Struct Annotated LlmRequest

Generated from cargo doc --no-deps -p nemo-relay-builtins -p nemo-relay-diagnostics -p nemo-relay-logging -p nemo-relay-plugin-host -p nemo-relay-codecs -p nemo-relay -p nemo-relay-runtime -p nemo-relay-model-pricing -p nemo-relay-resource-metrics -p nemo-relay-observability -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker.

pub struct AnnotatedLlmRequest {Show 21 fields
    pub messages: Vec<LlmMessage>,
    pub instructions: Option<MessageContent>,
    pub model: Option<String>,
    pub params: Option<GenerationParams>,
    pub tools: Option<ToolDefinitionList>,
    pub tool_choice: Option<ToolChoice>,
    pub store: Option<bool>,
    pub previous_response_id: Option<String>,
    pub truncation: Option<JsonValue>,
    pub reasoning: Option<JsonValue>,
    pub include: Option<JsonValue>,
    pub user: Option<String>,
    pub metadata: Option<JsonValue>,
    pub service_tier: Option<String>,
    pub parallel_tool_calls: Option<bool>,
    pub max_output_tokens: Option<u64>,
    pub max_tool_calls: Option<u64>,
    pub top_logprobs: Option<u64>,
    pub stream: Option<bool>,
    pub api_specific: Option<JsonValue>,
    pub extra: HashMap<String, JsonValue>,
}

Normalized request structure with explicit provider-specific and extension fields.

Fields

`messages: Vec<LlmMessage>`

Parsed conversation messages.

`instructions: Option<MessageContent>`

Provider-level instructions that are not part of the conversation array. Anthropic encodes this as system; OpenAI Responses uses instructions.

`model: Option<String>`

Model identifier (e.g., "gpt-4", "claude-sonnet-4-20250514").

`params: Option<GenerationParams>`

Common generation parameters, normalized.

`tools: Option<ToolDefinitionList>`

Tool definitions (function schemas) available to the model.

`tool_choice: Option<ToolChoice>`

Tool choice control.

`store: Option<bool>`

OpenAI Responses: whether to persist response state server-side.

`previous_response_id: Option<String>`

OpenAI Responses: prior response to continue from.

`truncation: Option<JsonValue>`

OpenAI Responses: context truncation behavior.

`reasoning: Option<JsonValue>`

OpenAI Responses: reasoning configuration object.

`include: Option<JsonValue>`

OpenAI Responses: include filter for additional output/state items.

`user: Option<String>`

OpenAI user identifier.

`metadata: Option<JsonValue>`

OpenAI metadata map/object.

`service_tier: Option<String>`

OpenAI service tier preference.

`parallel_tool_calls: Option<bool>`

OpenAI tool parallelism toggle.

`max_output_tokens: Option<u64>`

OpenAI Responses max output token limit.

`max_tool_calls: Option<u64>`

OpenAI Responses max tool calls.

`top_logprobs: Option<u64>`

OpenAI logprob fanout count.

`stream: Option<bool>`

OpenAI streaming toggle.

`api_specific: Option<JsonValue>`

Codec-owned request data; preserved as JSON and validated by the selected codec.

`extra: HashMap<String, JsonValue>`

Unknown provider fields, excluding modeled field names.

Implementations

`impl AnnotatedLlmRequest`

impl AnnotatedLlmRequest

`model`

pub fn model(&self) -> &str

Returns the value of model, or the default value if model is unset.

`store`

pub fn store(&self) -> bool

Returns the value of store, or the default value if store is unset.

`previous_response_id`

pub fn previous_response_id(&self) -> &str

Returns the value of previous_response_id, or the default value if previous_response_id is unset.

`user`

pub fn user(&self) -> &str

Returns the value of user, or the default value if user is unset.

`service_tier`

pub fn service_tier(&self) -> &str

Returns the value of service_tier, or the default value if service_tier is unset.

`parallel_tool_calls`

pub fn parallel_tool_calls(&self) -> bool

Returns the value of parallel_tool_calls, or the default value if parallel_tool_calls is unset.

`max_output_tokens`

pub fn max_output_tokens(&self) -> u64

Returns the value of max_output_tokens, or the default value if max_output_tokens is unset.

`max_tool_calls`

pub fn max_tool_calls(&self) -> u64

Returns the value of max_tool_calls, or the default value if max_tool_calls is unset.

`top_logprobs`

pub fn top_logprobs(&self) -> u64

Returns the value of top_logprobs, or the default value if top_logprobs is unset.

`stream`

pub fn stream(&self) -> bool

Returns the value of stream, or the default value if stream is unset.

Trait Implementations

`impl Clone for AnnotatedLlmRequest`

impl Clone for AnnotatedLlmRequest

`clone`

fn clone(&self) -> AnnotatedLlmRequest

`clone_from`

fn clone_from(&mut self, source: &Self)

`impl Debug for AnnotatedLlmRequest`

impl Debug for AnnotatedLlmRequest

`fmt`

fn fmt(&self, f: &mut Formatter<'_>) -> Result

`impl Default for AnnotatedLlmRequest`

impl Default for AnnotatedLlmRequest

`default`

fn default() -> Self

`impl Message for AnnotatedLlmRequest`

impl Message for AnnotatedLlmRequest

`encoded_len`

fn encoded_len(&self) -> usize

`clear`

fn clear(&mut self)

`encode`

fn encode(&self, buf: &mut impl BufMut) -> Result<(), EncodeError>where
    Self: Sized,

`encode_to_vec`

fn encode_to_vec(&self) -> Vec<u8> where
    Self: Sized,

`encode_length_delimited`

fn encode_length_delimited(
    &self,
    buf: &mut impl BufMut,
) -> Result<(), EncodeError>where
    Self: Sized,

`encode_length_delimited_to_vec`

fn encode_length_delimited_to_vec(&self) -> Vec<u8> where
    Self: Sized,

`decode`

fn decode(buf: impl Buf) -> Result<Self, DecodeError>where
    Self: Default,

`decode_length_delimited`

fn decode_length_delimited(buf: impl Buf) -> Result<Self, DecodeError>where
    Self: Default,

`merge`

fn merge(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
    Self: Sized,

`merge_length_delimited`

fn merge_length_delimited(&mut self, buf: impl Buf) -> Result<(), DecodeError>where
    Self: Sized,

`impl Name for AnnotatedLlmRequest`

impl Name for AnnotatedLlmRequest

`NAME`

const NAME: &'static str = "AnnotatedLlmRequest"

`PACKAGE`

const PACKAGE: &'static str = "nvidia.nemo.relay.worker.v1"

`full_name`

fn full_name() -> String

`type_url`

fn type_url() -> String

`impl PartialEq for AnnotatedLlmRequest`

impl PartialEq for AnnotatedLlmRequest

`eq`

fn eq(&self, other: &AnnotatedLlmRequest) -> bool

`ne`

fn ne(&self, other: &Rhs) -> bool

`impl WireValue<AnnotatedLlmRequest> for AnnotatedLlmRequest`

impl WireValue<AnnotatedLlmRequest> for AnnotatedLlmRequest

`to_wire`

fn to_wire(self) -> Result<AnnotatedLlmRequest>

`from_wire`

fn from_wire(value: AnnotatedLlmRequest) -> Result<Self>

`impl StructuralPartialEq for AnnotatedLlmRequest`

impl StructuralPartialEq for AnnotatedLlmRequest