https://github.com/ksm26/text-generation-service
Text Generation API is a lightweight FastAPI service that leverages Hugging Face Transformers for AI-powered text generation. It supports RESTful API requests, is Dockerized for easy deployment, and runs locally or in containers.
https://github.com/ksm26/text-generation-service
Last synced: 6 months ago
JSON representation
Text Generation API is a lightweight FastAPI service that leverages Hugging Face Transformers for AI-powered text generation. It supports RESTful API requests, is Dockerized for easy deployment, and runs locally or in containers.
- Host: GitHub
- URL: https://github.com/ksm26/text-generation-service
- Owner: ksm26
- Created: 2025-03-31T20:47:53.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-03-31T21:11:46.000Z (6 months ago)
- Last Synced: 2025-03-31T22:23:33.056Z (6 months ago)
- Language: Python
- Homepage: https://github.com/ksm26/text-generation-service
- Size: 3.91 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 📝 Text Generation API
A simple text generation service that uses a pretrained LLM (Hugging Face Transformers model).
This API takes a short prompt as input and returns a generated text passage.
---
## 🚀 Features
✅ **Pretrained LLM**: Uses an open-source model from Hugging Face. \
✅ **REST API**: Accepts a prompt and returns generated text. \
✅ **Dockerized**: Runs in a container for easy deployment. \
✅ **FastAPI Framework**: Provides a lightweight and efficient backend.
---
## 📂 Project Structure
text_generation_service/ \
│── backend/ # FastAPI backend
│ ├── main.py # API implementation
│ ├── model.py # LLM loading & inference
│ ├── requirements.txt # Backend dependencies
│── Dockerfile # Docker container setup
│── README.md # Documentation
---
## 🛠️ Tech Stack
| Component | Technology Used |
|------------|----------------|
| **Backend** | FastAPI, Transformers (Hugging Face) |
| **Containerization** | Docker |
| **Model** | GPT-2 (or any Hugging Face model) |
---
## 🚀 Setup Instructions
### **1️⃣ Clone the Repository**
```sh
git clone https://github.com/your-username/text_generation_service.git
cd text_generation_service
```
### **2️⃣ Install Dependencies**
```sh
cd backend
pip install -r requirements.txt
```
### **3️⃣ Run the API Locally**
```sh
uvicorn main:app --host 0.0.0.0 --port 8000
```
### **4️⃣ Start the Backend**
The API will be available at: http://localhost:8000
## 🐳 Docker Deployment
### 1️⃣ Build the Docker Image
```sh
docker build -t text-generation-service .
```
### 2️⃣ Run the Docker Container
```sh
docker run -p 8080:8000 text-generation-service
```
The API will be available at: http://localhost:8080
## 🌍 Usage
### Submit a Prompt
```sh
curl -X POST "http://127.0.0.1:8080/generate" \
-H "Content-Type: application/json" \
-d '{"prompt": "Once upon a time,"}'
```
### 📌 Expected Response:
```sh
{"generated_text": "Once upon a time, in a distant kingdom..."}
```