Build powerful RAG applications with your own data.
Most RAG projects stall on plumbing: chunking, embeddings, a vector store, retrieval logic, prompt assembly. HostYourAI ships that plumbing as a platform feature. Upload documents to a knowledge base, link it to the shared Router or a dedicated instance, and relevant context is injected into your chat completions automatically. Your code keeps making ordinary OpenAI-compatible calls.
The documents in a RAG pipeline are usually the exact material you would never post publicly: manuals, contracts, policies, internal knowledge. With HostYourAI both the documents and the inference stay in European datacenters, covered by a Data Processing Agreement, which makes RAG viable for the sensitive content it is best at. The full walkthrough lives in the guide Build RAG on EU GPUs.
Retrieval means document excerpts travel inside every enriched prompt. If inference happens outside Europe, your knowledge base effectively leaks across the border one chunk at a time. Keeping storage and inference together in multiple European regions, encrypted with AES-256 at rest, closes that gap. HostYourAI does not train on customer data.
A RAG stack has many moving parts, and each external service is another jurisdiction to assess. Running retrieval and generation on one European platform, with a public subprocessor list, gives organizations in government and healthcare a pipeline they can actually defend in a review.
Every RAG request does extra work before the first token: search, ranking, prompt assembly. When retrieval and inference sit in the same European infrastructure, that overhead stays small, and warm Router models mean generation starts without a model load.
from openai import OpenAI client = OpenAI( base_url="https://hostyourai.com/api/v1", api_key="hyai-...") client.chat.completions.create( model="llama-3.3-70b", messages=[{"role":"user","content":"Hallo!"}])
You create a knowledge base, add documents, and link it to the Router or to one of your dedicated GPU instances. On every chat completion, the platform retrieves the most relevant chunks for the user's question and injects them as context before the model generates. Non-streaming responses include a sources array with the document name and an excerpt for each chunk used, so you can show citations in your UI. Prefer explicit control? Pass knowledge_base_id in the request body instead of linking. And if retrieval ever fails, the request degrades gracefully: the chat continues without the extra context rather than erroring out.
| Pipeline stage | What happens |
|---|---|
| Ingest | Documents are uploaded, chunked and indexed in the knowledge base |
| Link | Knowledge base is attached to the Router or an instance, or passed per request |
| Retrieve | The user's question is matched against chunks by relevance |
| Inject | Top chunks are added to the prompt before generation |
| Cite | Non-streaming responses return sources with document name and excerpt |
| Degrade | If retrieval fails, the completion proceeds without context |
If a knowledge base is linked, no code changes are needed at all. To target one explicitly, pass knowledge_base_id via extra_body in the Python SDK:
from openai import OpenAI
client = OpenAI(
base_url="https://hostyourai.com/api/v1",
api_key="hyai-...",
)
response = client.chat.completions.create(
model="llama-3.2-1b",
messages=[{"role": "user", "content": "What does our warranty cover for water damage?"}],
extra_body={"knowledge_base_id": 42},
)
print(response.choices[0].message.content)
for source in response.model_extra.get("sources", []):
print(source["document"], "-", source["excerpt"][:80])No. The knowledge base handles chunking, indexing and retrieval on the platform. If you prefer full control, you can still bring your own retrieval stack and send assembled prompts.
Two ways: link it to the Router or to an instance so every completion is enriched automatically, or pass knowledge_base_id explicitly in the request body for per-call control.
Yes. Non-streaming responses include a sources array with the document name and an excerpt per retrieved chunk. Streaming responses are enriched with context but cannot carry sources metadata in the SSE chunks.
The completion continues without injected context instead of returning an error. Your chat stays up even if the knowledge base is briefly unavailable.
Any model you can call, on the EU Inference Router or a dedicated instance. Pick one from the model catalog; larger models tend to synthesize retrieved context more faithfully.
Retrieved context adds input tokens to each request, billed pay-as-you-go from your prepaid credit balance. See the pricing page.
From model hosting to a customer-facing API, it is built for developers and businesses who want their AI running on infrastructure they actually control, inside the EU.
Your data and your models stay on European GPUs. GDPR-friendly by design.
Llama, Qwen, DeepSeek, Mistral, FLUX and plenty more. Pick one and it is warm in minutes, with no DevOps on your end.
Point your existing client at the Router and keep your tools. No rewrite, no lock-in.
No infra to manage. Pick a model, get an OpenAI-compatible URL, ship.
Choose from the Model Garden or paste any HuggingFace ID. Set the VRAM and pick an EU GPU.
We deploy vLLM, run readiness probes, and hand you a warm OpenAI- and Anthropic-compatible URL plus an API key.
Point your client at the Router. It auto-routes to a warm instance, idles GPUs when nobody is online, and logs every request.
If a US cloud is off the table, HostYourAI gives you the same developer experience on European infrastructure.
Citizen data that legally has to stay in the EU, with full auditability.
Finance, healthcare and legal teams under GDPR, DORA and the AI Act.
Ship AI features your customers trust, without a US sub-processor.
Deliver private AI for clients on infrastructure you can stand behind.
HostYourAI keeps your models, prompts and data on European GPUs. It is built for teams that care about compliance, reliability and real control.
GPUs and data residency inside Europe. Your prompts never leave the EU.
Run open-weight models with no black boxes or hidden telemetry.
GPUs idle when nobody is online, so you only pay for what you run.
Your infra, your keys, your models. Leave whenever you want.
Yes. HostYourAI runs open models on GPUs in European datacenters via vLLM. Your prompts and outputs never leave the EU and there is no US cloud provider in the chain.
Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open weights also mean no training on your data.
Yes. Point your existing OpenAI or Anthropic client at our Router (https://hostyourai.com/api/v1), change only the base URL and API key. No rewrite, no lock-in.
Pay-as-you-go on one prepaid credit balance: the shared router per token or a dedicated GPU per hour. Free to start, no minimum, no fixed monthly fee.
Text and image models on dedicated EU GPUs. Every model tested on our own hardware.
Explore more about EU-hosted AI on HostYourAI.
Deploy any open model on a dedicated European GPU with vLLM. Your own endpoint, encrypted upstream keys, idle when nobody is online.
Read more →Browse a curated catalog of serveable open chat, image and embedding models with live warm/EU state. Deploy in one click on European GPUs.
Read more →Platform for AI agents with tool use and function calling. Build autonomous agents on European infrastructure.
Read more →Host AI chatbots on European infrastructure. Customer service, internal assistants, and more with GDPR compliance.
Read more →Fine-tune LLMs for your specific use case. LoRA, QLoRA, full fine-tuning on dedicated GPUs.
Read more →Point your Anthropic client at our Router through a /v1/messages shim and run open models on European GPUs. Drop-in, EU-hosted, no rewrite.
Read more →