Changing back this logprobs default.

router/src/lib.rs

@@ -782,7 +782,7 @@ pub(crate) struct ChatRequest {
     /// output token returned in the content of message.
     #[serde(default)]
     #[schema(example = "false")]
-    pub logprobs: bool,
+    pub logprobs: Option<bool>,
 
     /// An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with
     /// an associated log probability. logprobs must be set to true if this parameter is used.

router/src/server.rs

@@ -1123,6 +1123,8 @@ async fn chat_completions(
     let (generate_request, using_tools): (GenerateRequest, bool) =
         chat.try_into_generate(&infer)?;
 
+    let logprobs = logprobs.unwrap_or_default();
+
     // static values that will be returned in all cases
     let model_id = info.model_id.clone();
     let system_fingerprint = format!("{}-{}", info.version, info.docker_label.unwrap_or("native"));

router/src/vertex.rs

@@ -56,7 +56,7 @@ pub(crate) struct VertexParameters {
     /// output token returned in the content of message.
     #[serde(default)]
     #[schema(example = "false")]
-    pub logprobs: bool,
+    pub logprobs: Option<bool>,
 
     /// An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with
     /// an associated log probability. logprobs must be set to true if this parameter is used.