Jack Collins
Jack Collins
### Changes - Fix typo: `async_queue_length` -> `async_queued` so that the list of api_names is populated (currently empty) - Use `=~` with `api_name` where missing to enable displaying multiple AsyncAPIs...
### What happened? The [function calling example in the docs for `anthropic/claude-3-opus`](https://litellm.vercel.app/docs/providers/anthropic#usage---function-calling) does not work when `stream=True` is passed as an argument. It returns a streamed response with the `content`...
### What happened? I modified the Anthropic Claude function calling example from the README to use `acomplete` and `stream=True` and the returned object is not AsyncIterable. This works correctly for...
Support the `tools` and `tool_choice` parameters in the OpenAI-compatible API. Currently these are not supported https://github.com/ollama/ollama/blob/4ec7445a6f678b6efc773bb9fa886d7c9b075577/docs/openai.md#supported-request-fields I believe `llama.cpp` is used internally by Ollama, and this has support for tools...
Update scipy dependency to that vocode-python can be used with python 3.12. Scipy no longer supports python `3.8` so as a result this PR breaks compatibility with python 3.8. Also...
Resolves #74 - Create new `Usage` class - Add this as an optional attribute of `AssistantMessage` - Wrap openai response stream to set usage when encountered - Add usage to...
Follow-on from issue https://github.com/jackmpcollins/magentic/issues/194 Ollama models (via LiteLLM) are returning incorrect function name in tool call output, which leads to magentic failing to parse this. ```python from magentic import prompt...
Use a service container https://docs.github.com/en/actions/using-containerized-services/about-service-containers to run the ollama image https://hub.docker.com/r/ollama/ollama
Each function created using a magentic decorator (`@prompt`, `@chatprompt`, etc.) should have a corresponding span, as if it was also decorated with [`@tracer.start_as_current_span()`](https://opentelemetry.io/docs/languages/python/instrumentation/#creating-spans-with-decorators). The function arguments (with strings truncated) should...
Add a backend for Google's `google-generativeai` python package to support Gemini. https://ai.google.dev/tutorials/python_quickstart