LlamaIndex

import os
from llama_index.llms.openai import OpenAI
from llama_index.core import Settings

# Set your Nordlys API key
os.environ["OPENAI_API_KEY"] = os.environ["NORDLYS_API_KEY"]

# Initialize OpenAI client with Nordlys endpoint
llm = OpenAI(
    model="nordlys/hypernova",
    api_base="https://api.nordlyslabs.com/v1",
    api_key=os.environ["NORDLYS_API_KEY"],
)

# Set as global model
Settings.llm = llm

# Use with simple queries
response = llm.complete("What is retrieval-augmented generation?")
print(response)

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Load documents
documents = SimpleDirectoryReader("data").load_data()

# Create index
index = VectorStoreIndex.from_documents(documents)

# Query with Mixture of Models
query_engine = index.as_query_engine()
response = query_engine.query("What are the benefits of RAG?")
print(response)