Update app.py

app.py

@@ -1,16 +1,17 @@
 #using codes from mistralai official cookbook
 import gradio as gr
-from mistralai.client import MistralClient
+from mistralai.async_client import MistralAsyncClient
 from mistralai.models.chat_completion import ChatMessage
 import numpy as np
 import PyPDF2
 import faiss
 import os
 import httpx
+import asyncio
 
 mistral_api_key = os.environ.get("API_KEY")
 
-cli = MistralClient(api_key = mistral_api_key)
+cli = MistralAsyncClient(api_key = mistral_api_key)
 
 def get_text_embedding(input: str):
     embeddings_batch_response = cli.embeddings(
@@ -61,12 +62,26 @@ def ask_mistral(message: str, history: list):
         messages.append(ChatMessage(role = "user", content = message["text"]))
 
     full_response = ""
-    for chunk in cli.chat_stream(model = "open-mistral-7b", messages = messages, max_tokens = 1024):
+
+    async_response = cli.chat_stream(
+        model = "open-mistral-7b", 
+        messages = messages, 
+        max_tokens = 1024 
+    )
+
+    async for chunk in async_response:
         full_response += chunk.choices[0].delta.content
         yield full_response
 
-app = gr.ChatInterface(
-    fn = ask_mistral, 
-    title = "Ask Mistral and talk to your PDFs", 
-    multimodal = True)
-app.launch()
+chatbot = gr.Chatbot()
+
+with gr.Blocks(theme="soft") as demo:
+    gr.ChatInterface(
+        fn = ask_mistral,
+        title = "Ask Mistral and talk to your PDFs", 
+        multimodal = True,
+        chatbot=chatbot,
+    )
+
+if __name__ == "__main__":
+    demo.queue(api_open=False).launch(show_api=False, share=False)