Integration guide · RAG framework (Python)

LlamaIndex on EU-hosted open models

Build LlamaIndex RAG pipelines and agents on EU-hosted open models with OpenAILike and OpenAILikeEmbedding pointed at Frontière AI. OpenAILike(model, api_base, api_key, …) from llama-index-llms-openai-like.

Tested on 13 October 2026. complete(), a tool call (with allow_parallel_tool_calls=True) and bge-m3 embeddings against the gateway, with llama-index-llms-openai-like 0.8.1 and gpt-oss-120b on OVHcloud (bge-m3 has been paused since 20 October 2026; the example now uses qwen3-embedding-8b).

API format

OpenAI-compatible

Base URL

https://getfrontiereai.eu/api/v1

Where it goes

OpenAILike(model, api_base, api_key, …) from llama-index-llms-openai-like.

Your prompts

Straight from your machine to us

Setup

# pip install llama-index-llms-openai-like llama-index-embeddings-openai-like
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

llm = OpenAILike(
    model="glm-5.2",
    api_base="https://getfrontiereai.eu/api/v1",
    api_key="sk-front-...",
    context_window=256000,
    is_chat_model=True,
    is_function_calling_model=True,
)

embed_model = OpenAILikeEmbedding(
    model_name="qwen3-embedding-8b",
    api_base="https://getfrontiereai.eu/api/v1",
    api_key="sk-front-...",
)

Which model to pick

24 live models have tool calling measured by a real call through the gateway. Models labeled EU sovereign run at European providers; fast-access models are served through US-controlled infrastructure. Prices are per 100,000 tokens, margin and VAT included.

Good to know

• One OpenAILike instance per model; the embedding class takes model_name, not model.
• Pass allow_parallel_tool_calls=True to chat_with_tools and agents: LlamaIndex otherwise sends parallel_tool_calls=false, which OVHcloud-hosted models refuse with HTTP 400 (measured on 2026-10-13).
• Only set is_function_calling_model=True on models with measured tool calling.

Where your prompts go

The library runs in your Python process and calls api_base directly; nothing in OpenAILike routes through LlamaCloud.

On our side, a model labeled EU sovereign runs at a European provider, and the gateway itself runs in Paris on Vercel, a US company — our privacy page says so. Billing keeps the model, the token counts and the amount, never the prompt or the reply.

Sovereignty →Privacy →

Sources

Official documentation, checked on 12 October 2026:

• LlamaIndex — OpenAILike
• LlamaIndex — OpenAILikeEmbedding

FAQ

Other guides

• LangChainAgent framework (Python)
• Vercel AI SDKAgent framework (TypeScript)