https://github.com/deepak786/faq-chatbot
A streamlit-based chatbot that answers questions based on a FAQ database using LangChain and Ollama for local LLM inference.
https://github.com/deepak786/faq-chatbot
chatbot langchain ollama rag streamlit
Last synced: 3 months ago
JSON representation
A streamlit-based chatbot that answers questions based on a FAQ database using LangChain and Ollama for local LLM inference.
- Host: GitHub
- URL: https://github.com/deepak786/faq-chatbot
- Owner: deepak786
- Created: 2025-05-23T11:40:38.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-27T15:17:48.000Z (about 1 year ago)
- Last Synced: 2026-04-07T07:46:20.421Z (3 months ago)
- Topics: chatbot, langchain, ollama, rag, streamlit
- Language: Python
- Homepage: https://deepakdroid.medium.com/build-a-local-faq-chatbot-with-rag-streamlit-ollama-bc42b9400eee
- Size: 5.86 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# FAQ Chatbot
A streamlit-based chatbot that answers questions based on a FAQ database using LangChain and Ollama for local LLM inference.
## Features
- 🤖 Local LLM inference using Ollama
- 💾 Persistent vector storage using Chroma
- 🔍 Semantic search for finding relevant answers
- 🌐 Interactive web interface using Streamlit
- 💬 Chat history with expandable Q&A pairs
## Prerequisites
- Python 3.8 or higher
- [Ollama](https://ollama.com/) installed on your machine with the following models:
- `llama3.2` - for generating responses
- `nomic-embed-text` - for text embeddings
### Installing Ollama Models
After installing Ollama, run these commands to pull the required models:
```bash
ollama pull llama3.2
ollama pull nomic-embed-text
```
## Setup
1. Clone the repository:
```bash
git clone https://github.com/deepak786/faq-chatbot.git
cd faq_chatbot
```
2. Create a virtual environment and activate it:
```bash
python3 -m venv .venv
source .venv/bin/activate # On Windows, use `.venv\Scripts\activate`
```
3. Install the required packages:
```bash
pip install -r requirements.txt
```
## Running the Application
1. Make sure Ollama is running on your machine:
```bash
ollama serve
```
2. In a new terminal, start the Streamlit application:
```bash
streamlit run faq_chatbot.py
```