OpenAI-Compatible Server¶

from openai import OpenAI
client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="token-abc123",
)

completion = client.chat.completions.create(
    model="NousResearch/Meta-Llama-3-8B-Instruct",
    messages=[
        {"role": "user", "content": "Hello!"},
    ],
)

print(completion.choices[0].message)

completion = client.chat.completions.create(
    model="NousResearch/Meta-Llama-3-8B-Instruct",
    messages=[
        {"role": "user", "content": "Classify this sentiment: vLLM is wonderful!"},
    ],
    extra_headers={
        "x-request-id": "sentiment-classification-00001",
    },
)
print(completion._request_id)

completion = client.completions.create(
    model="NousResearch/Meta-Llama-3-8B-Instruct",
    prompt="A robot may not injure a human being",
    extra_headers={
        "x-request-id": "completion-test",
    },
)
print(completion._request_id)

    use_beam_search: bool = False
    top_k: int | None = None
    min_p: float | None = None
    repetition_penalty: float | None = None
    length_penalty: float = 1.0
    stop_token_ids: list[int] | None = []
    include_stop_str_in_output: bool = False
    ignore_eos: bool = False
    min_tokens: int = 0
    skip_special_tokens: bool = True
    spaces_between_special_tokens: bool = True
    truncate_prompt_tokens: Annotated[int, Field(ge=-1, le=_INT64_MAX)] | None = None
    allowed_token_ids: list[int] | None = None
    prompt_logprobs: int | None = None

    prompt_embeds: bytes | list[bytes] | None = None
    add_special_tokens: bool = Field(
        default=True,
        description=(
            "If true (the default), special tokens (e.g. BOS) will be added to "
            "the prompt."
        ),
    )
    response_format: AnyResponseFormat | None = Field(
        default=None,
        description=(
            "Similar to chat completion, this parameter specifies the format "
            "of output. Only {'type': 'json_object'}, {'type': 'json_schema'}"
            ", {'type': 'structural_tag'}, or {'type': 'text' } is supported."
        ),
    )
    structured_outputs: StructuredOutputsParams | None = Field(
        default=None,
        description="Additional kwargs for structured outputs",
    )
    priority: int = Field(
        default=0,
        ge=_INT64_MIN,
        le=_INT64_MAX,
        description=(
            "The priority of the request (lower means earlier handling; "
            "default: 0). Any priority other than 0 will raise an error "
            "if the served model does not use priority scheduling."
        ),
    )
    request_id: str = Field(
        default_factory=random_uuid,
        description=(
            "The request_id related to this request. If the caller does "
            "not set it, a random_uuid will be generated. This id is used "
            "through out the inference process and return in response."
        ),
    )

    return_tokens_as_token_ids: bool | None = Field(
        default=None,
        description=(
            "If specified with 'logprobs', tokens are represented "
            " as strings of the form 'token_id:{token_id}' so that tokens "
            "that are not JSON-encodable can be identified."
        ),
    )
    return_token_ids: bool | None = Field(
        default=None,
        description=(
            "If specified, the result will include token IDs alongside the "
            "generated text. In streaming mode, prompt_token_ids is included "
            "only in the first chunk, and token_ids contains the delta tokens "
            "for each chunk. This is useful for debugging or when you "
            "need to map generated text back to input tokens."
        ),
    )

    cache_salt: str | None = Field(
        default=None,
        description=(
            "If specified, the prefix cache will be salted with the provided "
            "string to prevent an attacker to guess prompts in multi-user "
            "environments. The salt should be random, protected from "
            "access by 3rd parties, and long enough to be "
            "unpredictable (e.g., 43 characters base64-encoded, corresponding "
            "to 256 bit)."
        ),
    )

    kv_transfer_params: dict[str, Any] | None = Field(
        default=None,
        description="KVTransfer parameters used for disaggregated serving.",
    )

    vllm_xargs: dict[str, str | int | float] | None = Field(
        default=None,
        description=(
            "Additional request parameters with string or "
            "numeric values, used by custom extensions."
        ),
    )

    repetition_detection: RepetitionDetectionParams | None = Field(
        default=None,
        description="Parameters for detecting repetitive N-gram patterns "
        "in output tokens. If such repetition is detected, generation will "
        "be ended early. LLMs can sometimes generate repetitive, unhelpful "
        "token patterns, stopping only when they hit the maximum output length "
        "(e.g. 'abcdabcdabcd...' or '\\emoji \\emoji \\emoji ...'). This feature "
        "can detect such behavior and terminate early, saving time and tokens.",
    )

    thinking_token_budget: int | None = Field(
        default=None,
        description=(
            "Maximum number of tokens allowed for thinking operations "
            "(reasoning models). -1 = unlimited."
        ),
    )

    use_beam_search: bool = False
    top_k: int | None = None
    min_p: float | None = None
    repetition_penalty: float | None = None
    length_penalty: float = 1.0
    stop_token_ids: list[int] | None = []
    include_stop_str_in_output: bool = False
    ignore_eos: bool = False
    min_tokens: int = 0
    skip_special_tokens: bool = True
    spaces_between_special_tokens: bool = True
    truncate_prompt_tokens: Annotated[int, Field(ge=-1, le=_INT64_MAX)] | None = None
    prompt_logprobs: int | None = None
    allowed_token_ids: list[int] | None = None
    bad_words: list[str] = Field(default_factory=list)

    echo: bool = Field(
        default=False,
        description=(
            "If true, the new message will be prepended with the last message "
            "if they belong to the same role."
        ),
    )
    add_generation_prompt: bool = Field(
        default=True,
        description=(
            "If true, the generation prompt will be added to the chat template. "
            "This is a parameter used by chat template in tokenizer config of the "
            "model."
        ),
    )
    continue_final_message: bool = Field(
        default=False,
        description=(
            "If this is set, the chat will be formatted so that the final "
            "message in the chat is open-ended, without any EOS tokens. The "
            "model will continue this message rather than starting a new one. "
            'This allows you to "prefill" part of the model\'s response for it. '
            "Cannot be used at the same time as `add_generation_prompt`."
        ),
    )
    add_special_tokens: bool = Field(
        default=False,
        description=(
            "If true, special tokens (e.g. BOS) will be added to the prompt "
            "on top of what is added by the chat template. "
            "For most models, the chat template takes care of adding the "
            "special tokens so this should be set to false (as is the "
            "default)."
        ),
    )
    documents: list[dict[str, str]] | None = Field(
        default=None,
        description=(
            "A list of dicts representing documents that will be accessible to "
            "the model if it is performing RAG (retrieval-augmented generation)."
            " If the template does not support RAG, this argument will have no "
            "effect. We recommend that each document should be a dict containing "
            '"title" and "text" keys.'
        ),
    )
    chat_template: str | None = Field(
        default=None,
        description=(
            "A Jinja template to use for this conversion. "
            "As of transformers v4.44, default chat template is no longer "
            "allowed, so you must provide a chat template if the tokenizer "
            "does not define one."
        ),
    )
    chat_template_kwargs: dict[str, Any] | None = Field(
        default=None,
        description=(
            "Additional keyword args to pass to the template renderer. "
            "Will be accessible by the chat template."
        ),
    )
    media_io_kwargs: dict[str, dict[str, Any]] | None = Field(
        default=None,
        description=(
            "Additional kwargs to pass to the media IO connectors, "
            "keyed by modality. Merged with engine-level media_io_kwargs."
        ),
    )
    mm_processor_kwargs: dict[str, Any] | None = Field(
        default=None,
        description=("Additional kwargs to pass to the HF processor."),
    )
    structured_outputs: StructuredOutputsParams | None = Field(
        default=None,
        description="Additional kwargs for structured outputs",
    )
    priority: int = Field(
        default=0,
        ge=_INT64_MIN,
        le=_INT64_MAX,
        description=(
            "The priority of the request (lower means earlier handling; "
            "default: 0). Any priority other than 0 will raise an error "
            "if the served model does not use priority scheduling."
        ),
    )
    request_id: str = Field(
        default_factory=random_uuid,
        description=(
            "The request_id related to this request. If the caller does "
            "not set it, a random_uuid will be generated. This id is used "
            "through out the inference process and return in response."
        ),
    )

    return_tokens_as_token_ids: bool | None = Field(
        default=None,
        description=(
            "If specified with 'logprobs', tokens are represented "
            " as strings of the form 'token_id:{token_id}' so that tokens "
            "that are not JSON-encodable can be identified."
        ),
    )
    return_token_ids: bool | None = Field(
        default=None,
        description=(
            "If specified, the result will include token IDs alongside the "
            "generated text. In streaming mode, prompt_token_ids is included "
            "only in the first chunk, and token_ids contains the delta tokens "
            "for each chunk. This is useful for debugging or when you "
            "need to map generated text back to input tokens."
        ),
    )
    return_prompt_text: bool | None = Field(
        default=None,
        description=(
            "If true, the response will include ``prompt_text`` containing the "
            "prompt string produced by chat templating. In streaming mode it "
            "is sent only on the first chunk. This is useful for inspecting "
            "exactly what was fed into the model."
        ),
    )

    cache_salt: str | None = Field(
        default=None,
        description=(
            "If specified, the prefix cache will be salted with the provided "
            "string to prevent an attacker to guess prompts in multi-user "
            "environments. The salt should be random, protected from "
            "access by 3rd parties, and long enough to be "
            "unpredictable (e.g., 43 characters base64-encoded, corresponding "
            "to 256 bit)."
        ),
    )

    kv_transfer_params: dict[str, Any] | None = Field(
        default=None,
        description="KVTransfer parameters used for disaggregated serving.",
    )

    vllm_xargs: dict[str, str | int | float | list[str | int | float]] | None = Field(
        default=None,
        description=(
            "Additional request parameters with (list of) string or "
            "numeric values, used by custom extensions."
        ),
    )

    repetition_detection: RepetitionDetectionParams | None = Field(
        default=None,
        description="Parameters for detecting repetitive N-gram patterns "
        "in output tokens. If such repetition is detected, generation will "
        "be ended early. LLMs can sometimes generate repetitive, unhelpful "
        "token patterns, stopping only when they hit the maximum output length "
        "(e.g. 'abcdabcdabcd...' or '\\emoji \\emoji \\emoji ...'). This feature "
        "can detect such behavior and terminate early, saving time and tokens.",
    )

    request_id: str = Field(
        default_factory=lambda: f"resp_{random_uuid()}",
        description=(
            "The request_id related to this request. If the caller does "
            "not set it, a random_uuid will be generated. This id is used "
            "through out the inference process and return in response."
        ),
    )
    media_io_kwargs: dict[str, dict[str, Any]] | None = Field(
        default=None,
        description=(
            "Additional kwargs to pass to the media IO connectors, "
            "keyed by modality. Merged with engine-level media_io_kwargs."
        ),
    )
    mm_processor_kwargs: dict[str, Any] | None = Field(
        default=None,
        description=("Additional kwargs to pass to the HF processor."),
    )
    priority: int = Field(
        default=0,
        ge=_INT64_MIN,
        le=_INT64_MAX,
        description=(
            "The priority of the request (lower means earlier handling; "
            "default: 0). Any priority other than 0 will raise an error "
            "if the served model does not use priority scheduling."
        ),
    )
    cache_salt: str | None = Field(
        default=None,
        description=(
            "If specified, the prefix cache will be salted with the provided "
            "string to prevent an attacker to guess prompts in multi-user "
            "environments. The salt should be random, protected from "
            "access by 3rd parties, and long enough to be "
            "unpredictable (e.g., 43 characters base64-encoded, corresponding "
            "to 256 bit)."
        ),
    )

    enable_response_messages: bool = Field(
        default=False,
        description=(
            "Dictates whether or not to return messages as part of the "
            "response object. Currently only supported for non-background."
        ),
    )
    # similar to input_messages / output_messages in ResponsesResponse
    # we take in previous_input_messages (ie in harmony format)
    # this cannot be used in conjunction with previous_response_id
    # TODO: consider supporting non harmony messages as well
    previous_input_messages: list[OpenAIHarmonyMessage | dict] | None = None
    structured_outputs: StructuredOutputsParams | None = Field(
        default=None,
        description="Additional kwargs for structured outputs",
    )

    repetition_penalty: float | None = None
    seed: int | None = Field(None, ge=_INT64_MIN, le=_INT64_MAX)
    stop: str | list[str] | None = []
    ignore_eos: bool = False
    vllm_xargs: dict[str, str | int | float | list[str | int | float]] | None = Field(
        default=None,
        description=(
            "Additional request parameters with (list of) string or "
            "numeric values, used by custom extensions."
        ),
    )
    kv_transfer_params: dict[str, Any] | None = Field(
        default=None,
        description="KVTransfer parameters used for disaggregated serving.",
    )
    chat_template_kwargs: dict[str, Any] | None = Field(
        default=None,
        description=(
            "Additional keyword args to pass to the chat template renderer. "
            "Will be accessible by the template."
        ),
    )

    # These are populated when enable_response_messages is set to True
    # NOTE: custom serialization is needed
    # see serialize_input_messages and serialize_output_messages
    input_messages: ResponseInputOutputMessage | None = Field(
        default=None,
        description=(
            "If enable_response_messages, we can show raw token input to model."
        ),
    )
    output_messages: ResponseInputOutputMessage | None = Field(
        default=None,
        description=(
            "If enable_response_messages, we can show raw token output of model."
        ),
    )