datasette-llm 0.1a11

Datasette released version 0.1a11 of datasette-llm, the intermediate plugin that configures LLMs for other Datasette plugins, adding support for OpenAI-compatible endpoints so Datasette can use a model hosted anywhere that speaks the OpenAI web protocol. The release lets users run local models through LM Studio, Ollama or llama.cpp — which just reached v1.0.0 — and launch a Datasette Agent instance via uvx by pointing the plugins.datasette-llm.default_model setting at an api_base such as http://localhost:1234/v1.

Release: datasette-llm 0.1a11 https://github.com/datasette/datasette-llm/releases/tag/0.1a11 datasette-llm is the intermediate plugin for Datasette that supports configuring LLMs for use with other Datasette plugins. This release adds support for OpenAI-compatible endpoints, so you can configure Datasette to use an LLM hosted anywhere that talks the OpenAI pseudo-standard web protocol. This means that if you're running local models with LM Studio https://lmstudio.ai or Ollama https://ollama.com or llama.cpp https://github.com/ggml-org/llama.cpp which just hit v1.0.0 https://huggingface.co/blog/ggml-org/llama-cpp-v1 you can run Datasette via uvx like this: wget https://datasette.io/content.db uvx --with datasette-agent datasette \ --root --secret 1 \ -s plugins.datasette-llm.default model '{ "model": "lmstudio-qwen", "model name": "qwen/qwen3.8-27b", "api base": "http://localhost:1234/v1" }' content.db And you'll get a local server running a Datasette Agent instance powered by your local model Tags: uv https://simonwillison.net/tags/uv , datasette-agent https://simonwillison.net/tags/datasette-agent , llm https://simonwillison.net/tags/llm , datasette https://simonwillison.net/tags/datasette , llms https://simonwillison.net/tags/llms , ai https://simonwillison.net/tags/ai , generative-ai https://simonwillison.net/tags/generative-ai