cpwan

Reimplementation in RL platform (CleanRL)

2

Hello there, my team has been trying to implement the Attention Model in RL platforms so that we can try out different RL algorithms. Eventually, we succeed to implement the...

feat: Add page_number attribute to document segments and update related retrieval logic

5

# Summary This feature was first introduced in #7749, but then reverted since it has a bug in #8211 . Since then, there are couple of issues asking to reintroduce...

Current implementation: https://github.com/microsoft/markitdown/blob/62b72284feb986ffaf8c22fa73614545b5713c30/packages/markitdown/src/markitdown/converters/_transcribe_audio.py#L48 The problem is that, when my audio is not in English, it still try to transcribe to English. Is it possible to implement some configurable options to...

[ENH]: Enable In memory loading, for format not supported by soundfile

4

### Problem Here is the current behavior: 1. No problem with load from path ```python import librosa librosa.load("sample.ogg") # no problem, use `soundfile` librosa.load("sample.webm") # no problem, falls back to...