Update app.py

app.py

@@ -1,70 +1,66 @@
+import torch
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
+model_name = "mistralai/Mistral-7B-Instruct-v0.1"
 
-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")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-    messages = [{"role": "system", "content": system_message}]
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    load_in_4bit=True,
+    torch_dtype=torch.float16
+)
 
-    messages.extend(history)
+generator = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=200,
+    temperature=0.3,
+    repetition_penalty=1.1
+)
 
-    messages.append({"role": "user", "content": message})
+def is_unsafe(query):
+    blocked = [
+        "dose", "dosage", "how much",
+        "diagnose", "prescribe",
+        "medicine for", "treatment", "cure"
+    ]
+    return any(word in query.lower() for word in blocked)
 
-    response = ""
+def health_chatbot(user_input):
+    if is_unsafe(user_input):
+        return (
+            "I can’t provide diagnosis or medication instructions. "
+            "Please consult a qualified healthcare professional."
+        )
 
-    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
+    prompt = f"""
+You are a general health information assistant.
 
-        response += token
-        yield response
+Rules:
+- Do NOT diagnose diseases.
+- Do NOT prescribe medicines or give dosages.
+- Provide general causes, symptoms, and prevention only.
+- Keep answers simple and clear.
+- End with: 'If symptoms persist, consult a healthcare professional.'
 
+Question:
+{user_input}
 
+Answer:
 """
-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)",
-        ),
-    ],
-)
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    output = generator(prompt)[0]["generated_text"]
+    return output.split("Answer:")[-1].strip()
 
+demo = gr.Interface(
+    fn=health_chatbot,
+    inputs=gr.Textbox(lines=2),
+    outputs="text",
+    title="🩺 General Health Query Chatbot"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()