Samuel Colvin
Samuel Colvin
TL;DR I spoke to @dsp on Friday, and the plan is to add support for MCP to PydanticAI via something I'm currently calling "toolsets". One of the things I've realised...
Instructor (and other libraries) support jinja templates for system prompt building, see [here](https://python.useinstructor.com/blog/2024/09/19/instructor-proposal-integrating-jinja-templating/#validation). It would be pretty easily for us to support, then again it doesn't need to be build...
Sqlite otel instrumentation doesn't seem to be working.
We plan to add an examples builder which would take a sequence of things (e.g. pydantic models, dataclasses, dicts etc.) and serialize them. Usage would be something like ```py from...
Currently `retriever`s are tools that are expected to be benign, e.g. have no side effects, so you don't care if the models chooses to call them or not. Technically there's...
To mitigate the risk that an agent gets into an infinite loop.
We should support explicitly setting the format to use, and raising a warning/error if not all parameters are documented set either on the decorator or on Agent `__init__`.
Currently we don't have anything, and the [RAG example](https://github.com/pydantic/pydantic-ai/blob/main/pydantic_ai_examples/rag.py) just uses OpenAI's plain API to generate embeddings. It seems simple enough to add a dedicated API to models to generate...
Is there any command or migration guide for converting an existing project to using uv? `uv init` doesn't work, and I'm a bit unclear on the steps required. (I maintain...