Update app.py

app.py

@@ -1,9 +1,8 @@
 import os
 import requests
-from bs4 import BeautifulSoup
 
 api_token = os.environ.get("TOKEN")
-API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-2-7b-chat-hf"
 headers = {"Authorization": f"Bearer {api_token}"}
 
 def query(payload):
@@ -32,34 +31,27 @@ user
 assistant
 '''
     })
-    
+
     print("API Response:", output)  # Print the full API response
 
-    # Extract the generated text
-    generated_text = output.get('generated_text', '')
-    print("Generated Text:", generated_text)  # Print the generated text
+    if isinstance(output, list) and len(output) > 0:
+        generated_text = output[0].get('generated_text', '')
+        print("Generated Text:", generated_text)  # Print the generated text
 
-    # Extract the first non-empty line as the category
-    lines = [line.strip().lower() for line in generated_text.split('\n') if line.strip()]
-    if lines:
-        return lines[0]
+        # Extract the first non-empty line as the category
+        lines = [line.strip().lower() for line in generated_text.split('\n') if line.strip()]
+        if lines:
+            return lines[0]
     return "unknown"
 
-# Fetch a single post
-url = 'https://huggingface.co/posts'
-response = requests.get(url)
-
-if response.status_code == 200:
-    soup = BeautifulSoup(response.content, 'html.parser')
-    pl7_element = soup.find(class_='pl-7')
-    if pl7_element:
-        pl7_text = pl7_element.text.strip()
-        print("Post content:")
-        print(pl7_text)
-        print("\nAnalyzing sentiment...")
-        sentiment = analyze_sentiment(pl7_text)
-        print(f"\nSentiment category: {sentiment}")
-    else:
-        print("No post found with class 'pl-7'")
-else:
-    print(f"Error {response.status_code} when retrieving {url}")
+# Entrée personnalisée pour le test
+custom_post_content = """
+This is a sample post about fine-tuning models for specific tasks. 
+It discusses various techniques and best practices for adjusting models.
+"""
+
+print("Post content:")
+print(custom_post_content)
+print("\nAnalyzing sentiment...")
+sentiment = analyze_sentiment(custom_post_content)
+print(f"\nSentiment category: {sentiment}")