Cameron Milne

Any update on making this installable via pip? Would love to use this!

> I used "BAAI/bge-base-en" embedding and created succesfully a Chroma Database. > > ``` > > # Supplying a persist_directory will store the embeddings on disk > persist_directory = '/content/drive/MyDrive/db'...

> ### Issue you'd like to raise. > I create my vector db using the following code: > > ``` > db = Chroma.from_documents( > chunked_documents, > embeddings, > persist_directory=db_path...

Also experiencing this problem periodically with version 1.33.0! I have a multi-page application with roughly 5-10 st.dataframe()'s on display. They pretty much all have _use_container_width=True_, but weirdly only a couple...

@jkleint I was able to resolve this by updating Conda, updating the Pillow library, and then manually deleting the _DroidSansMono.ttf_ file in this folder: C:\ProgramData\Anaconda3\Lib\site-packages\wordcloud\

> Hey! This clearly appears to be from a problem loading the custom torch/cuda files from upstream ColBERT. > > This bit in particular: > > > /bin/sh: 1: /usr/local/cuda-12.3/bin/nvcc:...

Also getting this error: `ValueError: Could not connect to a Chroma server. Are you sure it is running? ` I have two services: a Chroma service exposed on port 8000...

Any update on this? Getting the same result when using the pipeline class for question answering

> Hi, I am not sure but try converting mp3 to wav and trying again. Converting to a WAV file worked. Not sure why, but thanks!