llm
llm copied to clipboard
simonw
Access large language models from the command-line
I totally missed the "chat mode" docs because it's currently inside a section about using local models. But it's not specific to local models, so I think it should be...
## Steps to reproduce: 1. Create a clean virtual environment 2. `pip install llm llm-ollama` 3. `llm models` 4. See the following output (at time of writing, at least): ```python...
I ran `brew intstall llm` on a fresh machine. Then ran `llm instal gpt4all` per the instructions in the "Other Models" section of the docs. When running `llm models` I...
Hello, To aleviate Pythin's dependency hell, is someone considering packaging LLM for NixOS ? (newbie to this Nixpkgs thing, by super easy for the user side) Kind regards.
Thank you for a great software! Is there any plans / roadmap to add OpenAI compatible API? [Smth like that](https://llama-cpp-python.readthedocs.io/en/latest/server/), probably?
Question came up here: https://discord.com/channels/823971286308356157/1128504153841336370/1148406576739254363 Currently there isn't a documented way of having prompts run through the Python code get logged to SQLite. The undocumented way is to do this:...
I discovered that I couldn't set up options for templates. Until now I just made aliases to combine templates with options, but I'd rather have it stored with the template....
A command that launches a web server to allow you to both browse your logs and interact with APIs through your browser.
This PR adds Rich as a dependency and includes the option to print with Markdown formatting with the `--rich` flag.  Resolves: #12 Let me know if you're still interested...
Several embedding models supported by LLM plugins have a concept of "modes" - usually called something like "task types" or "input types". Some examples: - Gemini: https://github.com/google-gemini/cookbook/blob/9eb52260f979aa8339e6d1eb77323faa178bbd78/quickstarts/rest/Embeddings_REST.ipynb - "Use task_type...