Simon Willison has released updates for his `llm` tool, with version 0.33 introducing new features and version 0.32.1 addressing a dependency issue. The latest release allows for combining multiple prompt templates and enhances the handling of API keys for embedding models. It also adds a `reasoning_summary` option for models that emulate the OpenAI Responses API. The previous 0.32.1 release was a quick fix to resolve installation problems caused by changes in the OpenAI Python library's dependency on `httpx`. AI
IMPACT Improves developer workflows for interacting with various LLMs and embedding models.
RANK_REASON Software tool release with new features and bug fixes.
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →