DocsGPT Error training on new docs

Getting this error out of the gate when trying to train on a single new .rst file. Any thoughts?

Traceback (most recent call last):
  File "/home/pshriwise/soft/doc-gpt/docsgpt/scripts/ingest_rst.py", line 36, in <module>
    store = FAISS.from_texts(docs, OpenAIEmbeddings(), metadatas=metadatas)
  File "/home/pshriwise/.pyenv/versions/3.9.1/lib/python3.9/site-packages/langchain/vectorstores/faiss.py", line 192, in from_texts
    index = faiss.IndexFlatL2(len(embeddings[0]))
IndexError: list index out of range

Feb 06 '23 14:02 pshriwise

@pshriwise Could you provide the .rst file that causes the error?

Feb 06 '23 17:02 bil0u

Sure thing! https://github.com/openmc-dev/openmc/blob/develop/docs/source/index.rst

Feb 06 '23 17:02 pshriwise

@pshriwise Hey Patrick,

If you haven't already, create a folder named "scikit-learn" inside the "scripts" folder and toss your index.rst inside of it. That should fix your problem.

You can really name the folder anything you would like, just make sure it matches the path in the ingest_rst.py and ingest_rst_sphinx.py files:

ps = list(Path("<FolderName>").glob("**/*.rst"))

Feb 07 '23 02:02 jaredbradley243

Let me know if that works for you so I can close the issue. :)

Feb 07 '23 02:02 jaredbradley243

It did. Thanks! I appreciate the help!

Feb 07 '23 03:02 pshriwise

No problem! Glad to help.

Feb 07 '23 03:02 jaredbradley243