Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/abbes-larbaoui/llm-spring-hilla
This project is a fullstack AI chat application that integrates a backend powered by Spring AI with the Ollama model and a frontend developed using the Hilla framework. Both the frontend and backend are hosted on the same server, providing a unified and seamless user experience.
https://github.com/abbes-larbaoui/llm-spring-hilla
ai hilla ollama reactive spring spring-ai
Last synced: about 7 hours ago
JSON representation
This project is a fullstack AI chat application that integrates a backend powered by Spring AI with the Ollama model and a frontend developed using the Hilla framework. Both the frontend and backend are hosted on the same server, providing a unified and seamless user experience.
- Host: GitHub
- URL: https://github.com/abbes-larbaoui/llm-spring-hilla
- Owner: abbes-larbaoui
- Created: 2024-08-03T09:42:27.000Z (about 2 months ago)
- Default Branch: master
- Last Pushed: 2024-08-03T13:42:17.000Z (about 2 months ago)
- Last Synced: 2024-09-22T19:02:20.890Z (5 days ago)
- Topics: ai, hilla, ollama, reactive, spring, spring-ai
- Language: TypeScript
- Homepage:
- Size: 6.84 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# Fullstack AI Chat Application
## Overview
This project is a fullstack AI chat application that integrates a backend powered by Spring AI with the Ollama model and a frontend developed using the Hilla framework. Both the frontend and backend are hosted on the same server, providing a unified and seamless user experience.
## Features
- **AI-Powered Chat**: Uses the Ollama model via Spring AI to deliver intelligent and context-aware chat responses.
- **Integrated Frontend and Backend**: Built with the Hilla framework, ensuring a cohesive application where both components operate on the same server.
- **Responsive Interface**: Offers an interactive and modern chat experience within the web application.
## Technologies
- **Java 17**: The application is developed using Java 17.
- **Spring AI**: Framework for integrating AI models into Java applications.
- **Ollama Model**: Advanced AI model for generating chat responses.
- **Hilla Framework**: Combines Vaadin and Spring Boot for a unified fullstack solution.
- **Docker Compose**: Used for managing and running the Ollama container.
## Getting Started
### Prerequisites
- JDK 17
- Maven
- Docker and Docker Compose
### Installation
1. **Clone the Repository:**
```bash
git clone https://github.com/abbes-larbaoui/llm-spring-hilla.git
cd llm-spring-hilla
```
2. **Run the Docker Compose File:**
- Navigate to the directory containing the `docker-compose.yml` file.
- Start the Ollama container:
```bash
docker-compose up -d
```
3. **Run the Llama2 Model:**
- Start the Llama2 model within the Ollama container using::
```bash
docker exec -it ollama ollama run llama2
```
4. **Build and Run the Application:**
- Navigate to the project root directory.
- Install dependencies and build the application with Maven:
```bash
mvn clean install
```
- Run the Spring Boot application, which will start both the backend and frontend:
```bash
mvn spring-boot:run
```
5. **Access the Application:**
- Open your web browser and go to `http://localhost:8080` to interact with the chat application.
### Usage
- **Chat Interface:** Use the integrated chat interface to interact with the AI model.
- **Configuration:** Modify AI model parameters and other settings in the `src/main/resources/application.yml` file.