It allows users to search for frequently asked questions (FAQs) using a multilingual sentence transformer model to find the most relevant FAQ question and its corresponding answer based on the user query.
This project is done as a part of Human Language Technologies elective course.
Many companies often receive a large number of similar questions from their clients. Manually answering these questions can be time-consuming and inefficient. Similarly, it can be time-consuming for users to search through a long list of FAQs. Therefore, there is a need for an automated system that can quickly provide relevant answers to user queries.
This project provides a solution by building a web application that utilizes a sentence transformer model to understand the semantic similarity between user queries and FAQ questions. By encoding both the user query and FAQ questions into high-dimensional embeddings, the model can efficiently compute similarity scores and retrieve the most relevant FAQ.
- Clone the repository to your local machine:
git clone https://github.com/your-username/faq-search-web-app.git
cd faq-search-web-app- Install the required Python dependencies:
pip install -r requirements.txt- Start the FastAPI backend server:
uvicorn main:app --reload- Open the frontend React app in a separate terminal:
cd frontend
npm install
npm start- Open your web browser and navigate to http://localhost:3000 to access the FAQ search web app.