POST /rerank, /v1/rerank, /v2/rerank

curl -X 'POST' \
   'https://aios.private.kr-west1.e.samsungsdscloud.com/rerank' \ 
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "sds/bge-reranker-v2-m3",

{
  "id": "rerank-scp-aios-rerank",
  "model": "sds/sds/bge-m3",
  "usage": {
    "total_tokens": 65
  },
  "results": [
    {
      "index": 0,
      "document": {
        "text": "The capital of France is Paris."
      },
      "relevance_score": 0.8291233777999878
    },
    {
      "index": 1,
      "document": {
        "text": "France capital city is known for the Eiffel Tower."
      },
      "relevance_score": 0.6996355652809143
    }
  ]
}

POST /score, /v1/score

curl -X 'POST' \
  'https://aios.private.kr-west1.e.samsungsdscloud.com/score' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "sds/bge-reranker-v2-m3",
  "encoding_format": "float",
"text_1": [
  "What is the largest planet in the solar system?",
  "What is the chemical symbol for water?"
],
"text_2": [
  "Jupiter is the largest planet in the solar system.",
  "The chemical symbol for water is H₂O."
]
}'

{
  "id": "score-scp-aios-score",
  "object": "list",
  "created": 1748574112,
  "model": "sds/bge-reranker-v2-m3",
  "data": [
    {

curl -X 'POST' \
   'https://aios.private.kr-west1.e.samsungsdscloud.com/v1/chat/completions' \
  -H 'accept: application/json' \

{
  "id": "chatcmpl-scp-aios-chat-completions",
  "object": "chat.completion",
  "created": 1749702816,
  "model": "meta-llama/Meta-Llama-3.3-70B-Instruct",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "reasoning_content": null,
        "content": "The capital of Korea is Seoul.",
        "tool_calls": []
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null
    }
  ],
  "usage": {
    "prompt_tokens": 54,
    "total_tokens": 62,
    "completion_tokens": 8,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null
}

{
  "id": "cmpl-scp-aios-completions",
  "object": "text_completion",
  "created": 1749702612,
  "model": "meta-llama/Meta-Llama-3.3-70B-Instruct",
  "choices": [
    {
      "index": 0,
      "text": " \nOur capital city is Seoul. \n\nA. 1\nB. ",
      "logprobs": null,
      "finish_reason": "length",
      "stop_reason": null,
      "prompt_logprobs": null
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 25,
    "completion_tokens": 16,
    "prompt_tokens_details": null
  }
}

POST /v1/embeddings

curl -X 'POST' \
   'https://aios.private.kr-west1.e.samsungsdscloud.com/v1/embedding' \ 
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "sds/bge-m3",
    "input": "What is the capital of France?",
	"encoding_format": "float"
  }'

{
  "id":"embd-scp-aios-embeddings",
  "object":"list","created":1749035024,
  "model":"sds/bge-m3",
  "data":[
    {
      "index":0,
      "object":"embedding",
      "embedding":
      [0.01319122314453125,0.057220458984375,-0.028533935546875,-0.0008697509765625,-0.01422119140625,0.033416748046875,-0.0062408447265625,-0.04364013671875,-0.004497528076171875,0.0008072853088378906,-0.0193328857421875,0.041168212890625,-0.019317626953125,-0.0188751220703125,-0.047088623046875,
      -0 ....(omitted)

      -0.05706787109375,-0.0147705078125]
    }
  ],
  "usage":
  {
    "prompt_tokens":9,
    "total_tokens":9,
    "completion_tokens":0,
    "prompt_tokens_details":null
  }
}

pip install openai

/v1/completions

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model calls.
model = "<<model>>"                     # Enter the model ID for AIOS model calls.

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")


response = client.completions.create(
  model=model,
  prompt="Hi"
)

Completion(
  id='cmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    CompletionChoice(
      finish_reason='length', 
      index=0, 
      logprobs=None, 
      text=' future president of the United States, I hope you’re doing well. As a', 
      stop_reason=None, 
      prompt_logprobs=None
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='text_completion', 

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # AIOS model call endpoint-url to be input for AIOS model call
model = "<<model>>"                     # AIOS model call model ID to be input for AIOS model call

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")

response = client.completions.create(
  model=model,
  prompt="Hi",
  stream=True
)

# Receive the response as the model generates tokens.
for chunk in response:
  print(chunk)

Completion(
  id='cmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    CompletionChoice(
      finish_reason=None, 
      index=0, 
      logprobs=None, 
      text='.', 
      stop_reason=None
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='text_completion', 
  system_fingerprint=None, 
  usage=None
)
Completion(..., choices=[CompletionChoice(..., text=' I', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text="'m", ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' looking', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' for', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' a', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' way', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' to', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' check', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' if', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' a', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' specific', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' process', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' is', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' running', ...)], ...)
Completion(..., choices=[CompletionChoice(..., text=' on', ...)], ...)
Completion(..., choices=[], ..., 
  usage=CompletionUsage(
    completion_tokens=16, 
    prompt_tokens=2, 
    total_tokens=18, 
    completion_tokens_details=None, 
    prompt_tokens_details=None
  )
)

/v1/chat/completions

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # AIOS model call for aios endpoint-url to enter.
model = "<<model>>"                     # AIOS model call for model ID to enter.

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")

response = client.chat.completions.create(
  model=model,
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hi"}
  ]
)

ChatCompletion(
  id='chatcmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    Choice(
      finish_reason='stop', 
      index=0, 
      logprobs=None, 
      message=ChatCompletionMessage(
        content='Hello. How can I assist you today?', 
        refusal=None, 
        role='assistant', 
        annotations=None, 
        audio=None, 
        function_call=None, 
        tool_calls=[], 
        reasoning_content=None
      ), 
      stop_reason=None
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='chat.completion', 
  service_tier=None, 
  system_fingerprint=None, 
  usage=CompletionUsage(
    completion_tokens=10, 
    prompt_tokens=42, 
    total_tokens=52, 
    completion_tokens_details=None, 
    prompt_tokens_details=None
  ), 
  prompt_logprobs=None
)

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # AIOS model call for aios endpoint-url to enter.
model = "<<model>>"                     # AIOS model call for model ID to enter.

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")

response = client.chat.completions.create(
  model="meta-llama/Llama-3.3-70B-Instruct",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hi"}
  ],
  stream=True
)

# You can receive a response each time the model generates a token.
for chunk in response:
  print(chunk)

ChatCompletionChunk(
  id='chatcmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    Choice(
      delta=ChoiceDelta(
        content='', 
        function_call=None, 
        refusal=None, 
        role='assistant', 
        tool_calls=None
      ), 
      finish_reason=None, 
      index=0, 
      logprobs=None
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='chat.completion.chunk', 
  service_tier=None, 
  system_fingerprint=None, 
  usage=None
)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content='It', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content="'s", ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' nice', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' to', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content='meet', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' you', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content='.', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' Is', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' there', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' something', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' I', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' can', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' help', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' you', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' with', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' or', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' would', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' you', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' like', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' to', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content=' chat', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content='?', ...), ...)], ...)
ChatCompletionChunk(..., choices=[Choice(delta=ChoiceDelta(content='', ...), ...)], ...)
ChatCompletionChunk(..., choices=[], ..., 
  usage=CompletionUsage(
    completion_tokens=23, 
    prompt_tokens=42, 
    total_tokens=65, 
    completion_tokens_details=None, 
    prompt_tokens_details=None
  )
)

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # AIOS model call endpoint URL
model = "<<model>>"                     # AIOS model ID

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")

# Function to get weather information
tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get current temperature for provided coordinates in celsius.",
        "parameters": {
            "type": "object",
            "properties": {
                "latitude": {"type": "number"},
                "longitude": {"type": "number"}
            },
            "required": ["latitude", "longitude"],
            "additionalProperties": False
        },
        "strict": True
    }
}]

ChatCompletion(
  id='chatcmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    Choice(
      finish_reason='tool_calls', 
      index=0, 
      logprobs=None, 
      message=ChatCompletionMessage(
        content=None, 
        refusal=None, 
        role='assistant', 
        annotations=None, 
        audio=None, 
        function_call=None, 
        tool_calls=[
          ChatCompletionMessageToolCall(
            id='chatcmpl-tool-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
            function=Function(
              arguments='{"latitude": 48.8566, "longitude": 2.3522}', 
              name='get_weather'
            ), 
            type='function'
          )
        ], 
        reasoning_content=None
      ), 
      stop_reason=None
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='chat.completion', 
  service_tier=None, 
  system_fingerprint=None, 
  usage=CompletionUsage(
    completion_tokens=19, 
    prompt_tokens=194, 
    total_tokens=213, 
    completion_tokens_details=None, 
    prompt_tokens_details=None
  ), 
  prompt_logprobs=None
)

import json

# example function, always responds with 14 degrees.
def get_weather(latitude, longitude):
    return "14℃"

tool_call = response.choices[0].message.tool_calls[0]
args = json.loads(tool_call.function.arguments)

result = get_weather(args["latitude"], args["longitude"]) # "14℃"

# Add the model's tool call message to messages
messages.append(response.choices[0].message)
# Add the result of the actual function call to messages
messages.append({
  "role": "tool",
  "tool_call_id": tool_call.id,
  "content": str(result)
})

response_2 = client.chat.completions.create(
    model=model,
    messages=messages,
    # tools=tools

ChatCompletion(
  id='chatcmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    Choice(
      finish_reason='stop', 
      index=0, 
      logprobs=None, 
      message=ChatCompletionMessage(
        content='The current weather in Paris is 14℃.', 
        refusal=None, 
        role='assistant', 
        annotations=None, 
        audio=None, 
        function_call=None, 
        tool_calls=[], 
        reasoning_content=None
      ), 
      stop_reason=None
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='chat.completion', 
  service_tier=None, 
  system_fingerprint=None, 
  usage=CompletionUsage(
    completion_tokens=11, 
    prompt_tokens=74, 
    total_tokens=85, 
    completion_tokens_details=None, 
    prompt_tokens_details=None
  ), 
  prompt_logprobs=None
)

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model calls.
model = "<<model>>"                     # Enter the model ID for AIOS model calls.

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")

response = client.chat.completions.create(
  model=model,
  messages=[
    {"role": "user", "content": "9.11 and 9.8, which is greater?"}
  ],
)

ChatCompletion(
  id='chatcmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    Choice(
      finish_reason='stop', 
      index=0, 
      logprobs=None, 
      message=ChatCompletionMessage(
        content='''
        To determine whether 9.11 or 9.8 is larger, we compare the decimal parts since both numbers have the same whole number part (9).
        1. Convert both numbers to the same decimal places for easier comparison:
           - 9.11 remains as is.
           - 9.8 can be written as 9.80.
        2. Compare the tenths place:
           - The tenths place of 9.11 is 1.
           - The tenths place of 9.80 is 8.
        3. Since 8 (from 9.80) is greater than 1 (from 9.11), 9.80 (or 9.8) is larger.
        4. Verification by subtraction:
           - Subtracting 9.11 from 9.8 gives \(9.80 - 9.11 = 0.69\), which is positive, confirming 9.8 is larger.
        Thus, the larger number is \(\boxed{9.8}\).
        ''', 
        refusal=None, 
        role='assistant', 
        annotations=None, 
        audio=None, 
        function_call=None, 
        tool_calls=[], 
        reasoning_content="""Okay, so I need to figure out whether 9.11 is bigger than 9.8 or vice versa. 
        Hmm, let me think. Both numbers start with 9, so the whole number part is the same. 

ChatCompletion(
  id='chatcmpl-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  choices=[
    Choice(
      finish_reason='stop', 
      index=0, 
      logprobs=None, 
      message=ChatCompletionMessage(
        content="""Here's what's in the image:
        *   **A golden retriever puppy:** The main subject is a light-colored golden retriever puppy lying on green grass.
        *   **A bone:** The puppy is holding a large bone in its paws and appears to be enjoying chewing on it.
        *   **Grass:** The puppy is lying on a well-maintained lawn.
        *   **Vegetation:** Behind the puppy, there are some shrubs and other greenery.
        *   **Outdoor setting:** The scene is outdoors, likely a backyard.""", 
        refusal=None, 
        role='assistant', 
        annotations=None, 
        audio=None, 
        function_call=None, 
        tool_calls=[], 
        reasoning_content=None
      ), 
      stop_reason=106
    )
  ], 
  created=1750000000, 
  model='<<model>>', 
  object='chat.completion', 
  service_tier=None, 
  system_fingerprint=None, 
  usage=CompletionUsage(
    completion_tokens=114, 
    prompt_tokens=276, 
    total_tokens=390, 
    completion_tokens_details=None, 
    prompt_tokens_details=None
  ), 
  prompt_logprobs=None, 
  kv_transfer_params=None
)

/v1/embeddings

from openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # AIOS endpoint-url for model calls
model = "<<model>>"                     # Model ID for AIOS model calls

client = OpenAI(base_url=urljoin(aios_base_url, "v1"), api_key="EMPTY_KEY")

response = client.embeddings.create(
    input="What is the capital of France?",
    model=model
)

CreateEmbeddingResponse(
  data=[
    Embedding(
      embedding=[
        0.01319122314453125, 
        0.057220458984375, 
        -0.028533935546875, 
        -0.0008697509765625, 
        -0.01422119140625,
        ...omitted...
      ], 
      index=0, 
      object='embedding'
    )
  ], 
  model='<<model>>', 
  object='list', 
  usage=Usage(
    prompt_tokens=9, 
    total_tokens=9, 
    completion_tokens=0, 
    prompt_tokens_details=None
  ), 
  id='embd-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  created=1750000000
)

pip install cohere

/v2/rerank

import cohere
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model calls.
model = "<<model>>"                     # Enter the model ID for AIOS model calls.

client = cohere.ClientV2("EMPTY_KEY", base_url=aios_base_url)

docs = [
  "The capital of France is Paris.",
  "France capital city is known for the Eiffel Tower.",
  "Paris is located in the north-central part of France."
]
  
response = client.rerank(
    model=model,
    query="What is the capital of France?",
    documents=docs,
    top_n=3,
)

V2RerankResponse(
  id='rerank-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx', 
  results=[
    V2RerankResponseResultsItem(
      document=V2RerankResponseResultsItemDocument(
        text='The capital of France is Paris.'
      ), 
      index=0, 
      relevance_score=1.0
    ), 
    V2RerankResponseResultsItem(

pip install langchain langchain-openai langchain-cohere langchain-together

from langchain_openai import OpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model calls.
model = "<<model>>"                     # Enter the model ID for AIOS model calls.

llm = OpenAI(
  base_url=urljoin(aios_base_url, "v1"), 
  api_key="EMPTY_KEY", 
  model=model
)

llm.invoke("Can you introduce yourself in 5 words?")

from langchain_openai import ChatOpenAI
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model calls.
model = "<<model>>"                     # Enter the model ID for AIOS model calls.

chat_llm = ChatOpenAI(
  base_url=urljoin(aios_base_url, "v1"), 
  api_key="EMPTY_KEY", 
  model=model
)

chat_completion = chat_llm.invoke("Can you introduce yourself in 5 words?")

chat_completion.pretty_print()

from langchain_together import TogetherEmbeddings
from urllib.parse import urljoin

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model invocation.
model = "<<model>>"                     # Enter the model ID for AIOS model invocation.

embedding = TogetherEmbeddings(
  base_url=urljoin(aios_base_url, "v1"), 
  api_key="EMPTY_KEY", 
  model=model
)

embedding.embed_query("What is the capital of France?")

[
  0.01319122314453125, 
  0.057220458984375, 
  -0.028533935546875, 
  -0.0008697509765625, 
  -0.01422119140625, 
  ...omitted...
]

from langchain_cohere.rerank import CohereRerank

aios_base_url = "<<aios endpoint-url>>" # Enter the aios endpoint-url for AIOS model invocation.
model = "<<model>>"                     # Enter the model ID for AIOS model invocation.

rerank = CohereRerank(
  base_url=aios_base_url,
  cohere_api_key="EMPTY_KEY",
  model=model
)

docs = [
  "The capital of France is Paris.",
  "France capital city is known for the Eiffel Tower.",
  "Paris is located in the north-central part of France."
]

rerank.rerank(
  documents=docs, 
  query="What is the capital of France?",
  top_n=3
)

[
  {'index': 0, 'relevance_score': 1.0}, 
  {'index': 1, 'relevance_score': 1.0}, 
  {'index': 2, 'relevance_score': 0.982421875}
]