Update app.py

app.py

@@ -436,6 +436,63 @@ For more information on `huggingface_hub` Inference API support, please check th
 
 # app.py
 
+# app.py
+
+# import os
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+# from dotenv import load_dotenv
+
+# # Load environment variables
+# load_dotenv()
+# HF_TOKEN = os.getenv("HF_TOKEN")
+
+# # Initialize Hugging Face Inference Client
+# client = InferenceClient(
+#     model="mistralai/Codestral-22B-v0.1",
+#     token=HF_TOKEN
+# )
+
+# # System prompt for coding assistant
+# system_message = (
+#     "You are a helpful and experienced coding assistant specialized in web development. "
+#     "Help the user by generating complete and functional code for building websites. "
+#     "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) "
+#     "based on their requirements."
+# )
+
+# # Streaming chatbot logic using chat.completions
+# def respond(message, history):
+#     # 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/Codestral-22B-v0.1",
+#         messages=messages,
+#         max_tokens=1024,
+#         temperature=0.7,
+#         top_p=0.95,
+#         stream=True,
+#     ):
+#         token = chunk.choices[0].delta.get("content", "") or ""
+#         response += token
+#         yield response
+
+# # 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()
+
+
 # app.py
 
 import os
@@ -449,7 +506,7 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 
 # Initialize Hugging Face Inference Client
 client = InferenceClient(
-    model="mistralai/Codestral-22B-v0.1",
+    model="mistralai/Mistral-7B-Instruct-v0.3",
     token=HF_TOKEN
 )
 
@@ -461,7 +518,7 @@ system_message = (
     "based on their requirements."
 )
 
-# Streaming chatbot logic using chat.completions
+# Streaming chatbot logic
 def respond(message, history):
     # Prepare messages with system prompt
     messages = [{"role": "system", "content": system_message}]
@@ -472,7 +529,7 @@ def respond(message, history):
     # Stream response from the model
     response = ""
     for chunk in client.chat.completions.create(
-        model="mistralai/Codestral-22B-v0.1",
+        model="mistralai/Mistral-7B-Instruct-v0.3",
         messages=messages,
         max_tokens=1024,
         temperature=0.7,
@@ -498,4 +555,3 @@ if __name__ == "__main__":
 
 
 
-