File size: 5,869 Bytes
e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 f9b0ae0 e8af220 3ba76f6 e8af220 883071c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 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 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 |
import requests
from bs4 import BeautifulSoup
import pandas as pd
import gradio as gr
import os
from groq import Groq
import creds # Ensure creds.py contains `api_key` as `creds.api_key`
# Step 1: Scrape free courses from Analytics Vidhya
def scrape_courses():
url = "https://courses.analyticsvidhya.com/pages/all-free-courses"
response = requests.get(url)
soup = BeautifulSoup(response.content, 'html.parser')
courses = []
for course_card in soup.find_all('header', class_='course-card__img-container'):
img_tag = course_card.find('img', class_='course-card__img')
if img_tag:
title = img_tag.get('alt')
image_url = img_tag.get('src')
link_tag = course_card.find_previous('a')
if link_tag:
course_link = link_tag.get('href')
if not course_link.startswith('http'):
course_link = 'https://courses.analyticsvidhya.com' + course_link
courses.append({
'title': title,
'image_url': image_url,
'course_link': course_link
})
return pd.DataFrame(courses)
# Initialize course DataFrame
df = scrape_courses()
# Step 2: Initialize the Groq client and set the API key
client = Groq(api_key=creds.api_key)
def search_courses(query):
try:
print(f"Searching for: {query}")
prompt = f"""Given the query: "{query}"
Rank the following courses based on relevance to the query, prioritizing Analytics Vidhya courses.
Provide a relevance score (0-1) for each course, returning only those with a score >= 0.5.
Courses:
{df['title'].to_string(index=False)}
"""
response = client.chat.completions.create(
model="mixtral-8x7b-32768",
messages=[{"role": "system", "content": "You are an AI assistant specialized in course recommendations."},
{"role": "user", "content": prompt}],
temperature=0.2,
max_tokens=1000
)
results = []
for line in response.choices[0].message.content.split('\n'):
if line.startswith('Title:'):
title = line.split('Title:')[1].strip()
elif line.startswith('Relevance:'):
relevance = float(line.split('Relevance:')[1].strip())
if relevance >= 0.5:
matching_courses = df[df['title'] == title]
if not matching_courses.empty:
course = matching_courses.iloc[0]
results.append({
'title': title,
'image_url': course['image_url'],
'course_link': course['course_link'],
'score': relevance
})
return sorted(results, key=lambda x: x['score'], reverse=True)[:10] # Return top 10 results
except Exception as e:
print(f"An error occurred in search_courses: {str(e)}")
return []
def gradio_search(query):
result_list = search_courses(query)
if result_list:
html_output = '<div class="results-container">'
for item in result_list:
course_title = item['title']
course_image = item['image_url']
course_link = item['course_link']
relevance_score = round(item['score'] * 100, 2)
html_output += f'''
<div class="course-card">
<img src="{course_image}" alt="{course_title}" class="course-image"/>
<div class="course-info">
<h3>{course_title}</h3>
<p>Relevance: {relevance_score}%</p>
<a href="{course_link}" target="_blank" class="course-link">View Course</a>
</div>
</div>'''
html_output += '</div>'
return html_output
else:
return '<p class="no-results">No results found. Please try a different query.</p>'
# Custom CSS for the Gradio interface
custom_css = """
body { font-family: Arial, sans-serif; background-color: #f0f2f5; }
h1, h2, p, .container .examples { color: #333; }
.container { max-width: 800px; margin: 0 auto; padding: 20px; }
.results-container { display: flex; flex-wrap: wrap; justify-content: space-between; }
.course-card { background-color: white; border-radius: 8px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1); margin-bottom: 20px; overflow: hidden; width: 48%; transition: transform 0.2s; }
.course-card:hover { transform: translateY(-5px); }
.course-image { width: 100%; height: 150px; object-fit: cover; }
.course-info { padding: 15px; }
.course-info h3 { margin-top: 0; font-size: 18px; color: #333; }
.course-info p { color: #666; font-size: 14px; margin-bottom: 10px; }
.course-link { display: inline-block; background-color: #007bff; color: white; padding: 8px 12px; text-decoration: none; border-radius: 4px; font-size: 14px; transition: background-color 0.2s; }
.course-link:hover { background-color: #0056b3; }
.no-results { text-align: center; color: #666; font-style: italic; }
"""
# Gradio interface
iface = gr.Interface(
fn=gradio_search,
inputs=gr.Textbox(label="Enter your search query", placeholder="e.g., machine learning, data science, python"),
outputs=gr.HTML(label="Search Results"),
title="Analytics Vidhya Smart Course Search",
description="Find the most relevant courses from Analytics Vidhya based on your query.",
theme="huggingface",
css=custom_css,
examples=[
["machine learning for beginners"],
["advanced data visualization techniques"],
["python programming basics"],
["Business Analytics"]
],
)
if __name__ == "__main__":
iface.launch() |