This is a submission for the Bright Data AI Web Access Hackathon
🔥 What I Built
OpinionFlow helps users skip the endless scroll. It's an AI-powered review assistant that:
- Crawls live product reviews from Amazon and Walmart using Bright Data MCP
- Summarizes insights using Gemini Flash
- Caches results semantically using Pinecone
- Lets users ask product-specific questions via LangChain
Want to know if the AirPods Pro have battery issues? Just ask — you’ll get instant, evidence-backed answers.
📌 Demo
- 🌐 Live App
- 💻 GitHub Repo
- 🎥 Loom Demo
🧠 How It Works
| Step | Description |
|---|---|
| 🔍 Search | Users enter a query (e.g., "Noise Buds X Prime") |
| 📄 Crawl | Bright Data scrapes live reviews from both stores |
| ✨ Summarize | Gemini Flash extracts sentiment, pros/cons, and key specs |
| 🧠 Cache | MiniLM embeddings stored in Pinecone to avoid repetition |
| 💬 Answer | LangChain generates natural-language responses with citations |
🧩 Features at a Glance
| Feature | Description |
|---|---|
| 💬 Instant AI Answer Box | Summary with links to real reviews |
| 👍 Top Pros / Cons | Highlighted from verified buyers |
| 📊 Sentiment Comparison | Side-by-side scores from Amazon & Walmart |
| 🏷️ Aspect Mini-Charts | Dynamic breakdowns: battery, comfort, etc. |
| 🧭 Multi-Store Tabs | Compare similar SKUs across platforms |
| 🔎 Review Explorer | Drill down into sources and keywords |
🚀 Bright Data in Action
| MCP Tool | Role |
|---|---|
| SERP API | Fetches product listings via Google Search |
| Web Unlocker | Unblocks product pages seamlessly |
| Scraping Browser | Renders full review sections |
| Browser API + Playwright | Handles dynamic navigation like "See all reviews" |
Bright Data saved me dozens of hours — no captchas, no proxy headaches, just clean data.
🧠 Architecture Overview
OpinionFlow is built with a modular microservice-style architecture with FastAPI as the core backend. Key flows include:
- Product discovery → via Bright Data SERP API
- Review scraping → using custom extractors
- Analysis → powered by Gemini Flash
- Semantic caching → via Pinecone vector search
- Natural Q&A → powered by LangChain and Gemini
🧰 Tech Stack
FastAPI, React.js, Bright Data MCP, Gemini Flash, Pinecone, LangChain, HuggingFace MiniLM, Netlify, Cloud Run
🔮 What's Next
- Add Target.com integration
- Launch a real-time price tracker
- Let users add their own reviews
- Enable Gemini-powered follow-ups in chat
🙏 Thanks
Big thanks to Bright Data and DEV for the challenge. If you liked this project, consider checking out:
🌟 github.com/luminati-io/brightdata-mcp
Built with ❤️ by @shivanshsinghh
🏷️ Tags
#BrightData #Hackathon #AI #LLM #Gemini #LangChain #Ecommerce #ProductReviews #FastAPI #React #Pinecone #SemanticSearch
Top comments (77)
Super cool seeing live reviews merged with quick AI insights like this. Any plans to add more stores or deeper personalization next?
Thank you so much for your comment. Yes I am thinking to add more stores and do deeper personalizations in this project. This project really resonates with me.
Good work
Thank you
Great work shivansh, thanks for sharing this
Really appreciate that - it was a fun challenge putting all together.
Great work as always!!
Thanks for always showing up and supporting. Means a lot!
Thanks for sharing this sir!
Very great work❣️
Top-notch work! Sir
pretty cool seeing tools get tied together like this - makes me curious, you think momentum on stuff like this depends more on habits or just chasing little wins day by day?
Thanks! Honestly, I think it's a mix of both - I definitely chase small wins to stay motivated, but a lot of it also just comes from long-term habits. I've been coding since I was a kid, so some of that momentum is just muscle memory at this point.
Honestly didn’t think something like this could be built in a hackathon timeframe. Hats off!
Fabulous this is! Such a life saver. Good work!
Thank you so much! Glad to hear it's helpful to you. Let me know if you try it out!
This is such a cool use of Ai and web scrapping.. something like this can save so much time and efforts of users. Great stuff man!
I'm glad you liked it! Thanks for commenting.
Some comments have been hidden by the post's author - find out more