prolego-team / neo-sophia

Applying the latest advancements in AI and machine learning to solve complex business problems.
BSD 3-Clause "New" or "Revised" License
66 stars 26 forks source link

Fix issue with MSRB rules PDF #125

Closed bdzimmer closed 11 months ago

bdzimmer commented 11 months ago

New version of MSRB rules PDF has a longer section that won't generate an embedding. I've updated the downloader to use the 2022 version explicitly. (Seems to be a slightly different version than what we were using before though.)

I've also added the embeddings.pkl so people don't have to run the downloader. I wasn't sure about adding the PDF, let me know if you want me to.

Note that this PR doesn't fix the failing unit test.

Fixes #124

kevindewalt commented 11 months ago

@bdzimmer Let's add the PDF. That way it is there if we need it.