https://github.com/gerinsp/faq-chatbot
An experimental FAQ chatbot for customer service, built with LangChain and Streamlit to provide automated responses efficiently.
https://github.com/gerinsp/faq-chatbot
chatbot gemini-api huggingface-spaces langchain rag streamlit vector-database
Last synced: about 2 months ago
JSON representation
An experimental FAQ chatbot for customer service, built with LangChain and Streamlit to provide automated responses efficiently.
- Host: GitHub
- URL: https://github.com/gerinsp/faq-chatbot
- Owner: gerinsp
- Created: 2025-02-09T14:00:38.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-03-01T21:24:51.000Z (3 months ago)
- Last Synced: 2025-03-01T22:23:47.420Z (3 months ago)
- Topics: chatbot, gemini-api, huggingface-spaces, langchain, rag, streamlit, vector-database
- Language: Python
- Homepage: https://huggingface.co/spaces/gerinsp/faq-chatbot
- Size: 18.6 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
---
title: FAQ Chatbot
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: streamlit
sdk_version: 1.42.0
app_file: app.py
pinned: false
license: apache-2.0
---
# Chatbot FAQ dengan RAG
## 🚀 Fitur Utama
- Menggunakan **LangChain + Vector Database (FAISS)**
- Menjalankan **chatbot secara lokal dengan Streamlit**
- Evaluasi performa menggunakan **Confusion Matrix, Accuracy, Precision, Recall, F1-score**
---
## 🔧 Instalasi
```bash
git clone https://github.com/username/chatbot-faq.git
cd chatbot-faq
python -m venv env
source env/bin/activate # Linux/macOS
pip install -r requirements.txt
```
---
## 📌 Cara Menjalankan
1. **Persiapkan dataset** di `data/faq.csv`
2. **Jalankan chatbot dengan Streamlit**
```bash
streamlit run app.py
```
---
## 📊 Evaluasi Performa
Jalankan skrip evaluasi chatbot:
```bash
python src/evaluation.py
```
---
## 📂 Struktur Proyek
```plaintext
chatbot-faq/
│── data/ # Dataset FAQ
│── models/ # Model (jika diperlukan)
│── src/ # Kode utama chatbot
│── app.py # UI Streamlit
│── requirements.txt # Dependensi proyek
│── README.md # Dokumentasi proyek
```
---
## 📌 Teknologi yang Digunakan
- **LangChain** → pipeline NLP.
- **FAISS** → vector database untuk pencarian cepat.
- **Streamlit** → antarmuka chatbot.
- **Scikit-Learn** → evaluasi chatbot.
---
## 🎯 Kesimpulan
Chatbot FAQ berbasis **RAG + LangChain** ini bisa digunakan untuk customer support dan hanya menjawab berdasarkan **dataset CSV** yang diberikan. Sistem ini cocok untuk otomatisasi layanan pelanggan yang efisien.