Google Reviews Analyzer

Introduction

It gather the reviews of businesses using SerpApi. And then structure the data to feed into OpenAI LLM with the use of Langchain LLM framework. With custom prompting, we produce the result as below.

Example Reults

Sample analysis

1. Food Quality (👍): ⭐⭐⭐⭐⭐
2. Service (👍): ⭐⭐⭐⭐
3. Cleanliness (👎): ⭐⭐
4. Price (👍): ⭐⭐⭐⭐
5. Taste (👍): ⭐⭐⭐⭐⭐
6. Portions (👍): ⭐⭐⭐⭐
7. Variety (👍): ⭐⭐⭐
8. Atmosphere (👍): ⭐⭐⭐⭐
9. Value (👍): ⭐⭐⭐⭐
10. Parking (👍): ⭐⭐⭐

Launch it with Vercel

or run it locally

Prerequisite

Before running the application, we have to get the necessary API key:

1. Duplicate the file .env.example and rename it to .env
2. We need 2 API keys from SerpApi and OpenAI for SERPAPI_KEY and OPENAI_API_KEY respectively.

Installation

First, install the dependencies

npm install

Run the development server:

npm run dev

Open http://localhost:3000 with your browser to see the result.

Building Blocks

• Next.JS - React framework for the web application
• Langchain - Framework for the LLM
• OpenAI - LLM provider
• SerpApi - Data provider for the businesses reviews on Google. Related documentations: Google Maps API and Google Maps Reviews API.

Future Improvements

Quick analysis is fine, it helps you to understand the review as quick and intuitive as possible. But what if you can chat with it? Sort of like interviewing your customers. I believe we can get more in depth understanding out of it.