Hey when using unstructured can you help me decipher what format the data needs to be in to use llama index. I am looking to extend the partition_html to the auto partition.
it looks like i will need to write a extract_elements since that one is hard coded for html.

When using UnstructuredElementNodeParser is there an easy way to get it to use a hi-res strategy ?

I got another one for you. Ill make it a thread to keep the server a little clean . but it involved using the local embeddingz

I have a question. I noticed that are requests that go out to posthog. Is there a way to disable those from happening. I am using llamaindex in a completely offline environment. The requests timeout takes about 7 minutes in total.

Hi all. I have a question, I am truing to use the unstructured loader
node_parser = UnstructuredElementNodeParser(llm=llm)
The llm is local and if i use any other parser then there isnt a problem.
But i get this error
Could not load OpenAI embedding model. If you intended to use OpenAI, please check your OPENAI_API_KEY.
Original error:

@Logan M I am just gonna make a thread. I am working on getting unstructured to use pdf instead of html. And i am running into an openai request issue again