Marco Tulio Correia Ribeiro
Marco Tulio Correia Ribeiro
I think https://github.com/microsoft/guidance/discussions/129 answers this now, feel free to reopen otherwise.
You can access the docs [here](https://guidance.readthedocs.io/en/latest/) (this should have been on the readme, I'll add it).
In the works.
We have no plans to implement a js version, but as soon as we get server support going it should be easy to call guidance from `js`
In the new [release](https://github.com/guidance-ai/guidance/discussions/429), we support [llama-cpp models](https://github.com/guidance-ai/guidance#llamacpp). Sorry it took us so long to get to this! They are great, and very fast.
I think this is fixed now. If not, please reopen and give us a snippet to reproduce.
> The error goes away after seting stop=False as suggested in the error message but I think this should be added to the readme. I can do the pull request...
The cleanest way would be to set `pattern='[0-9]+`, but as you noted that doesn't work for OpenAI models. Another easy fix is to get the model to stop generation at...
Sorry, how does this explain the process better than the gif we have in the readme right now?
Hey, sorry it took us so long (please see [this](https://github.com/guidance-ai/guidance/discussions/429) announcement). The new version works a little differently, we have [immutable objects](https://github.com/guidance-ai/guidance#basic-generation), and it's easy to take partial completions and...