Jack Collins

Hi @forensicmike , could you try with https://github.com/ollama/ollama/releases/tag/v0.4.6 or newer please? This is when tool calls in streaming responses were implemented in ollama (magentic currently uses streaming responses for all...

Hi @weaversam8 thanks for the issue. Here are a few things that might be useful to you. - Prompt-functions expose a `format` method that takes the same arguments as the...

@weaversam8 @rawwerks https://github.com/jackmpcollins/magentic/releases/tag/v0.28.0 adds instrumentation for LogFire 🪵🔥 / OpenTelemetry which allows you to easily see all requests to the LLM provider APIs. Just need to install logfire and add...

@michael-conrad > Text Generation Inference (TGI) now supports the Messages API, which is fully compatible with the OpenAI Chat Completion API. This feature is available starting from version 1.4.0. You...

Here's some code I have added to my `conftest.py` to create a span for each test. However there is no indication of which tests have failed in the logfire UI....

@jo-s-eph Thanks! This would be a good one to start with. Please also keep track of (or fix) any tricky parts of getting set up to contribute. Hopefully it's as...

@jo-s-eph From what I can see, JSON keys must be strings, so this seems fine to me! https://restfulapi.net/valid-json-key-names/ Is there a separate streaming issue, or is this only in the...

Hi @mnicstruwig , currently the `tool_choice` forces a specific tool if only one function / output type is specified. https://github.com/jackmpcollins/magentic/blob/fd0d03edad0b2b9b685c084f933256bfaba3828e/src/magentic/chat_model/openai_chat_model.py#L423-L434 Is your use case to provide multiple tools but still...

Seems to be fixed since https://github.com/BerriAI/litellm/releases/tag/v1.31.6 Thanks!

@jo-s-eph The whole `JsonArrayParserState` should be gone. In the end I expect there to be less code due from switching to `pydantic_core.from_json`. My suggested approach is in comment https://github.com/jackmpcollins/magentic/issues/422#issuecomment-2643968478 Thanks...