Build against Eldric
like you would against OpenAI.

Assuming an Eldric server is reachable at https://eldric.local and you have an API key from the Admin Console, your existing OpenAI-shaped code works unchanged after pointing the base URL at Eldric.

Need to install Eldric first? Start at get-started; the post-install setup (admin signup, license, first KB) lives on first-run. This page assumes the server is already up.

Curl

curl https://eldric.local/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "messages": [{"role":"user","content":"Hello."}],
    "stream": true
  }'

OpenAI SDK (Python)

from openai import OpenAI
client = OpenAI(
    base_url="https://eldric.local/v1",
    api_key="$API_KEY",
)
resp = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role":"user","content":"Hello."}],
)

Existing tooling — LangChain, LlamaIndex, Continue, Cursor, anything that consumes the OpenAI API — works after pointing the base URL at Eldric.