Simon Willison

Part of the problem here is that the PNG images returned by that API are pretty huge - 1MB or more: 

Some options to consider: 1. Store them in BLOB columns in the database. Pros: Everything is in one place. Cons: takes up a ton of space, inconvenient to access. Could...

I solved this already with attachments used for input, which stay on disk or in a URL if that's how the user specified them, but can also be stored in...

Storing them on disk would make it easier to handle them with the CLI/terminal interface, it could provide paths to the files for the user to then view with whatever...

Displaying them with the iTerm2 inline image protocol would be pretty neat though: https://iterm2.com/documentation-images.html  Got o4-mini to port that imgcat Bash script to Python, which seems to work: https://chatgpt.com/share/681c3a25-5544-8006-9103-c9a6b838360a

Would be good to support a `llm-openai-azure` plugin. That plugin could work today by setting the global `openai.api_type = 'azure'` variable, but I worry that would break other plugins that...

Worth reviewing to see what other options might be useful. `api_version` looks like one.

Got it working! ```bash git diff | llm -m azure-gpt4 -s 'explain this change' ``` > This change in the Python file 'openai_models.py' expands the 'Chat' Model object and its...

OK, what do I have to do to get a test account so I can try out Azure myself?

I want templates to be able to include raw Python code - the `python_tools: string of code` YAML string described in: - #1008 I am nervous about the intersection of...