, with the intention of pulling llama2 before starting the Next.js server. However, an error occurs:
ollama-1 | Error: unknown command "ollama" for "ollama"The goal of this project is to have a combined container running the ollama server with certain LLMs, alongside my Next.js server, and I want the process of pulling LLMs to be cached. Is my approach correct? If not, what should I do instead?
I'm sure this issue may seem minor, but I would appreciate any guidance on how to resolve it.
Thank you!