wip-sweep

crates/clawhdf5-bench/src/bin/longmemeval_bench.rs

@@ -89,6 +89,26 @@ const HYBRID: Mode = Mode {
     keyword_weight: 0.3,
 };
 
+/// Every 0.1 step of vector weight, keyword weight taking the remainder.
+///
+/// Labels are leaked to `&'static str` because `Mode::label` is a `&'static
+/// str` for the eleven named modes and a sweep is a short-lived process; the
+/// alternative is threading a lifetime through the whole report path for a
+/// diagnostic mode.
+#[cfg(feature = "embeddings")]
+fn sweep_modes() -> Vec<Mode> {
+    (0..=10)
+        .map(|i| {
+            let v = i as f32 / 10.0;
+            Mode {
+                label: Box::leak(format!("sweep v={v:.1} / k={:.1}", 1.0 - v).into_boxed_str()),
+                vector_weight: v,
+                keyword_weight: 1.0 - v,
+            }
+        })
+        .collect()
+}
+
 /// Text -> embedding, built once for the whole corpus.
 type EmbeddingMap = HashMap<String, Vec<f32>>;
 
@@ -651,6 +671,7 @@ fn main() {
     let mut json_path: Option<String> = None;
     let mut limit: Option<usize> = None;
     let mut weights_dir: Option<String> = None;
+    let mut sweep = false;
     let mut args = std::env::args().skip(1);
     while let Some(arg) = args.next() {
         match arg.as_str() {
@@ -658,6 +679,7 @@ fn main() {
                 let v = args.next().expect("--limit needs a value");
                 limit = Some(v.parse().expect("--limit must be a positive integer"));
             }
+            "--sweep" => sweep = true,
             "--embeddings" => {
                 weights_dir = Some(args.next().expect("--embeddings needs a directory"));
             }
@@ -675,7 +697,10 @@ fn main() {
                               and tokenizer.json. Enables the vector stage and reports\n\
                               BM25-only, vector-only, and hybrid separately. Requires\n\
                               --features embeddings; without it the vector stage is\n\
-                              inert and only the BM25 row is produced."
+                              inert and only the BM25 row is produced.\n\
+                     --sweep  instead of the three named modes, sweep vector_weight\n\
+                              from 0.0 to 1.0 in 0.1 steps. The 0.7/0.3 default was\n\
+                              never searched; this is what searches it."
                 );
                 return;
             }
@@ -736,13 +761,20 @@ fn main() {
     let modes: Vec<Mode> = if embeddings.is_some() {
         #[cfg(feature = "embeddings")]
         {
-            vec![BM25_ONLY, VECTOR_ONLY, HYBRID]
+            if sweep {
+                sweep_modes()
+            } else {
+                vec![BM25_ONLY, VECTOR_ONLY, HYBRID]
+            }
         }
         #[cfg(not(feature = "embeddings"))]
         {
             vec![BM25_ONLY]
         }
     } else {
+        if sweep {
+            eprintln!("warning: --sweep needs --embeddings; running BM25 only");
+        }
         vec![BM25_ONLY]
     };