wrong url

no logo

Remove Git LFS tracking and reset file state

add well known plugin manifest and logo for mcp integration

ignore .gradio folder

checkpoint 1

Revert "1. Structure responses with both diagnoses and follow-up questions"

1. Structure responses with both diagnoses and follow-up questions

see a progress counter when submit is it

submit button wasn't working

these integrations could potentially multiply winnings

actually... the gradio live link would allow me to show o4-mini-high the results, where I could not before

no need for gradio live

included badly needed links to where I'm developing

tags chosen highlight technical strengths and practical applications, I am attempting to target multiple prize categories, there's a limit to the number of tags

solved ffmpeg-related error

1. Removed global pipeline initialization to prevent warm-up crashes

FutureWarning: The input name `inputs` is deprecated. Please make sure to use `input_features` instead.

preventing segmentation fault

1. Added memory management

1. Added text input processing function

attention mask is not set

audio processing pipeliine

1. Removed unsafe `.get()` calls

taking out type

enable cross-origin requests

should resolve font-related console errors

microphone should now transcribe directly to text wihtout needing intermediate audio file processing

popped the bubble

bug fix

Add footer with social links

- Create the models directory on demand

fixed problems

Streamline dependencies for better build reliability

1. Added a professional header and instructions

enhanced logging

should resolve the `ModuleNotFoundError` in the Hugging Face Space while maintaining the local development setup

1. More structured query format focusing on ICD-10 codes

1. Modified the query prompt to explicitly ask for differentiating questions

1. Removed hardcoded "cough" question

better visibility into the startup process

added import

1. Only download the specific `.gguf` file we need

doesn't seem to be running

setup for local llm

neaten

use llamacpp integration instead

no problems, local llm setup

requests module for optional mcp endpoint testing

feat: Add local LLM support with ctransformers