https://github.com/renaldiangsar/customer-support-rag
Customer Support Chatbot that answer all your question about what your purchase. The Chatbot is build with Langchain, chromaDB, Groq, HuggingFace, Streamlit, and etc.
https://github.com/renaldiangsar/customer-support-rag
customer-support-ai langchain langchain-python large-language-model rag-chatbot streamlit
Last synced: 2 months ago
JSON representation
Customer Support Chatbot that answer all your question about what your purchase. The Chatbot is build with Langchain, chromaDB, Groq, HuggingFace, Streamlit, and etc.
- Host: GitHub
- URL: https://github.com/renaldiangsar/customer-support-rag
- Owner: renaldiangsar
- Created: 2025-03-27T06:58:58.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2025-03-27T07:32:15.000Z (about 1 year ago)
- Last Synced: 2025-03-27T08:30:24.724Z (about 1 year ago)
- Topics: customer-support-ai, langchain, langchain-python, large-language-model, rag-chatbot, streamlit
- Language: Python
- Homepage:
- Size: 373 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RAG Customer Support Chatbot
## 📌 Overview
This project is a **Customer Support RAG Chatbot that can be accessed through streamlit web applications.**
Users can **Ask questions** about products, the purchase process, returning goods, etc. **Questioning everything** that related to the **system of purchase**. And the added value is Chatbot **remember previous Conversation**.
## 🚀 Features
- **PDF-based Knowledge Base**: Extracts relevant information from uploaded PDFs.
- **RAG Architecture**: Combines retrieval and generation for better responses.
- **Conversational Memory**: Stores chat history using LangChain memory in ChromaDB, allowing the chatbot to remember previous interactions.
- Uses **LangChain**, **Hugging Face embeddings**, and **ChromaDB** for retrieval.
- Frontend built with **Streamlit** for a smooth user experience.
---
## 🛠️ Tech Stack
- **Chatbot RAG:** LangChain, Groq API, ChromaDB, Hugging Face embeddings
- **Frontend:** Streamlit
- **PDF Processing:** PyPDFLoader
---
## 🏗️ Installation & Setup
### **Clone the Repository**
```sh
git clone https://github.com/renaldiangsar/Customer-Support-RAG.git
cd Customer-Support-RAG
```
### **Create a Virtual Environment & Install Dependencies**
```sh
# open command prompt and run
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
```
### **Run the Streamlit**
```sh
# open command prompt and run
streamlit run app.py
```
> The Streamlit app will open in your browser at `http://localhost:8501`
### Don't forget to give your api in .env file
- open .env file an set your groq and huggingface api
## 🛠️ Customization & Improvements
- Use a **different LLM model** (e.g., GPT-4, LLaMA, or local models) for customization.
- Improved response generation using fine-tuned models.
---
## 📝 Future Enhancements
- Add **multilingual support** for Conversation.
- Support **multiple type file**, not just pdf format. Try file.txt with many Question Answer
---
## Visual
---
I hope i can do better in my next project. 🎉