Update app.py

app.py

@@ -95,36 +95,88 @@
 # # Load your model after launching the interface
 # gr.load("models/Bhaskar2611/Capstone").launch()
 
+# import os
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+# from dotenv import load_dotenv
+
+# # Load API token from .env or environment
+# load_dotenv()
+# HF_TOKEN = os.getenv("HF_TOKEN")  # or directly use your token here
+
+# # Initialize the Hugging Face inference client
+# client = InferenceClient(
+#     model="mistralai/Mistral-7B-Instruct-v0.3",
+#     token=HF_TOKEN
+# )
+
+# # Skin assistant prompt
+# HAIR_ASSISTANT_PROMPT = (
+#     "You are an AI Dermatologist chatbot designed to assist users with Hair by only providing text "
+#     "and if user information is not provided related to Hair then ask what they want to know related to Hair."
+# )
+
+# def respond(message, history):
+#     messages = [{"role": "system", "content": HAIR_ASSISTANT_PROMPT}]
+#     for user_msg, bot_msg in history:
+#         if user_msg:
+#             messages.append({"role": "user", "content": user_msg})
+#         if bot_msg:
+#             messages.append({"role": "assistant", "content": bot_msg})
+#     messages.append({"role": "user", "content": message})
+
+#     response = ""
+#     for chunk in client.chat.completions.create(
+#         model="mistralai/Mistral-7B-Instruct-v0.3",
+#         messages=messages,
+#         max_tokens=1024,
+#         temperature=0.7,
+#         top_p=0.95,
+#         stream=True,
+#     ):
+#         token = chunk.choices[0].delta.get("content", "")
+#         response += token
+#         yield response
+
+# # Launch Gradio interface
+# demo = gr.ChatInterface(
+#     fn=respond,
+#     title="Hair-Bot",
+#     theme="default"
+# )
+
+# if __name__ == "__main__":
+#     demo.launch()
 import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 from dotenv import load_dotenv
 
-# Load API token from .env or environment
+# Load Hugging Face API token
 load_dotenv()
-HF_TOKEN = os.getenv("HF_TOKEN")  # or directly use your token here
+HF_TOKEN = os.getenv("HF_TOKEN")
 
-# Initialize the Hugging Face inference client
+# Initialize Hugging Face client
 client = InferenceClient(
     model="mistralai/Mistral-7B-Instruct-v0.3",
     token=HF_TOKEN
 )
 
-# Skin assistant prompt
-HAIR_ASSISTANT_PROMPT = (
+# System prompt about Indian monuments
+system_message = (
     "You are an AI Dermatologist chatbot designed to assist users with Hair by only providing text "
-    "and if user information is not provided related to Hair then ask what they want to know related to Hair."
+    "and if user information is not provided related to Hair then ask what they want to know related to Hair."   
 )
 
+# Streaming chatbot logic
 def respond(message, history):
-    messages = [{"role": "system", "content": HAIR_ASSISTANT_PROMPT}]
-    for user_msg, bot_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if bot_msg:
-            messages.append({"role": "assistant", "content": bot_msg})
+    # Prepare messages with system prompt
+    messages = [{"role": "system", "content": system_message}]
+    for msg in history:
+        messages.append(msg)
     messages.append({"role": "user", "content": message})
 
+    # Stream response from the model
     response = ""
     for chunk in client.chat.completions.create(
         model="mistralai/Mistral-7B-Instruct-v0.3",
@@ -134,16 +186,15 @@ def respond(message, history):
         top_p=0.95,
         stream=True,
     ):
-        token = chunk.choices[0].delta.get("content", "")
+        token = chunk.choices[0].delta.get("content", "") or ""
         response += token
         yield response
 
-# Launch Gradio interface
-demo = gr.ChatInterface(
-    fn=respond,
-    title="Hair-Bot",
-    theme="default"
-)
+# Create Gradio interface
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot(type='messages')  # Use modern message format
+    gr.ChatInterface(fn=respond, chatbot=chatbot, type="messages")  # Match format
 
+# Launch app
 if __name__ == "__main__":
     demo.launch()