Daniel Barker

Same issue. Tried moving the two lines mentioned below the Resources section, but still no luck. I'm on Ubuntu 18.04, FWIW.

Here's how I run my container to get the display to output properly. (Note: I'm elevating the privileges of the container to have access to the host, so be aware...

How about something like this? The code below expects the pose keypoints to be input as a numpy array shaped like (num_people, 25, 3), which is how the pyopenpose Python...

This is actually pretty easy to implement as is with the HF inference server since Langchain supports wrapping custom models (example below is taken nearly verbatim from the Langchain docs)....

> langchain team has already built this integration: https://python.langchain.com/en/latest/modules/models/llms/integrations/huggingface_textgen_inference.html Yes, and we also have the streaming feature working in that implementation, contrary to my original post. Unfortunately, it doesn't support...

@ArnaudHureaux, unfortunately the answer right now is (to my knowledge) 'no', there isn't a similar option available for embeddings. This is a major hole in the LLM ecosystem IMO, so...

> Collaborator Sure thing! [Here is a quick video demo](https://drive.google.com/file/d/1RA7bTT3YtHIDFwEugfnmE0Uf3EsFM95l/view?usp=share_link).

lol looks like we were working on the same thing within a few hours of each other: [PR 4434](https://github.com/hwchase17/langchain/pull/4434)

@gsaivinay, awesome, I'm good with whatever is easiest. Thanks for working on this. It should make working with local LLMs a lot easier!

These are all great ideas. I recommend submitting a PR in the [form generation API repo here](https://github.com/ramblingjordan/AbBOT-api).