LlamaIndex¶

LlamaIndex is the leading framework for building LLM-powered agents over your data with LLMs and workflows.

Python¶

Installation¶

First, install the llama-index and llama-index-llms-ovhcloud packages:

pip install llama-index llama-index-llms-ovhcloud

https://developers.llamaindex.ai/python/framework-api-reference/llms/ovhcloud/

Usage¶

Create a new file such as main.py and paste this code. Don't forget to add your AI Endpoints API key in the api_key parameter or by setting your OVHCLOUD_API_KEY environmnent variable.

from llama_index.llms.ovhcloud import OVHcloud
from llama_index.core.llms import ChatMessage

llm = OVHcloud(
    model="gpt-oss-120b",
    api_key="",
)

response = llm.complete("The capital of France is")
print(response.text)

messages = [
    ChatMessage(
        role="system", content="You are a helpful assistant"
    ),
    ChatMessage(role="user", content="What is the capital of France?"),
]
response = llm.chat(messages)
print(response)

Execute the script using the following command:

python main.py

You should see the following output in your terminal:

The capital of France is **Paris**.
assistant: The capital of France is **Paris**.

Typescript¶

Going further¶

You can explore the LlamaIndex Python documentation and Typescript documentation to dive deeper into advanced features.

• Check out our Getting Started guide to learn more about OVHcloud AI Endpoints capabilities.
• Need support or want to chat? Join our community on Discord.
• Found a mistake or want to improve this guide? Feel free to open a Pull Request or Issue on GitHub.