Installing the new Go-based Fabric LLM cli

Fabric’s installation instructions from its website make it appear that installing this new version rewritten in the Go language should be easier than it was with the original Python implementation.

Although pipx made things relatively easy before, I ran into trouble when my installed version of Go did not meet the requirements of the newer Fabric package.

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

# Old Python-based implementation
# git clone https://github.com/danielmiessler/fabric.git && # Clone Fabric to your computer
# 	pushd fabric &&
# 	pipx install . &&
# 	exec zsh && fabric --help

# New go version
# Install Fabric directly from the repo

go install github.com/daniel/miessler/fabric@latest

My solution was to try out PKGX which was something that I had been looking for an excuse to try.

Run Large Language Models Locally With *ollama.ai's* Docker Image

ollama is an open-source framework for self-hosting large language models (LLM) similar to ChatGPT or Google’s Bard. The official Docker image makes it painless to host any number of the supported models.

Shell script to get an Ollama model running #

The example “run_ollama_container.sh” script(s) below take the LLM model name as an argument (assigned to $LLMMODEL), but the pull and run docker exec commands can be called additional times to start other models as well within the same running container.