CloudCents LLM 🤖
This project integrates a custom Model, CloudCents LLM 🤖, optimized for cloud computing insights, including AWS, Azure, Google Cloud, and more. This includes a RAG (Retrieval-Augmented Generation) implementation from thousands of scraped cloud articles along with real-time pricing feeds. This Beta phase focuses on document relevance in the RAG and optimized data structures.
Beta Features
- Powered by a Custom Cloud-Specific LLM
- Enhanced RAG implementation for accurate and relevant responses for cloud environments
- Supports multi-cloud environments including AWS, Azure, Google Cloud, Linode, Digital Ocean
Python Code Example 🐍
import requests
API_URL = "https://cloudcents.ai/api/llm"
API_KEY = "your_api_key_here"
response = requests.post(
API_URL,
json={"query": "What is the best cloud service for hosting a database?"},
headers={"Authorization": f"Bearer {API_KEY}"}
)
if response.status_code == 200:
result = response.json()
print("LLM Response:", result['answer'])
else:
print(f"Error: {response.status_code} - {response.text}")
