llm
llm copied to clipboard
simonw
Access large language models from the command-line
Hi there, and thank you for making LLM, it's a _really_ handy package. I have a query that I could not see a solution to in the docs, and when...
I found on a new machine that `llm` was giving me rubbish results. It turned out the reason for this was because the default model is `gpt-4o-mini`. This is a...
It would be great if there was an option to unload (or not load in the first place) the default openAI plugin. For example, `LLM_LOAD_PLUGINS=''` could not load the default...
Need this to support implementing a Chat Completions API.
In an "llm chat" prompt (single-line input), whenever I reach the last column of the line, the cursor overwrites a single character and starts confusing where the line begins. In...
https://llm.datasette.io/en/stable/index.html https://deepwiki.com/search/does-it-support-ollama-cloud_658b4538-a837-4cae-9b14-c6ab8c316547 # DeepWiki Q&A with Code Context for Repository: simonw/llm ## Q1 Does it support ollama cloud ### Answer Based on the codebase context, you're asking about whether LLM...
Use case: Run `--help` for each command This isn't limited to `--help`, it takes 5 seconds to report `--version` This can take forever because of the extremely high startup cost....
Signed-off-by: thiswillbeyourgithub pip allows using --user which does the following: ``` --user Install to the Python user install directory for your platform. Typically ~/.local/, or %APPDATA%\Python on Windows. (See the...
I installed a plugin that turned out to crash on my machine: ``` > llm install llm-gpt4all ... > llm --help Traceback (most recent call last): File "/Users/jcushman/.local/bin/llm", line 4,...
It takes quite long (30s or so?) for operation to time out when LLM configured in extra-openai-models.yaml is not responding. 2 Options would be nice: - default LLM_HTTPX_TIMEOUT like global...
