~/llamay $ llamay serve -m gemma2:2b -addr 127.0.0.1:11439
time=2026-09-18T08:51:26.911-04:00 level=INFO msg="device graph attached" max-tokens=256
time=2026-09-18T08:51:26.911-04:00 level=INFO msg="llamay serving" addr=127.0.0.1:11439 mode
l=gemma2:2b arch=gemma2 max-loaded=2 keepalive=5m0s params="1.59 GB" context=8192 threads=7
kv=f32 lexicon=0

  OpenAI      POST http://127.0.0.1:11439/v1/chat/completions
  Anthropic   POST http://127.0.0.1:11439/v1/messages
  Embeddings  POST http://127.0.0.1:11439/v1/embeddings     (start with -embed <encoder.gguf
>)
  Rerank      POST http://127.0.0.1:11439/rerank            (start with -rerank <reranker.gg
uf>)
  Contexts    POST http://127.0.0.1:11439/v1/contexts        (then /{id}/fork?n=8, /{id}/sna
pshot)
  Models      POST http://127.0.0.1:11439/api/pull          (and /api/copy, /api/delete)
  Stats       GET  http://127.0.0.1:11439/v1/stats


~/llamay $ # the server stays up; the rest of this is a second terminal
~/llamay $ # the document, which is the kind that cannot leave the building
~/llamay $ cat build/demo/work/note.txt
Discharge summary. Patient: Anita Sharma, age 62. Admitted 2026-03-04 with chest pain; tropo
nin normal throughout. Discharged 2026-03-06 on aspirin 75mg daily and atorvastatin 20mg nig
htly. Cardiology follow-up in six weeks.
~/llamay $ # the request, with the schema the answer has to fit
~/llamay $ cat scripts/site/demo_extract.json
{
  "model": "gemma2:2b",
  "max_tokens": 200,
  "temperature": 0,
  "messages": [{ "role": "user", "content": "replaced by the note" }],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "discharge",
      "schema": {
        "type": "object",
        "properties": {
          "patient":        { "type": "string" },
          "age":            { "type": "integer" },
          "admitted":       { "type": "string" },
          "discharged":     { "type": "string" },
          "medications":    { "type": "array", "items": { "type": "string" } },
          "followup_weeks": { "type": "integer" }
        },
        "required": ["patient", "age", "admitted", "discharged",
                     "medications", "followup_weeks"],
        "additionalProperties": false
      }
    }
  }
}
~/llamay $ # put the note in the request, send it, and validate what comes back
~/llamay $ jq --rawfile note build/demo/work/note.txt \
>   '.messages[0].content = "Extract the record.\n\n" + $note' \
>   scripts/site/demo_extract.json \
> | curl -s http://127.0.0.1:11439/v1/chat/completions -H 'content-type: application/json' -
d @- \
> | jq -r '.choices[0].message.content' | jq
{
  "patient": "Anita Sharma",
  "age": 62,
  "admitted": "2026-03-04",
  "discharged": "2026-03-06",
  "medications": [
    "aspirin 75mg daily",
    "atorvastatin 20mg nightly"
  ],
  "followup_weeks": 6
}
~/llamay $ # nothing left the machine, which for this text is the requirement