# 512x512 is supported too
curl http://localhost:8080/v1/images/generations -H "Content-Type: application/json" -d '{
  "prompt": "A cute baby sea otter",
  "size": "256x256"
}'

curl http://localhost:8080/v1/images/generations -H "Content-Type: application/json" -d '{
  "prompt": "floating hair, portrait, ((loli)), ((one girl)), cute face, hidden hands, asymmetrical bangs, beautiful detailed eyes, eye shadow, hair ornament, ribbons, bowties, buttons, pleated skirt, (((masterpiece))), ((best quality)), colorful|((part of the head)), ((((mutated hands and fingers)))), deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, Octane renderer, lowres, bad anatomy, bad hands, text",
  "size": "256x256"
}'

name: animagine-xl
parameters:
  model: Linaqruf/animagine-xl
backend: diffusers

# Force CPU usage - set to true for GPU
f16: false
diffusers:
  pipeline_type: StableDiffusionXLPipeline
  cuda: false # Enable for GPU usage (CUDA)
  scheduler_type: euler_a

curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
  "model": "ggml-koala-7b-model-q4_0-r2.bin",
  "messages": [{"role": "user", "content": "Say this is a test!"}],
  "temperature": 0.7
}'

curl http://localhost:8080/v1/edits -H "Content-Type: application/json" -d '{
  "model": "ggml-koala-7b-model-q4_0-r2.bin",
  "instruction": "rephrase",
  "input": "Black cat jumped out of the window",
  "temperature": 0.7
}'

curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
  "model": "ggml-koala-7b-model-q4_0-r2.bin",
  "prompt": "A long time ago in a galaxy far, far away",
  "temperature": 0.7
}'

curl http://localhost:8080/v1/models

curl http://localhost:8080/v1/audio/transcriptions -H "Content-Type: multipart/form-data" -F file="@<FILE_PATH>" -F model="<MODEL_NAME>"

name: whisper-1
backend: whisper
parameters:
  model: whisper-en

## Get an example audio file
wget --quiet --show-progress -O gb1.ogg https://upload.wikimedia.org/wikipedia/commons/1/1f/George_W_Bush_Columbia_FINAL.ogg

## Send the example audio file to the transcriptions endpoint
curl http://localhost:8080/v1/audio/transcriptions -H "Content-Type: multipart/form-data" -F file="@$PWD/gb1.ogg" -F model="whisper-1"

## Result
{"text":"My fellow Americans, this day has brought terrible news and great sadness to our country.At nine o'clock this morning, Mission Control in Houston lost contact with our Space ShuttleColumbia.A short time later, debris was seen falling from the skies above Texas.The Columbia's lost.There are no survivors.One board was a crew of seven.Colonel Rick Husband, Lieutenant Colonel Michael Anderson, Commander Laurel Clark, Captain DavidBrown, Commander William McCool, Dr. Kultna Shavla, and Elon Ramon, a colonel in the IsraeliAir Force.These men and women assumed great risk in the service to all humanity.In an age when spaceflight has come to seem almost routine, it is easy to overlook thedangers of travel by rocket and the difficulties of navigating the fierce outer atmosphere ofthe Earth.These astronauts knew the dangers, and they faced them willingly, knowing they had a highand noble purpose in life.Because of their courage and daring and idealism, we will miss them all the more.All Americans today are thinking as well of the families of these men and women who havebeen given this sudden shock and grief.You're not alone.Our entire nation agrees with you, and those you loved will always have the respect andgratitude of this country.The cause in which they died will continue.Mankind has led into the darkness beyond our world by the inspiration of discovery andthe longing to understand.Our journey into space will go on.In the skies today, we saw destruction and tragedy.As farther than we can see, there is comfort and hope.In the words of the prophet Isaiah, \"Lift your eyes and look to the heavens who createdall these, he who brings out the starry hosts one by one and calls them each by name.\"Because of his great power and mighty strength, not one of them is missing.The same creator who names the stars also knows the names of the seven souls we mourntoday.The crew of the shuttle Columbia did not return safely to Earth yet we can pray that all aresafely home.May God bless the grieving families and may God continue to bless America.[BLANK_AUDIO]"}

name: openllama
parameters:
  model: ggml-openllama.bin
  top_p: 80
  top_k: 0.9
  temperature: 0.1
backend: llama # Set the `llama` backend

import openai
# ...
# Send the conversation and available functions to GPT
messages = [{"role": "user", "content": "What's the weather like in Boston?"}]
functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
        },
    }
]
response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=messages,
    functions=functions,
    function_call="auto",
)
# ...

curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
     "model": "gpt-4",
     "messages": [{"role": "user", "content": "How are you?"}],
     "temperature": 0.1,
     "grammar_json_functions": {
        "oneOf": [
            {
                "type": "object",
                "properties": {
                    "function": {"const": "create_event"},
                    "arguments": {
                        "type": "object",
                        "properties": {
                            "title": {"type": "string"},
                            "date": {"type": "string"},
                            "time": {"type": "string"}
                        }
                    }
                }
            },
            {
                "type": "object",
                "properties": {
                    "function": {"const": "search"},
                    "arguments": {
                        "type": "object",
                        "properties": {
                            "query": {"type": "string"}
                        }
                    }
                }
            }
        ]
    }
   }'

curl http://localhost:8080/tts -H "Content-Type: application/json" -d '{
  "input": "Hello world",
  "model": "tts"
}'

curl http://localhost:8080/tts -H "Content-Type: application/json" -d '{
  "model":"it-riccardo_fasol-x-low.onnx",
  "input": "Ciao, sono Ettore"
}' | aplay

name: text-embedding-ada-002 # The model name used in the API
parameters:
  model: <model_file>
backend: "<backend>"
embeddings: true
# .. other parameters

name: text-embedding-ada-002
parameters:
  model: bert
backend: bert-embeddings
embeddings: true
# .. other parameters

wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O models/bert

curl http://localhost:8080/embeddings -X POST -H "Content-Type: application/json" -d '{
  "input": "Your text string goes here",
  "model": "text-embedding-ada-002"
}' | jq "."

name: text-embedding-ada-002
backend: huggingface-embeddings
embeddings: true
parameters:
  model: all-MiniLM-L6-v2

name: my-awesome-model
backend: llama
embeddings: true
parameters:
  model: ggml-file.bin
# ...

curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
  "model": "gpt-4",
  "messages": [{"role": "user", "content": "Do you like apples?"}],
  "grammar": "root ::= (\"yes\" | \"no\")"
}'