https://github.com/ualusham/amazon_ai_assisted_faq
This chatbot helps customers to get AI assistance while using Amazon. The information is based on the Frequently Asked Questions (FAQ) provided by Amazon. This project is based on the concept of Retrieval Augmented Generation (RAG).
https://github.com/ualusham/amazon_ai_assisted_faq
ai amazon langchain llm rag streamlit
Last synced: about 2 months ago
JSON representation
This chatbot helps customers to get AI assistance while using Amazon. The information is based on the Frequently Asked Questions (FAQ) provided by Amazon. This project is based on the concept of Retrieval Augmented Generation (RAG).
- Host: GitHub
- URL: https://github.com/ualusham/amazon_ai_assisted_faq
- Owner: ualUsham
- Created: 2024-12-07T21:24:42.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-04-07T19:57:24.000Z (about 1 year ago)
- Last Synced: 2025-10-13T04:36:36.267Z (8 months ago)
- Topics: ai, amazon, langchain, llm, rag, streamlit
- Language: Python
- Homepage: https://amazonaiassistedfaq.streamlit.app/
- Size: 676 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Amazon AI-Assisted FAQ Chatbot
This repository contains the code for an AI-powered FAQ chatbot designed for Amazon customers. It uses **Retrieval-Augmented Generation (RAG)** techniques to assist users with queries based on Amazon FAQs.
---
## 🌐 Access the App
👉 **To use the app, go to the link:** [Amazon AI-Assisted FAQ Chatbot](https://amazonaiassistedfaq.streamlit.app/)
---
## 🚀 Implementation Instructions
Follow these steps to run the project locally:
### Requirements
Install the necessary dependencies:
```cmd
pip install -r requirements.txt
```
###**Suggested to use a virtual environment**
📂 **Code Files**
app.py: main python file of the project.
streamlit_code.py: Contains the code for the Streamlit-based UI.
helper_code.py: Implements RAG using LLM, LangChain, embeddings, and the vector database.
🛠 **Tools Used**
LLM: Google’s “Gemini-1.5-Flash”
Embeddings: HuggingFace Instructor Embeddings
Vector Database & Retrieval: FAISS
Integration: LangChain
UI & Deployment: Streamlit