router-spec: Reorder ChatCompletionRequest and fix validation logic (#10675)
This commit is contained in:
Chang Su
@@ -179,26 +179,94 @@ pub struct FunctionCallDelta {
|
||||
|
||||
// ============= Request =============
|
||||
|
||||
#[derive(Debug, Clone, Deserialize, Serialize)]
|
||||
#[derive(Debug, Clone, Deserialize, Serialize, Default)]
|
||||
pub struct ChatCompletionRequest {
|
||||
/// ID of the model to use
|
||||
pub model: String,
|
||||
|
||||
/// A list of messages comprising the conversation so far
|
||||
pub messages: Vec<ChatMessage>,
|
||||
|
||||
/// What sampling temperature to use, between 0 and 2
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub temperature: Option<f32>,
|
||||
/// ID of the model to use
|
||||
pub model: String,
|
||||
|
||||
/// An alternative to sampling with temperature
|
||||
/// Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub top_p: Option<f32>,
|
||||
pub frequency_penalty: Option<f32>,
|
||||
|
||||
/// Deprecated: Replaced by tool_choice
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
#[deprecated(note = "Use tool_choice instead")]
|
||||
pub function_call: Option<FunctionCall>,
|
||||
|
||||
/// Deprecated: Replaced by tools
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
#[deprecated(note = "Use tools instead")]
|
||||
pub functions: Option<Vec<Function>>,
|
||||
|
||||
/// Modify the likelihood of specified tokens appearing in the completion
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub logit_bias: Option<HashMap<String, f32>>,
|
||||
|
||||
/// Whether to return log probabilities of the output tokens
|
||||
#[serde(default)]
|
||||
pub logprobs: bool,
|
||||
|
||||
/// Deprecated: Replaced by max_completion_tokens
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
#[deprecated(note = "Use max_completion_tokens instead")]
|
||||
pub max_tokens: Option<u32>,
|
||||
|
||||
/// An upper bound for the number of tokens that can be generated for a completion
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub max_completion_tokens: Option<u32>,
|
||||
|
||||
/// Developer-defined tags and values used for filtering completions in the dashboard
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub metadata: Option<HashMap<String, String>>,
|
||||
|
||||
/// Output types that you would like the model to generate for this request
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub modalities: Option<Vec<String>>,
|
||||
|
||||
/// How many chat completion choices to generate for each input message
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub n: Option<u32>,
|
||||
|
||||
/// Whether to enable parallel function calling during tool use
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub parallel_tool_calls: Option<bool>,
|
||||
|
||||
/// Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub presence_penalty: Option<f32>,
|
||||
|
||||
/// Cache key for prompts (beta feature)
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub prompt_cache_key: Option<String>,
|
||||
|
||||
/// Effort level for reasoning models (low, medium, high)
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub reasoning_effort: Option<String>,
|
||||
|
||||
/// An object specifying the format that the model must output
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub response_format: Option<ResponseFormat>,
|
||||
|
||||
/// Safety identifier for content moderation
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub safety_identifier: Option<String>,
|
||||
|
||||
/// Deprecated: This feature is in Legacy mode
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
#[deprecated(note = "This feature is in Legacy mode")]
|
||||
pub seed: Option<i64>,
|
||||
|
||||
/// The service tier to use for this request
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub service_tier: Option<String>,
|
||||
|
||||
/// Up to 4 sequences where the API will stop generating further tokens
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub stop: Option<StringOrArray>,
|
||||
|
||||
/// If set, partial message deltas will be sent
|
||||
#[serde(default)]
|
||||
pub stream: bool,
|
||||
@@ -207,69 +275,29 @@ pub struct ChatCompletionRequest {
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub stream_options: Option<StreamOptions>,
|
||||
|
||||
/// Up to 4 sequences where the API will stop generating further tokens
|
||||
/// What sampling temperature to use, between 0 and 2
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub stop: Option<StringOrArray>,
|
||||
|
||||
/// The maximum number of tokens to generate
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub max_tokens: Option<u32>,
|
||||
|
||||
/// An upper bound for the number of tokens that can be generated for a completion
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub max_completion_tokens: Option<u32>,
|
||||
|
||||
/// Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub presence_penalty: Option<f32>,
|
||||
|
||||
/// Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub frequency_penalty: Option<f32>,
|
||||
|
||||
/// Modify the likelihood of specified tokens appearing in the completion
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub logit_bias: Option<HashMap<String, f32>>,
|
||||
|
||||
/// A unique identifier representing your end-user
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub user: Option<String>,
|
||||
|
||||
/// If specified, our system will make a best effort to sample deterministically
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub seed: Option<i64>,
|
||||
|
||||
/// Whether to return log probabilities of the output tokens
|
||||
#[serde(default)]
|
||||
pub logprobs: bool,
|
||||
|
||||
/// An integer between 0 and 20 specifying the number of most likely tokens to return
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub top_logprobs: Option<u32>,
|
||||
|
||||
/// An object specifying the format that the model must output
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub response_format: Option<ResponseFormat>,
|
||||
|
||||
/// A list of tools the model may call
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub tools: Option<Vec<Tool>>,
|
||||
pub temperature: Option<f32>,
|
||||
|
||||
/// Controls which (if any) tool is called by the model
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub tool_choice: Option<ToolChoice>,
|
||||
|
||||
/// Whether to enable parallel function calling during tool use
|
||||
/// A list of tools the model may call
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub parallel_tool_calls: Option<bool>,
|
||||
pub tools: Option<Vec<Tool>>,
|
||||
|
||||
/// Deprecated: use tools instead
|
||||
/// An integer between 0 and 20 specifying the number of most likely tokens to return
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub functions: Option<Vec<Function>>,
|
||||
pub top_logprobs: Option<u32>,
|
||||
|
||||
/// Deprecated: use tool_choice instead
|
||||
/// An alternative to sampling with temperature
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub function_call: Option<FunctionCall>,
|
||||
pub top_p: Option<f32>,
|
||||
|
||||
/// Verbosity level for debugging
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub verbosity: Option<i32>,
|
||||
|
||||
// ============= SGLang Extensions =============
|
||||
/// Top-k sampling parameter (-1 to disable)
|
||||
@@ -316,7 +344,6 @@ pub struct ChatCompletionRequest {
|
||||
#[serde(default = "default_true")]
|
||||
pub skip_special_tokens: bool,
|
||||
|
||||
// ============= SGLang Extensions =============
|
||||
/// Path to LoRA adapter(s) for model customization
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub lora_path: Option<LoRAPath>,
|
||||
|
||||
Reference in New Issue
Block a user