Spaces:
Runtime error
Runtime error
Upload tool
Browse files- app.py +4 -65
- requirements.txt +3 -11
- tool.py +43 -114
app.py
CHANGED
@@ -1,67 +1,6 @@
|
|
|
|
|
|
1 |
|
2 |
-
|
3 |
-
from smolagents import load_tool
|
4 |
|
5 |
-
|
6 |
-
web_analyzer = load_tool("MHamdan/web-analyzer", trust_remote_code=True)
|
7 |
-
|
8 |
-
def analyze_content(url, mode):
|
9 |
-
return web_analyzer(url, mode)
|
10 |
-
|
11 |
-
def create_interface():
|
12 |
-
with gr.Blocks(title="AI Web Analyzer") as iface:
|
13 |
-
gr.Markdown("# π€ AI-Powered Web Content Analyzer")
|
14 |
-
gr.Markdown("""
|
15 |
-
## Features:
|
16 |
-
- π **Analyze**: Complete content analysis with AI summary
|
17 |
-
- π **Summarize**: AI-generated multi-section summary
|
18 |
-
- π **Sentiment**: Section-by-section sentiment analysis
|
19 |
-
- π― **Topics**: AI topic classification
|
20 |
-
""")
|
21 |
-
|
22 |
-
with gr.Row():
|
23 |
-
with gr.Column():
|
24 |
-
url_input = gr.Textbox(
|
25 |
-
label="Webpage URL",
|
26 |
-
placeholder="Enter URL to analyze..."
|
27 |
-
)
|
28 |
-
mode = gr.Dropdown(
|
29 |
-
choices=["analyze", "summarize", "sentiment", "topics"],
|
30 |
-
label="Analysis Mode",
|
31 |
-
value="analyze"
|
32 |
-
)
|
33 |
-
submit_btn = gr.Button("Analyze Content", variant="primary")
|
34 |
-
|
35 |
-
with gr.Column():
|
36 |
-
output = gr.Textbox(
|
37 |
-
label="AI Analysis Results",
|
38 |
-
lines=15
|
39 |
-
)
|
40 |
-
|
41 |
-
# Example data
|
42 |
-
examples = [
|
43 |
-
["https://www.artificialintelligence-news.com/2024/02/14/openai-anthropic-google-white-house-red-teaming/", "analyze"],
|
44 |
-
["https://www.artificialintelligence-news.com/2024/02/13/ai-21-labs-wordtune-chatgpt-plugin/", "summarize"],
|
45 |
-
["https://www.artificialintelligence-news.com/2024/02/12/google-responds-gemini-ai-historical-images/", "sentiment"],
|
46 |
-
["https://www.artificialintelligence-news.com/2024/02/09/anthropic-claude-3-models-preview/", "topics"]
|
47 |
-
]
|
48 |
-
|
49 |
-
gr.Examples(
|
50 |
-
examples=examples,
|
51 |
-
inputs=[url_input, mode],
|
52 |
-
outputs=output,
|
53 |
-
fn=analyze_content,
|
54 |
-
cache_examples=True
|
55 |
-
)
|
56 |
-
|
57 |
-
submit_btn.click(
|
58 |
-
fn=analyze_content,
|
59 |
-
inputs=[url_input, mode],
|
60 |
-
outputs=output
|
61 |
-
)
|
62 |
-
|
63 |
-
return iface
|
64 |
-
|
65 |
-
# Create and launch the interface
|
66 |
-
demo = create_interface()
|
67 |
-
demo.launch()
|
|
|
1 |
+
from smolagents import launch_gradio_demo
|
2 |
+
from tool import SimpleTool
|
3 |
|
4 |
+
tool = SimpleTool()
|
|
|
5 |
|
6 |
+
launch_gradio_demo(tool)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
requirements.txt
CHANGED
@@ -1,12 +1,4 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
beautifulsoup4>=4.9.3
|
4 |
-
requests>=2.25.1
|
5 |
-
smolagents
|
6 |
transformers
|
7 |
-
|
8 |
-
accelerate
|
9 |
-
sacremoses
|
10 |
-
sentencepiece
|
11 |
-
protobuf
|
12 |
-
scipy
|
|
|
1 |
+
bs4
|
2 |
+
requests
|
|
|
|
|
|
|
3 |
transformers
|
4 |
+
smolagents
|
|
|
|
|
|
|
|
|
|
tool.py
CHANGED
@@ -2,141 +2,70 @@ from smolagents import Tool
|
|
2 |
from typing import Any, Optional
|
3 |
|
4 |
class SimpleTool(Tool):
|
5 |
-
name = "
|
6 |
-
description = "
|
7 |
-
inputs = {"url":{"type":"string","description":"The webpage URL to analyze."}
|
8 |
output_type = "string"
|
9 |
|
10 |
-
def forward(self, url: str
|
11 |
-
"""
|
12 |
|
13 |
Args:
|
14 |
url: The webpage URL to analyze.
|
15 |
-
mode: Analysis mode ('analyze', 'summarize', 'sentiment', 'topics').
|
16 |
|
17 |
Returns:
|
18 |
-
str:
|
19 |
"""
|
20 |
import requests
|
21 |
from bs4 import BeautifulSoup
|
22 |
import re
|
23 |
from transformers import pipeline
|
24 |
-
import
|
25 |
-
|
26 |
-
# Check if GPU is available
|
27 |
-
device = 0 if torch.cuda.is_available() else -1
|
28 |
|
29 |
try:
|
|
|
30 |
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'}
|
31 |
response = requests.get(url, headers=headers, timeout=10)
|
32 |
-
response.raise_for_status()
|
33 |
|
|
|
34 |
soup = BeautifulSoup(response.text, 'html.parser')
|
35 |
-
|
36 |
-
# Remove scripts and styles
|
37 |
for tag in soup(['script', 'style', 'meta']):
|
38 |
tag.decompose()
|
39 |
|
|
|
40 |
title = soup.title.string if soup.title else "No title found"
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
elif mode == "summarize":
|
73 |
-
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
74 |
-
|
75 |
-
# Process in chunks
|
76 |
-
chunk_size = 1024
|
77 |
-
summaries = []
|
78 |
-
|
79 |
-
for i in range(0, min(len(text_content), 3072), chunk_size):
|
80 |
-
chunk = text_content[i:i+chunk_size]
|
81 |
-
if len(chunk) > 100:
|
82 |
-
summary = summarizer(chunk, max_length=100, min_length=30)[0]['summary_text']
|
83 |
-
summaries.append(summary)
|
84 |
-
|
85 |
-
return f"""π Multi-Section Summary
|
86 |
-
|
87 |
-
Title: {title}
|
88 |
-
|
89 |
-
{' '.join(summaries)}"""
|
90 |
-
|
91 |
-
elif mode == "sentiment":
|
92 |
-
classifier = pipeline("text-classification",
|
93 |
-
model="nlptown/bert-base-multilingual-uncased-sentiment")
|
94 |
-
|
95 |
-
# Analyze paragraphs
|
96 |
-
paragraphs = soup.find_all('p')
|
97 |
-
sentiments = ""
|
98 |
-
count = 0
|
99 |
-
|
100 |
-
for p in paragraphs:
|
101 |
-
text = p.text.strip()
|
102 |
-
if len(text) > 50:
|
103 |
-
result = classifier(text[:512])[0]
|
104 |
-
score = int(result['label'][0])
|
105 |
-
mood = ["Very Negative", "Negative", "Neutral", "Positive", "Very Positive"][score-1]
|
106 |
-
sentiments += f"\nSection {count + 1}: {mood} ({score}/5 stars)"
|
107 |
-
count += 1
|
108 |
-
if count >= 5:
|
109 |
-
break
|
110 |
-
|
111 |
-
return f"""π Sentiment Analysis
|
112 |
-
|
113 |
-
Title: {title}
|
114 |
-
{sentiments}"""
|
115 |
-
|
116 |
-
elif mode == "topics":
|
117 |
-
classifier = pipeline("zero-shot-classification",
|
118 |
-
model="facebook/bart-large-mnli")
|
119 |
-
|
120 |
-
topics = [
|
121 |
-
"Technology", "AI/ML", "Business", "Science",
|
122 |
-
"Innovation", "Research", "Industry News"
|
123 |
-
]
|
124 |
-
|
125 |
-
results = classifier(text_content[:512], topics)
|
126 |
-
|
127 |
-
topic_analysis = "Detected Topics:\n"
|
128 |
-
for topic, score in zip(results['labels'], results['scores']):
|
129 |
-
if score > 0.1:
|
130 |
-
topic_analysis += f"- {topic}: {score*100:.1f}% confidence\n"
|
131 |
-
|
132 |
-
return f"""π― Topic Classification
|
133 |
-
|
134 |
-
Title: {title}
|
135 |
-
|
136 |
-
{topic_analysis}"""
|
137 |
-
|
138 |
-
else:
|
139 |
-
return f"Error: Unknown mode '{mode}'"
|
140 |
|
141 |
except Exception as e:
|
142 |
-
return
|
|
|
|
|
|
2 |
from typing import Any, Optional
|
3 |
|
4 |
class SimpleTool(Tool):
|
5 |
+
name = "web_content_analyzer"
|
6 |
+
description = "Analyzes web content using AI models."
|
7 |
+
inputs = {"url":{"type":"string","description":"The webpage URL to analyze."}}
|
8 |
output_type = "string"
|
9 |
|
10 |
+
def forward(self, url: str) -> str:
|
11 |
+
"""Analyzes web content using AI models.
|
12 |
|
13 |
Args:
|
14 |
url: The webpage URL to analyze.
|
|
|
15 |
|
16 |
Returns:
|
17 |
+
str: Analysis results in JSON format.
|
18 |
"""
|
19 |
import requests
|
20 |
from bs4 import BeautifulSoup
|
21 |
import re
|
22 |
from transformers import pipeline
|
23 |
+
import json
|
|
|
|
|
|
|
24 |
|
25 |
try:
|
26 |
+
# Fetch content
|
27 |
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'}
|
28 |
response = requests.get(url, headers=headers, timeout=10)
|
|
|
29 |
|
30 |
+
# Parse HTML
|
31 |
soup = BeautifulSoup(response.text, 'html.parser')
|
|
|
|
|
32 |
for tag in soup(['script', 'style', 'meta']):
|
33 |
tag.decompose()
|
34 |
|
35 |
+
# Extract basic info
|
36 |
title = soup.title.string if soup.title else "No title found"
|
37 |
+
text = re.sub(r'\s+', ' ', soup.get_text()).strip()
|
38 |
+
|
39 |
+
if len(text) < 100:
|
40 |
+
return json.dumps({
|
41 |
+
"error": "Not enough content to analyze"
|
42 |
+
})
|
43 |
+
|
44 |
+
# Get summary
|
45 |
+
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
46 |
+
summary = summarizer(text[:1024], max_length=100, min_length=30)[0]['summary_text']
|
47 |
+
|
48 |
+
# Get sentiment
|
49 |
+
classifier = pipeline("text-classification",
|
50 |
+
model="nlptown/bert-base-multilingual-uncased-sentiment")
|
51 |
+
sentiment = classifier(text[:512])[0]
|
52 |
+
score = int(sentiment['label'][0])
|
53 |
+
mood = ["Very Negative", "Negative", "Neutral", "Positive", "Very Positive"][score-1]
|
54 |
+
|
55 |
+
# Format results
|
56 |
+
result = {
|
57 |
+
"title": title,
|
58 |
+
"summary": summary,
|
59 |
+
"sentiment": f"{mood} ({score}/5)",
|
60 |
+
"stats": {
|
61 |
+
"words": len(text.split()),
|
62 |
+
"chars": len(text)
|
63 |
+
}
|
64 |
+
}
|
65 |
+
|
66 |
+
return json.dumps(result)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
except Exception as e:
|
69 |
+
return json.dumps({
|
70 |
+
"error": str(e)
|
71 |
+
})
|