Update app.py

app.py

@@ -1,70 +1,86 @@
+# app.py
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import torch
+from transformers import pipeline, AutoProcessor, AutoModelForVision2Seq
+
+# -------------------
+# Load Whisper (STT) from Hugging Face
+# -------------------
+stt_pipe = pipeline(
+    "automatic-speech-recognition",
+    model="openai/whisper-small",   # Replace with your uploaded Whisper model repo
+    device=0 if torch.cuda.is_available() else -1
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+# -------------------
+# Load ChatDOC model
+# -------------------
+chatdoc_model_id = "username/CHATDOCMODEL"  # replace with your uploaded repo
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float16 if device == "cuda" else torch.float32
+
+processor = AutoProcessor.from_pretrained(chatdoc_model_id, trust_remote_code=True)
+chatdoc_model = AutoModelForVision2Seq.from_pretrained(
+    chatdoc_model_id,
+    torch_dtype=dtype
+).to(device)
+
+# -------------------
+# Chat function
+# -------------------
+def chat_with_doc(audio, message, history=[]):
+    transcript = ""
+    if audio is not None:
+        result = stt_pipe(audio)
+        transcript = result["text"]
+
+    user_msg = message or transcript
+    if not user_msg.strip():
+        return history, "No input detected."
+
+    history.append([user_msg, None])
+
+    # System prompt (simplified for demo)
+    system_prompt = "You are a medical doctor interviewing a patient. Respond helpfully."
+    dialogue = "\n".join([f"Patient: {u}\nDoctor: {b}" for u, b in history if u and b])
+    prompt = f"{system_prompt}\n\nConversation:\n{dialogue}\nPatient: {user_msg}\nDoctor:"
+
+    inputs = processor(text=prompt, images=None, return_tensors="pt").to(device)
+    with torch.inference_mode():
+        outputs = chatdoc_model.generate(
+            **inputs,
+            max_new_tokens=200,
+            do_sample=True,
+            temperature=0.7
+        )
+
+    input_len = inputs["input_ids"].shape[1]
+    gen_tokens = outputs[:, input_len:]
+    response = processor.batch_decode(gen_tokens, skip_special_tokens=True)[0].strip()
+
+    history[-1][1] = response
+    return history, response
+
+# -------------------
+# Gradio UI
+# -------------------
+with gr.Blocks(title="ChatDOC") as demo:
+    gr.Markdown("# 🩺 ChatDOC + Whisper\nTalk or type your symptoms.")
+
+    chatbot = gr.Chatbot(height=400)
+    msg = gr.Textbox(placeholder="Type your symptoms...")
+    mic = gr.Audio(sources=["microphone"], type="filepath", label="🎤 Speak your symptoms")
+
+    clear_btn = gr.Button("Clear Chat")
+
+    state = gr.State([])
+
+    def respond(audio, text, history):
+        return chat_with_doc(audio, text, history)
 
+    msg.submit(respond, [mic, msg, state], [chatbot, msg, state])
+    mic.change(respond, [mic, msg, state], [chatbot, msg, state])
+    clear_btn.click(lambda: ([], "", []), None, [chatbot, msg, state])
 
 if __name__ == "__main__":
     demo.launch()