Update app.py

app.py

@@ -3,7 +3,12 @@ import torch
 import spaces
 import logging
 from deep_translator import GoogleTranslator
-
+import pandas as pd
+from tqdm import tqdm
+import urllib
+import aiohttp
+import asyncio
+from bs4 import BeautifulSoup
 
 # Configure logging to write messages to a file
 logging.basicConfig(filename='app.log', level=logging.ERROR)
@@ -12,44 +17,31 @@ logging.basicConfig(filename='app.log', level=logging.ERROR)
 max_seq_length = 2048
 dtype = None  # Auto detection of dtype
 load_in_4bit = True  # Use 4-bit quantization to reduce memory usage
-
-peft_model_name = "limitedonly41/website_mistral7b_v02_1200_finetuned_7"
+peft_model_name = "limitedonly41/website_qwen2_7b_2"
 
 # Initialize model and tokenizer variables
 model = None
 tokenizer = None
 
-
-
-
-import pandas as pd
-from tqdm import tqdm
-import urllib
-import aiohttp
-import asyncio
-from bs4 import BeautifulSoup
-
+# Async function to fetch data
 async def fetch_data(url):
     headers = {
         'Accept': '*/*',
         'Accept-Language': 'ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7',
         'Connection': 'keep-alive',
-        # 'Origin': 'https://www.beckman.es',
         'Referer': f'{url}',
         'Sec-Fetch-Dest': 'empty',
         'Sec-Fetch-Mode': 'cors',
         'Sec-Fetch-Site': 'cross-site',
-        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
+        'User-Agent': 'Mozilla/5.0',
         'sec-ch-ua': '"Google Chrome";v="125", "Chromium";v="125", "Not.A/Brand";v="24"',
         'sec-ch-ua-mobile': '?0',
         'sec-ch-ua-platform': '"macOS"',
     }
 
-
-    # encoding = 'windows-1251'
     encoding = 'utf-8'
-
     timeout = 10  # Set your desired timeout value in seconds
+
     try:
         # Function to make the request using urllib
         def get_content():
@@ -57,90 +49,26 @@ async def fetch_data(url):
             with urllib.request.urlopen(req, timeout=timeout) as response:
                 return response.read()
 
+        # Async task using executor for blocking I/O
+        loop = asyncio.get_event_loop()
         response_content = await loop.run_in_executor(None, get_content)
 
         soup = BeautifulSoup(response_content, 'html.parser', from_encoding=encoding)
-
-        title = soup.find('title').text
+        title = soup.find('title').text if soup.find('title') else ""
         description = soup.find('meta', attrs={'name': 'description'})
-        if description and "content" in description.attrs:
-            description = description.get("content")
-        else:
-            description = ""
+        description = description.get("content") if description and "content" in description.attrs else ""
 
         keywords = soup.find('meta', attrs={'name': 'keywords'})
-        if keywords and "content" in keywords.attrs:
-            keywords = keywords.get("content")
-        else:
-            keywords = ""
-
-        # h1_all = " ".join(h.text for h in soup.find_all('h1'))
-        # h2_all = " ".join(h.text for h in soup.find_all('h2'))
-        # h3_all = " ".join(h.text for h in soup.find_all('h3'))
-        # paragraphs_all = " ".join(p.text for p in soup.find_all('p'))
-
-
-
-        h1 = soup.find_all('h1')
-        h1_all = ""
-
-        try:
-            for x in range (len(h1)):
-                if x ==  len(h1) -1:
-                    h1_all = h1_all + h1[x].text
-                else:
-                    h1_all = h1_all + h1[x].text + ". "
-        except:
-            h1_all = ""
-
-        paragraphs_all = ""
-        paragraphs = soup.find_all('p')
-        try:
-            for x in range (len(paragraphs)):
-                if x ==  len(paragraphs) -1:
-                    paragraphs_all = paragraphs_all + paragraphs[x].text
-                else:
-                    paragraphs_all = paragraphs_all + paragraphs[x].text + ". "
-        except:
-            paragraphs_all = ""
-
-        h2 = soup.find_all('h2')
-        h2_all = ""
-        try:
-            for x in range (len(h2)):
-                if x ==  len(h2) -1:
-                    h2_all = h2_all + h2[x].text
-                else:
-                    h2_all = h2_all + h2[x].text + ". "
-        except:
-            h2_all = ""
-
-        h3 = soup.find_all('h3')
-        h3_all = ""
-
-        try:
-            for x in range (len(h3)):
-                if x ==  len(h3) -1:
-                    h3_all = h3_all + h3[x].text
-                else:
-                    h3_all = h3_all + h3[x].text + ". "
-        except:
-            h3_all = ""
-
+        keywords = keywords.get("content") if keywords and "content" in keywords.attrs else ""
 
+        h1_all = ". ".join(h.text for h in soup.find_all('h1'))
+        paragraphs_all = ". ".join(p.text for p in soup.find_all('p'))
+        h2_all = ". ".join(h.text for h in soup.find_all('h2'))
+        h3_all = ". ".join(h.text for h in soup.find_all('h3'))
 
         allthecontent = f"{title} {description} {h1_all} {h2_all} {h3_all} {paragraphs_all}"
         allthecontent = allthecontent[:4999]
 
-        # Clean up the text
-        h1_all = h1_all.replace(r'\xa0', ' ').replace('\n', ' ').replace('\t', ' ')
-        h2_all = h2_all.replace(r'\xa0', ' ').replace('\n', ' ').replace('\t', ' ')
-        h3_all = h3_all.replace(r'\xa0', ' ').replace('\n', ' ').replace('\t', ' ')
-
-        title = title.replace(r'\xa0', ' ')
-        description = description.replace(r'\xa0', ' ')
-        keywords = keywords.replace(r'\xa0', ' ')
-
         return {
             'url': url,
             'title': title,
@@ -152,8 +80,9 @@ async def fetch_data(url):
             'paragraphs': paragraphs_all,
             'text': allthecontent
         }
+
     except Exception as e:
-        print(url, e)
+        logging.exception(f"Error fetching data for {url}: {e}")
         return {
             'url': url,
             'title': None,
@@ -166,6 +95,7 @@ async def fetch_data(url):
             'text': None
         }
 
+# Main async function to process multiple URLs
 async def main(urls):
     tasks = [fetch_data(url) for url in urls]
     results = []
@@ -174,44 +104,37 @@ async def main(urls):
         results.append(result)
     return results
 
-
-
-
-
-
-
 @spaces.GPU()
 def classify_website(url):
-    global model, tokenizer  # Declare model and tokenizer as global variables
+    global model, tokenizer
 
     urls = [url]
-    
-    # Run asyncio event loop
-    loop = asyncio.get_event_loop()
-    results_shop = await main(urls[:])  # Instead of loop.run_until_complete(main(urls))
-    
+
+    # Start asyncio loop for fetching data
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    results_shop = loop.run_until_complete(main(urls))  # Correctly use asyncio loop
+
     # Convert results to DataFrame
     df_result_train_more = pd.DataFrame(results_shop)
-    
     text = df_result_train_more['text'][0]
     translated = GoogleTranslator(source='auto', target='en').translate(text[:4990])
 
     try:
-        # Load the model and tokenizer if they are not already loaded
+        # Load the model and tokenizer if not already loaded
         if model is None or tokenizer is None:
             from unsloth import FastLanguageModel
-            
-            # Load the model and tokenizer
+
             model, tokenizer = FastLanguageModel.from_pretrained(
-                model_name=peft_model_name,  # YOUR MODEL YOU USED FOR TRAINING
+                model_name=peft_model_name,
                 max_seq_length=max_seq_length,
                 dtype=dtype,
                 load_in_4bit=load_in_4bit,
             )
-            FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
-        
+            FastLanguageModel.for_inference(model)
+
         prompt = f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-    
+
 ### Instruction:
 Categorize the website into one of the 3 categories:
 
@@ -223,21 +146,19 @@ Categorize the website into one of the 3 categories:
 {translated}
 
 ### Response:"""
-        
+
         inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
         outputs = model.generate(**inputs, max_new_tokens=64, use_cache=True)
         ans = tokenizer.batch_decode(outputs)[0]
         ans_pred = ans.split('### Response:')[1].split('<')[0]
-        
+
         if 'OTHER' in ans_pred:
             ans_pred = 'OTHER'
         elif 'NEWS/BLOG' in ans_pred:
             ans_pred = 'NEWS/BLOG'
         elif 'E-commerce' in ans_pred:
             ans_pred = 'E-commerce'
-        # else:
-        #     ans_pred = 'OTHER'
-            
+
         return ans_pred
 
     except Exception as e:
@@ -252,7 +173,6 @@ iface = gr.Interface(
     title="Website Categorization",
     description="Categorize a website into one of the 3 categories: OTHER, NEWS/BLOG, or E-commerce."
 )
-iface.queue()  # <-- Sets up a queue with default parameters
-
-# Launch the interface
+iface.queue()  # Enable queue with default settings
 iface.launch()
+