llm
llm copied to clipboard
simonw
Access large language models from the command-line
no matter what model I use, no matter the prompt, it dies in the middle of responding, same behavior with --no-stream. Example: ``` ⮕ llm prompt --no-stream -m wiz 'write...
Since openai version `1.x`, the azure endpoint annoyingly uses a different class than the regular `OpenAI` class, namely `AzureOpenAI` (see [here for the Microsoft Documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/switching-endpoints)). With the current release, it...
What happens when `--continue` and `--model` are used together? Will the new model specified by `--model` be used, even if the previous conversation had a different model? This is unclear...
Implemented a new `--conversation-json` flag that allows users to supply a JSON-formatted conversation history when using the prompt command. This enhancement enables better interoperability. ## Usage Users can now pass...
I'd like to be able to pass an option to the chat command to make it return the full logged (json) object, or at least something structured that includes `conversation_id`...
Hi! I have followed every step in [Run Llama 2 on your own Mac using LLM and Homebrew](https://simonwillison.net/2023/Aug/1/llama-2-mac/), in particular: ``` pipx install llm # python 3.11 llm install llm-llama-cpp...
os.sep + path + skipping readline for windows. Why I suggest skipping readline: Me & Chat GPT (back when it thought its name was Assistant) made a pacman game in...
