Alexander Chemeris

[feature request] Allow selection of audio track/language

4

Great app! It lacks an important feature for international users though - an ability to select audio stream/language in a video file. Most movies I'm watching are coming with multiple...

Manual OpenAI async code vs official AsyncOpenAI

2

I noticed that you're making async calls to OpenAI API manually in `async def async_create_completion()`. Is there any reason for this instead of using the `AsyncOpenAI` from the official library?...

Running agent.arun(input=df) with environment=None is totally valid.

4

Otherwise this code requires us to create an dummy async environment which is not used in the code and not even possible with the current code base.

A bunch of improvements for the classification skill

1

Thank you for an excellent library. I ran it against our dataset of 10k social media posts to detect their sentiment and classify it into a set of topics. This...

Support for Anyscale models with Log Probabilities

1

**Is your feature request related to a problem? Please describe.** OpenAI support at guidance doesn't rely on logrpobs, as far as I understand. Anyscale seems to mimic OpenAI API but...

[Model][Frontend] Adding timeseries modality support and Qwen2.5-ChatTS model support

5

This pull request has two parts: 1. Adds generic infrastructure for handling time series as a modality, including an OpenAI API server. 2. Adds support for [ChatTS](https://github.com/NetManAIOps/ChatTS/) model inference that...