Dhruv Anand

+1 for this feature

@davidbernat you've not solved anything as far as I can see. Please keep this issue open until the functionality is implemented in Gradio, or there is a simple process we...

https://huggingface.co/docs/datasets/dataset_script

@emekaokoli19 did you test the newest version of the code with a weaviate instance?

@emekaokoli19 you need to make sure that it works for any import command. eg: ``` import_vdf \ --max_num_rows 1000 \ --hf_dataset aintech/vdf_prefix-cache \ weaviate ``` Here it asks me for...

yes, it does

works

Actually, the cost calculation is wrong: https://github.com/BerriAI/litellm/blob/eb9eca6f3709cc894dc0542a4ecce5cffc2383de/model_prices_and_context_window.json#L1690-L1703 https://docs.perplexity.ai/docs/pricing The pricing has a $5/1000 requests component, and $0.28/1M output tokens. Your mapping only has $0.0005 per output token, which gives the...

+1

@emilrueh did you figure this out? Getting the same error. I wonder if I should be closing the pinecone client somehow