mkdir local-ai-work && cd local-ai-work

docker compose up

api-1  | 4:31PM INF LocalAI API is listening! Please connect to the endpoint for API documentation. endpoint=http://0.0.0.0:8080

curl http://localhost:8080/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "gpt-4",
        "messages":[{"role":"user","content":"こんにちは。"}],
        "temperature": 0.7
    }' | jq -r .

{
  "created": 1743184253,
  "object": "chat.completion",
  "id": "23db1330-785e-4ffd-a6d0-d559fe202922",
  "model": "gpt-4",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "こんにちは！何かお手伝いできることがありますか？"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 11,
    "completion_tokens": 14,
    "total_tokens": 25
  }
}

curl http://localhost:8080/v1/images/generations \
    -H "Content-Type: application/json" -d '{
        "prompt": "A cute baby sea otter",
        "size": "256x256"
    }' | jq -r .

{
  "created": 1743186052,
  "id": "444f5650-dac1-4050-9c59-a538fab83c8b",
  "data": [
    {
      "embedding": null,
      "index": 0,
      "url": "http://localhost:8080/generated-images/b641867159540.png"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

curl http://localhost:8080/v1/audio/speech \
    -H "Content-Type: application/json" \
    -d '{
        "model": "tts-1",
        "input": "The quick brown fox jumped over the lazy dog.",
        "voice": "alloy"
    }' \
    --output speech.wav

curl -X POST http://localhost:8080/v1/audio/transcriptions \
  -H "accept: application/json" \
  -H "Content-Type: multipart/form-data" \
  -F model="whisper-1" \
  -F file="@$PWD/voice_lunch_jp_1min.wav" | jq -r .text

はいじゃあ始めますちょっとまだこらえてない方もいらっしゃるんですけどポイスランジューでP始めますはい日曜日にお集まりいただきましたありがとうございます 今日下手部員ですねおフラインということで今日はですねスペシャルのゲストを二人 来ていただいておりますということではいときはちょっとトピックにもありますけれどもボイスローの使用であるレデンリームさんとあとセルソースのカムセドラル レザインのディレクターであるグレークベネスさんに来ていただいてますということで日本に来ていただいてありがとうございます

curl http://localhost:8080/embeddings \
  -X POST -H "Content-Type: application/json" \
  -d '{
      "input": "こんにちは。今日はいいお天気ですね。",
      "model": "text-embedding-ada-002"
    }'

{
  "created": 1743187168,
  "object": "list",
  "id": "9caaf8ee-8e24-4d9b-93ce-d8a7a417b290",
  "model": "text-embedding-ada-002",
  "data": [
    {
      "embedding": [
        -0.005331782,
        0.1366555,
        0.08138748,
        0.01946513,
        -0.034704104,
        0.054323412,
        0.09842277,
(snip)

api-1  | 6:59PM INF BackendLoader starting backend=/build/backend/python/diffusers/run.sh modelID=gemma-3-4b-it o.model=gemma-3-4b-it-Q4_K_M.gguf
api-1  | 6:59PM DBG Loading model in memory from file: /build/models/gemma-3-4b-it-Q4_K_M.gguf
api-1  | 6:59PM DBG Loading Model gemma-3-4b-it with gRPC (file: /build/models/gemma-3-4b-it-Q4_K_M.gguf) (backend: /build/backend/python/diffusers/run.sh): {backendString:/build/backend/python/diffusers/run.sh model:gemma-3-4b-it-Q4_K_M.gguf modelID:gemma-3-4b-it assetDir:/tmp/localai/backend_data context:{emptyCtx:{}} gRPCOptions:0xc00018e2c8 externalBackends:map[autogptq:/build/backend/python/autogptq/run.sh bark:/build/backend/python/bark/run.sh coqui:/build/backend/python/coqui/run.sh diffusers:/build/backend/python/diffusers/run.sh exllama2:/build/backend/python/exllama2/run.sh faster-whisper:/build/backend/python/faster-whisper/run.sh kokoro:/build/backend/python/kokoro/run.sh rerankers:/build/backend/python/rerankers/run.sh transformers:/build/backend/python/transformers/run.sh vllm:/build/backend/python/vllm/run.sh] grpcAttempts:20 grpcAttemptsDelay:2 singleActiveBackend:false parallelRequests:false}
api-1  | 6:59PM INF [/build/backend/python/diffusers/run.sh] Fails: failed to load model with internal loader: backend not found: /tmp/localai/backend_data/backend-assets/grpc/build/backend/python/diffusers/run.sh