Skip to main content
This integration shows how to use Gravix Layer together with MongoDB for storing metadata, search indices, and application data while performing model inference and retrieval over vectors.

​
What You’ll Learn​

  • How to save LLM outputs to MongoDB
  • How to query and analyze AI-generated data
  • Example: Storing chat completions in MongoDB

​
1. Install Required Packages​

pip install pymongo openai python-dotenv

​
2. Configure Your API Key​

Add your API key to a .env file: 
GRAVIXLAYER_API_KEY=your_api_key_here

​
3. Using MongoDB with Gravix Layer​

from pymongo import MongoClient
from openai import OpenAI
import os
from dotenv import load_dotenv

load_dotenv()
api_key = os.environ.get("GRAVIXLAYER_API_KEY", "test_key")

llm = OpenAI(
	api_key=api_key,
	base_url="https://api.gravixlayer.com/v1/inference"
)

client = MongoClient("mongodb://localhost:27017/")
db = client["ai_data"]
collection = db["completions"]

response = llm.chat.completions.create(
	model="meta-llama/llama-3.1-8b-instruct",
	messages=[{"role": "user", "content": "Summarize this: AI is changing the world."}]
)

collection.insert_one({
	"prompt": "Summarize this: AI is changing the world.",
	"response": response.choices[0].message.content
})

print("Saved to MongoDB!")
Expected Output: 
Saved to MongoDB!
If MongoDB is not running, you may see: 
pymongo.errors.ServerSelectionTimeoutError: localhost:27017: [Errno 61] Connection refused ...
Sample Output: 
pymongo.errors.ServerSelectionTimeoutError: localhost:27017: [Errno 61] Connection refused ...
Note: You must have a running MongoDB server on localhost:27017 for this code to work.
MongoDB lets you store and analyze AI-generated data at scale. Gravix Layer provides the LLM power for any data-driven application.
⌘I