Exemplar Prompt Hub

#llm #promptengineering #ai #rag

🧠 API for Managing AI Prompts

I developed Exemplar Prompt Hub asto streamline prompt management for my AI applications in production. It centralizes prompt storage, versioning, tagging, and retrieval via a simple REST API—perfect for chatbots, RAG systems, or prompt engineering workflows.

🚀 Core Features

RESTful API for prompt CRUD operations
Version control for prompt evolution
Tag-based organization and metadata support
Powerful search and filtering capabilities
Prompt Playground

🛠️ Quick Start

Prerequisites:

Python 3.8+
PostgreSQL
FastAPI

Clone the repo and follow the README for setup.

📦 Example: Create a Greeting Prompt Template

curl -X POST "http://localhost:8000/api/v1/prompts/" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "greeting-template",
    "text": "Hello {{ name }}! Welcome to {{ platform }}. Your role is {{ role }}.",
    "description": "A greeting template with dynamic variables",
    "meta": {
      "template_variables": ["name", "platform", "role"],
      "author": "test-user"
    },
    "tags": ["template", "greeting"]
  }'

🧩 Rendering Prompts with Jinja2 and usage with LLM (OpenAI)

Fetch the prompt by name or ID, then render it dynamically by injecting variables:

import requests
import jinja2
from jinja2 import Template
from openai import OpenAI

client = OpenAI(api_key="<your-api-key>")

# Fetch the prompt template
response = requests.get("http://localhost:8000/api/v1/prompts/?skip=0&limit=1&search=greeting-template")
prompt_data = response.json()

# Create a Jinja template
template = Template(prompt_data[0]["text"])

# Render with variables
rendered_prompt = template.render(
    name="John",
    platform="Exemplar Prompt Hub",
    role="Developer",
    department="Engineering"
)
print("\nRendered Prompt:")
print(rendered_prompt)
# Use the new OpenAI client format
completion = client.chat.completions.create(
    model="o1-mini",
    messages=[
        {
            "role": "user",
            "content": rendered_prompt
        }
    ]
)

print("\nGenerated Response:")
print(completion.choices[0].message.content)

Output

Rendered Prompt:
Hello John! Welcome to Exemplar Prompt Hub. Your role is Developer.

Generated Response:
Hello! Thank you for the warm welcome. I’m John, the Developer at Exemplar Prompt Hub. I’m here to help you with any development needs or questions you might have. How can I assist you today?

Refer the Example Here!

This enables seamless integration of your prompt management service with downstream AI models.

Try Playground API via OpenRouter.ai