Update app.py

app.py

@@ -1,18 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 import json
-import uuid
-from PIL import Image
 from bs4 import BeautifulSoup
 import requests
-import random
-from transformers import LlavaProcessor, LlavaForConditionalGeneration, TextIteratorStreamer
-from threading import Thread
-import re
-import time 
-import torch
-import cv2
-from gradio_client import Client, file
 
 def extract_text_from_webpage(html_content):
     soup = BeautifulSoup(html_content, 'html.parser')
@@ -22,7 +12,6 @@ def extract_text_from_webpage(html_content):
 
 def search(query):
     term = query
-    start = 0
     all_results = []
     max_chars_per_page = 8000
     with requests.Session() as session:
@@ -70,8 +59,7 @@ def respond(message, history):
         func_caller.append({"role": "user", "content": f"{str(msg[0])}"})
         func_caller.append({"role": "assistant", "content": f"{str(msg[1])}"})
 
-    message_text = message["text"]
-    func_caller.append({"role": "user", "content": f'[SYSTEM]You are a helpful assistant. You have access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }}  </functioncall>  [USER] {message_text}'})
+    func_caller.append({"role": "user", "content": f'[SYSTEM]You are a helpful assistant. You have access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }}  </functioncall>  [USER] {message}'})
     
     response = client_gemma.chat_completion(func_caller, max_tokens=200)
     response = str(response)
@@ -97,7 +85,7 @@ def respond(message, history):
             for msg in history:
                 messages += f"\nuser\n{str(msg[0])}"
                 messages += f"\nassistant\n{str(msg[1])}"
-            messages+=f"\nuser\n{message_text}\nweb_result\n{web2}\nassistant\n"
+            messages+=f"\nuser\n{message}\nweb_result\n{web2}\nassistant\n"
             stream = client_mixtral.text_generation(messages, max_new_tokens=2000, do_sample=True, stream=True, details=True, return_full_text=False)
             output = ""
             for response in stream:
@@ -109,7 +97,7 @@ def respond(message, history):
             for msg in history:
                 messages += f"\nuser\n{str(msg[0])}"
                 messages += f"\nassistant\n{str(msg[1])}"
-            messages+=f"\nuser\n{message_text}\nassistant\n"
+            messages+=f"\nuser\n{message}\nassistant\n"
             stream = client_llama.text_generation(messages, max_new_tokens=2000, do_sample=True, stream=True, details=True, return_full_text=False)
             output = ""
             for response in stream:
@@ -121,7 +109,7 @@ def respond(message, history):
         for msg in history:
             messages += f"\nuser\n{str(msg[0])}"
             messages += f"\nassistant\n{str(msg[1])}"
-        messages+=f"\nuser\n{message_text}\nassistant\n"
+        messages+=f"\nuser\n{message}\nassistant\n"
         stream = client_llama.text_generation(messages, max_new_tokens=2000, do_sample=True, stream=True, details=True, return_full_text=False)
         output = ""
         for response in stream:
@@ -133,8 +121,8 @@ demo = gr.ChatInterface(
     fn=respond,
     chatbot=gr.Chatbot(show_copy_button=True, likeable=True, layout="panel"),
     description=" ",
-    textbox=gr.Textbox(),
-    multimodal=False,
+    textbox=gr.Textbox(),  # Changed to Textbox
+    multimodal=False,  # Disabled multimodal
     concurrency_limit=200,
 )
-demo.launch()
+demo.launch(share=True)