fix: use rawPredict for non-streaming Claude requests

src/client/vertexai.rs

@@ -119,7 +119,11 @@ fn prepare_chat_completions(
             format!("{base_url}/google/models/{model_name}:{func}")
         }
         ModelCategory::Claude => {
-            format!("{base_url}/anthropic/models/{model_name}:streamRawPredict")
+            let func = match data.stream {
+                true => "streamRawPredict",
+                false => "rawPredict",
+            };
+            format!("{base_url}/anthropic/models/{model_name}:{func}")
         }
         ModelCategory::Mistral => {
             let func = match data.stream {

src/rag/mod.rs

@@ -16,8 +16,8 @@ use parking_lot::RwLock;
 use serde::{Deserialize, Serialize};
 use serde_json::json;
 use std::{
-    collections::HashMap, env, fmt, fmt::Debug, fs, hash::Hash, path::Path, sync::Arc,
+    cmp::Ordering, collections::HashMap, env, fmt, fmt::Debug, fs, hash::Hash, path::Path,
-    time::Duration,
+    sync::Arc, time::Duration,
 };
 use tokio::time::sleep;
 
@@ -1196,7 +1196,7 @@ fn reciprocal_rank_fusion(
         }
     }
     let mut sorted_items: Vec<(DocumentId, f32)> = map.into_iter().collect();
-    sorted_items.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap());
+    sorted_items.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap_or(Ordering::Equal));
 
     sorted_items
         .into_iter()