Private AI inference, carried on your drive.

curl http://127.0.0.1:$THOXBEAM_PORT/v1/chat/completions \
  -H "Authorization: Bearer $THOXBEAM_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thox-general-1b-q4",
    "messages": [
      {"role": "user", "content": "Explain this document."}
    ],
    "stream": true
  }'

const response = await fetch(
  `http://127.0.0.1:${port}/v1/chat/completions`,
  {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${token}`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "thox-general-1b-q4",
      messages: [{ role: "user", content: "Explain this document." }],
      stream: true
    })
  }
);

from openai import OpenAI

client = OpenAI(
    base_url=f"http://127.0.0.1:{port}/v1",
    api_key=token,
)

stream = client.chat.completions.create(
    model="thox-general-1b-q4",
    messages=[{"role": "user", "content": "Explain this document."}],
    stream=True,
)