Marie Stephen Leo

Is there a ticket or PR I can watch to get updates on GCP support? Thanks

Support in VSCode's jupyter notebooks will be very much appreciated!

Thanks! was able to import and run on STS-B dataset. However, loading the model throws this warning. Is it expected? ``` from DiffCSE.diffcse import DiffCSE model = DiffCSE('voidism/diffcse-roberta-base-sts') ``` ```...

I took a look at the Visjs example. It looks like you just have to add an additional `fixed` node to your graph for each legend. I've been trying it...

There seems to be a bug with setting `.settings(url_params={'pruneOrphans': 'true'})` On initial load, the `Hide Standalone Nodes` setting is selected, but it doesn't seem to be working  However, toggling...

I see I see... just the index size RAM @lmcinnes Unfortunately, my use case is a large dataset. Pynndescent provides the best queries/s on a sample of the dataset, hence...

That's right, the streaming mode doesn't support token_usage even for the OpenAI llm https://langchain.readthedocs.io/en/latest/modules/llms/streaming_llm.html?highlight=token_usage

Awesome! #1785 adds much of the functionality of this PR. Will debug the 0 token_usage on the new master and re-submit a cleaner PR

Related to https://github.com/hwchase17/langchain/pull/1924, pls take a look at the discussion there

@hwchase17 , could you pls help to take a look at this when you can?