File uploading for embedding via API ?

Can't find any mention of file uploads via API calls, OpenAI API endpoints have `/v1/files`
But when I upload the file, it takes time, as if it is uploading, then I get an error.

I've noticed LM Studio uses a built-in tool, `rag-v1`. If we call that tool via chat in the API, how do we upload the file? Or is this simply not possible?

Would I need to add another layer to break down the document with LangChain and add embeddings via LM Studio text embedding?

No reference to any documentation about working with files with the web API, only found image uploads..

Any help would be appreciated😁

Start by checking the documentation for API file uploads, the `/v1/files` endpoint, and the `rag-v1` tool mentioned in the issue. Determine whether file upload and retrieval-augmented generation are supported, and document the supported workflow or state clearly that an external preprocessing and embedding layer is required.

Written by the indexing model from the issue text.