OpenAI API completions endpoint#

Note: This endpoint works only with LLM graphs.

API Reference#

OpenVINO Model Server includes now the completions endpoint using OpenAI API. Please see the OpenAI API Reference for more information on the API. The endpoint is exposed via a path:

http://server_name:port/v3/completions

Example request#

curl http://localhost/v3/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3",
    "prompt": "This is a test",
    "stream": false
  }'

Example response#

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "text": "You are testing me!"
    }
  ],
  "created": 1716825108,
  "model": "llama3",
  "object": "text_completion"
}

Request#

Generic#

Param

OpenVINO Model Server

OpenAI /completions API

vLLM Serving Sampling Params

Type

Description

model

✅

✅

✅

string (required)

Name of the model to use. From administrator point of view it is the name assigned to a MediaPipe graph configured to schedule generation using desired model.

stream

✅

✅

✅

bool (optional, default: false)

If set to true, partial message deltas will be sent to the client. The generation chunks will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code

prompt

⚠️

✅

✅

string or array (required)

The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. Limitations: only single string prompt is currently supported.

max_tokens

✅

✅

✅

integer

The maximum number of tokens that can be generated. If not set, the generation will stop once EOS token is generated.

ignore_eos

✅

❌

✅

bool (default: false)

Whether to ignore the EOS token and continue generating tokens after the EOS token is generated. If set to true, the maximum allowed max_tokens value is 4000.

Beam search sampling specific#

Param

OpenVINO Model Server

OpenAI /completions API

vLLM Serving Sampling Params

Type

Description

n

✅

✅

✅

integer (default: 1)

Number of output sequences to return for the given prompt. This value must be between 1 <= N <= BEST_OF.

best_of

✅

✅

✅

integer (default: 1)

Number of output sequences that are generated from the prompt. From these best_of sequences, the top n sequences are returned. best_of must be greater than or equal to n. This is treated as the beam width for beam search sampling.

diversity_penalty

✅

❌

❌

float (default: 1.0)

This value is subtracted from a beam’s score if it generates the same token as any beam from other group at a particular time. See arXiv 1909.05858.

length_penalty

✅

❌

✅

float (default: 1.0)

Exponential penalty to the length that is used with beam-based generation. It is applied as an exponent to the sequence length, which in turn is used to divide the score of the sequence. Since the score is the log likelihood of the sequence (i.e. negative), length_penalty > 0.0 promotes longer sequences, while length_penalty < 0.0 encourages shorter sequences.

Multinomial sampling specific#

Param

OpenVINO Model Server

OpenAI /completions API

vLLM Serving Sampling Params

Type

Description

temperature

✅

✅

✅

float (default: 0.0)

The value is used to modulate token probabilities for multinomial sampling. It enables multinomial sampling when set to > 0.0.

top_p

✅

✅

✅

float (default: 1.0)

Controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.

top_k

✅

❌

✅

int (default: 0)

Controls the number of top tokens to consider. Set to 0 to consider all tokens.

repetition_penalty

✅

❌

✅

float (default: 1.0)

Penalizes new tokens based on whether they appear in the prompt and the generated text so far. Values > 1.0 encourage the model to use new tokens, while values < 1.0 encourage the model to repeat tokens. 1.0 means no penalty.

seed

✅

✅

✅

integer (default: 0)

Random seed to use for the generation.

Unsupported params from OpenAI service:#

  • echo

  • frequency_penalty

  • logit_bias

  • logprobs

  • presence_penalty

  • stop

  • stream_options

  • suffix

Unsupported params from vLLM:#

  • presence_penalty

  • frequency_penalty

  • min_p

  • use_beam_search (In OpenVINO Model Server just simply increase best_of param to enable beam search)

  • early_stopping

  • stop

  • stop_token_ids

  • include_stop_str_in_output

  • min_tokens

  • logprobs

  • prompt_logprobs

  • detokenize

  • skip_special_tokens

  • spaces_between_special_tokens

  • logits_processors

  • truncate_prompt_tokens

Response#

Param

OpenVINO Model Server

OpenAI /completions API

Type

Description

choices

✅

✅

array

A list of chat completion choices. Can be more than one if n is greater than 1 (beam search or multinomial samplings).

choices.index

✅

✅

integer

The index of the choice in the list of choices.

choices.text

✅

✅

string

A chat completion text generated by the model.

choices.finish_reason

⚠️

✅

string or null

The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, or null when generation continues (streaming). However, in current version length is not supported

choices.logprobs

❌

✅

object or null

Log probability information for the choice. In current version, the logprobs is always null.

created

✅

✅

string

The Unix timestamp (in seconds) of when the chat completion was created.

model

✅

✅

string

The model used for the chat completion.

object

✅

✅

string

always text_completion

Unsupported params from OpenAI service:#

  • id

  • system_fingerprint

  • usage

References#

End to end demo with LLM model serving over OpenAI API

Code snippets

LLM calculator

Developer guide for writing custom calculators with REST API extension