Cleanup before shipping 0.5

[simonw]

• Release notes for 0.5 #99
• Blog entry
• Update https://github.com/simonw/llm-plugins to no longer say that you need main to install plugins
• Ship releases of all of the plugins, depending on llm>=0.5 - and update their READMEs too
• Review and update LLM README and docs index page
• After 0.5 release, run https://github.com/simonw/homebrew-llm/actions/workflows/llm.yaml

[simonw]

I should point this to a better blog entry:

llm/README.md

Line 13 in 898418a

See [llm, ttok and strip-tags—CLI tools for working with ChatGPT and other LLMs](https://simonwillison.net/2023/May/18/cli-tools-for-llms/) for more on this project.

[simonw]

The sequence of doing this is a bit tricky, since I want to link things to other things and need those links in the release before it gets frozen as a version tag.

• Link release notes and documentation to unpublished blog entry
• Update the different plugin repos to depend on the 0.5 release (prepare commits but don't push yet or CI will fail)
• Add CI temp token to all plugin repos for that first publish
• Ship the 0.5 release
• Publish the blog entry
• Ship all the plugins
• Reset CI PyPI token on each plugin repo to one for that plugin

[simonw]

Blog entry URL will be:

https://simonwillison.net/2023/Jul/12/llm/

Title will be:

The LLM CLI tool now supports self-hosted language models via plugins

As a Markdown link:

[The LLM CLI tool now supports self-hosted language models via plugins](https://simonwillison.net/2023/Jul/12/llm/)

[simonw]

New tagline for the project:

A CLI utility and Python library for interacting with Large Language Models, including OpenAI, PaLM and local models installed on your own machine.

[simonw]

For later:

cd llm-palm && git push && cd ../llm-gpt4all && git push && cd ../llm-mpt30b && git push && cd ../llm-markov && git push

[simonw]

Blog entry: https://simonwillison.net/2023/Jul/12/llm/