Spaces:
Sleeping
Sleeping
Commit History
-
checkpoint 2 - we are in a very good position right now, audio transcription is working, gradio page looks good, local llms are working, returning the consultation, the json that will be sent to the mcp client, and a debugging panel
5e4e457 -
improved seperation of concerns best practice in the code, added print statements for better understanding of what code is doing
9d2bec8 -
app.py wrapper for Gradio waa very bad idea, regoranizing project for clarity, utils folder will be very import of separation of concerns
3b5fe24
-
hf embeddings for llama index had to be installed: https://docs.llamaindex.ai/en/stable/module_guides/models/embeddings/
357828f -
Add multi‐backend LLM support and audio‐driven medical agent pipeline
- Integrate Whisper ASR for speech‐to‐text symptom input - Unify agent logic in `transcribe_and_respond()` using `get_llm_predictor()` (OpenAI, Mistral, or local pipeline) - Enable environment flags `USE_LOCAL_GPU` and `USE_MISTRAL` to switch models dynamically - Update Gradio `app.py` to launch audio/chat interface with MCP support82d84c7 -
added ability to develop on my local rtx2060
16559c8 -
utilizing llama index can net an extra $1000 in winnings
1f22857