LLM-Chatbot

KO | EN

gitlite — search

#python #java #python3 #arduino #golang #machine-learning #rust #html #flask #javascript #seismology #nodejs

★ 12 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

LLM Chatbot

A simple LLM-powered chatbot that demonstrates how a backend application can interact with a large language model (LLM) to generate text-based responses.
Users can submit prompts, receive AI-generated replies, and continue conversations through follow-up inputs.

Features

Prompt-based text generation

Conversational follow-up support

Local LLM inference using Ollama

Easy local setup and testing

Prerequisites

Make sure you have the following installed:

Git

A supported runtime environment (based on your project setup)

Ollama

Getting Started
1. Set Up Ollama

Start the Ollama server:

ollama serve

The server will listen on port 11434.

In a separate terminal, download the required language model:

ollama run llama3.1:8b

This downloads an 8B parameter model (~4GB).
Once the model loads, you can stop the process. This step is only required once.

2. Clone the Repository
git clone <repository-url>
cd <project-directory>

3. Install Dependencies

Install project dependencies according to the project stack:

npm install

4. Run the Application

Start the development server:

npm run dev

Once running, interact with the chatbot through the provided interface or API.

Usage

Enter a prompt into the chatbot interface.

Receive an AI-generated response.

Submit follow-up prompts to continue the conversation.

Security Notes

This project is intended for learning and experimentation.
For production use, ensure you implement:

Proper input validation

Secure handling of environment variables

Rate limiting and access controls

LLM-Chatbot

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README