Skip to main content
Use Gravix Layer with LangGraph to build knowledge-graph-augmented workflows that combine vector search and inference for richer, context-aware results.

​
What You’ll Learn​

  • How to connect LangGraph nodes to Gravix Layer’s API
  • How to use OpenAI-compatible endpoints for graph-based workflows
  • Example: Using LangGraph for multi-step document analysis

​
1. Install Required Packages​

pip install langgraph 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 LangGraph with Gravix Layer​

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"
)

response = llm.chat.completions.create(
	model="meta-llama/llama-3.1-8b-instruct",
	messages=[{"role": "user", "content": "Analyze this document: ..."}]
)

print(response.choices[0].message.content)
Expected Output: 
This document discusses ... (sample output will depend on the actual document content provided)
Note: The LangGraph API has changed and the original example may not work. The above code uses the OpenAI client directly for document analysis, which is always compatible with Gravix Layer.
⌘I