Support similar and dissimilar threshold searches

tests/test_similarity_graph.py

@@ -53,3 +53,11 @@ def test_graph_is_block_size_independent_and_deterministic(
     write_graph_edges(first_path, first.edges)
     write_graph_edges(second_path, repeated.edges)
     assert first_path.read_bytes() == second_path.read_bytes()
+
+
+def test_graph_supports_less_than_threshold_direction(small_dataset: Path) -> None:
+    result = build_similarity_graph(
+        small_dataset, threshold=0.15, block_size=2, threshold_direction="less"
+    )
+
+    assert all(edge.similarity <= 0.15 for edge in result.edges)

tests/test_similarity_search.py

@@ -37,3 +37,22 @@ def test_search_matches_full_sorting_and_skips_query_and_invalid(
     assert "DUPLICATE" not in {match.molecule_id for match in result.matches}
     assert result.stats.invalid == 1
     assert result.stats.valid == 5
+
+
+def test_search_can_rank_and_filter_least_similar_molecules(
+    small_dataset: Path,
+) -> None:
+    query = find_molecule_by_id(small_dataset, "QUERY")
+    result = search_similar(
+        small_dataset,
+        query,
+        top_k=20,
+        threshold=0.2,
+        threshold_direction="less",
+    )
+
+    assert result.matches
+    assert all(match.similarity <= 0.2 for match in result.matches)
+    assert result.matches == sorted(
+        result.matches, key=lambda match: match.sort_key("less")
+    )