-
Notifications
You must be signed in to change notification settings - Fork 1
Getting Started
Abid Ali Awan edited this page Dec 2, 2025
·
1 revision
This guide will walk you through installing, configuring, and using ECom Intel to analyze product reviews.
Before you begin, ensure you have:
- Python 3.8+ installed
- pip (Python package manager)
- API keys for OpenAI and Firecrawl
git clone https://github.com/kingabzpro/ECom-Intel.git
cd ECom-Intelpip install -r requirements.txtThe following packages will be installed:
| Package | Purpose |
|---|---|
streamlit |
Web dashboard framework |
openai |
OpenAI API client for AI analysis |
firecrawl-py |
Web scraping API client |
pandas |
Data manipulation |
plotly |
Interactive charts |
python-dotenv |
Environment variable management |
requests |
HTTP requests |
cp .env.example .envEdit the .env file and add your API keys:
# OpenAI API Key
OPENAI_API_KEY=sk-your-openai-key-here
# Firecrawl API Key
FIRECRAWL_API_KEY=fc-your-firecrawl-key-here
# Database path (optional, defaults to reviews.db)
DATABASE_PATH=reviews.db- Visit platform.openai.com/api-keys
- Sign in or create an account
- Click "Create new secret key"
- Copy the key and add it to your
.envfile
Note: ECom Intel uses the
gpt-4o-minimodel, which is cost-effective and fast.
- Visit firecrawl.dev
- Sign up for an account
- Navigate to API settings
- Copy your API key and add it to your
.envfile
streamlit run app.pyThe application will start and open in your default browser at http://localhost:8501.
-
Enter a Product URL in the sidebar
- Supported formats: Amazon, eBay, or other e-commerce product pages
-
Adjust Settings (optional)
- Max review pages: Slider to control how many pages to scrape (1-10)
- Use cached results: Toggle to use previously stored results
-
Click "Analyze Reviews" and watch the progress:
- 🔍 Searching for reviews...
- 📥 Scraping review content...
- 🧠 Analyzing reviews with AI...
- 💾 Saving results...
-
View Results:
- Key metrics (total reviews, average rating, sentiment percentages)
- Sentiment distribution pie chart
- Rating distribution bar chart
- Key insights and recommendations
- Pros and cons summary
- Sample reviews with sentiment labels
| Tip | Description |
|---|---|
| 🔗 Use direct product URLs | More accurate results with specific product pages |
| ⭐ Popular products | Products with more reviews provide better insights |
| 💾 Check cached results | Save API credits by using stored data |
| 📊 Adjust max pages | More pages = more reviews but longer processing time |
| ⏳ Allow sufficient time | Comprehensive analysis may take 1-2 minutes |
- ✅ Ensure
.envfile exists in the project root - ✅ Verify API keys are correctly formatted
- ✅ Check that API keys are active and valid
- ✅ Try a different product URL
- ✅ Verify the product has reviews available
- ✅ Increase the max pages setting in the sidebar
- ✅ Verify Firecrawl API key is valid
- ✅ Check your internet connection
- ✅ Some websites may block scraping attempts
- ✅ Verify OpenAI API key and available credits
- ✅ Check if the
gpt-4o-minimodel is accessible - ✅ Try again with fewer reviews (reduce max pages)
| Metric | Description |
|---|---|
| Total Reviews | Number of reviews analyzed |
| Average Rating | Mean rating across all reviews (1-5 scale) |
| Positive Sentiment | Percentage of positive reviews |
| Negative Sentiment | Percentage of negative reviews |
- Sentiment Distribution: Pie chart showing positive/negative/neutral breakdown
- Rating Distribution: Bar chart showing 1-5 star distribution
- Key Insights: AI-generated observations about the product
- What Customers Love: Most praised features (Pros)
- Common Complaints: Frequent issues mentioned (Cons)
- Recommendations: Actionable suggestions based on reviews
View history of previously analyzed products with their ratings and review counts.
Contributions are welcome! To contribute:
- Fork the project
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Next: Architecture-and-Tools - Learn about the technical architecture