From e0841307d4da809754d995a4524b39b87040f2d0 Mon Sep 17 00:00:00 2001
From: Antonio Sarosi <sarosiantonio@gmail.com>
Date: Mon, 11 Nov 2024 19:12:25 +0000
Subject: [PATCH] Add basic grammar for `a` vs `an` articles (#1158)

<!-- ELLIPSIS_HIDDEN -->



> [!IMPORTANT]
> Add function to determine 'a' or 'an' for indefinite articles and
integrate it into output format rendering logic.
>
>   - **Behavior**:
> - Add `indefinite_article_a_or_an()` function in `types.rs` to
determine 'a' or 'an' based on the first letter of a word.
> - Update `OutputFormatContent::prefix()` to use
`indefinite_article_a_or_an()` for primitive types.
>   - **Documentation**:
> - Update `output-format.mdx` to reflect changes in default prefixes
for primitive types.
>   - **Tests**:
> - Add tests `render_int()` and `render_float()` in `types.rs` to
verify correct article usage.
>
> <sup>This description was created by </sup>[<img alt="Ellipsis"
src="https://img.shields.io/badge/Ellipsis-blue?color=175173">](https://www.ellipsis.dev?ref=BoundaryML%2Fbaml&utm_source=github&utm_medium=referral)<sup>
for 7c264361d2e7564f1bde87a4ffe4146fe8951695. It will automatically
update as commits are pushed.</sup>

<!-- ELLIPSIS_HIDDEN -->
---
 .../jinja-runtime/src/output_format/types.rs  | 29 ++++++++++++++++++-
 .../baml/prompt-syntax/output-format.mdx      |  3 +-
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/engine/baml-lib/jinja-runtime/src/output_format/types.rs b/engine/baml-lib/jinja-runtime/src/output_format/types.rs
index d1fe52dcc..23f1d50ae 100644
--- a/engine/baml-lib/jinja-runtime/src/output_format/types.rs
+++ b/engine/baml-lib/jinja-runtime/src/output_format/types.rs
@@ -285,6 +285,16 @@ impl<'s> std::fmt::Display for MapRender<'s> {
     }
 }
 
+/// Basic grammar for "a" VS "an" indefinite articles.
+///
+/// It does NOT cover all rules & exceptions.
+fn indefinite_article_a_or_an(word: &str) -> &str {
+    match word.chars().next() {
+        Some(c) if matches!(c.to_ascii_lowercase(), 'a' | 'e' | 'i' | 'o' | 'u') => "an",
+        _ => "a",
+    }
+}
+
 struct RenderState {
     hoisted_enums: IndexSet<String>,
 }
@@ -302,7 +312,10 @@ impl OutputFormatContent {
         ) -> Option<String> {
             match ft {
                 FieldType::Primitive(TypeValue::String) => None,
-                FieldType::Primitive(_) => Some(String::from("Answer as a: ")),
+                FieldType::Primitive(p) => Some(format!(
+                    "Answer as {article} ",
+                    article = indefinite_article_a_or_an(&p.to_string())
+                )),
                 FieldType::Literal(_) => Some(String::from("Answer using this specific value:\n")),
                 FieldType::Enum(_) => Some(String::from("Answer with any of the categories:\n")),
                 FieldType::Class(cls) => {
@@ -659,6 +672,20 @@ mod tests {
         assert_eq!(rendered, None);
     }
 
+    #[test]
+    fn render_int() {
+        let content = OutputFormatContent::target(FieldType::int()).build();
+        let rendered = content.render(RenderOptions::default()).unwrap();
+        assert_eq!(rendered, Some("Answer as an int".into()));
+    }
+
+    #[test]
+    fn render_float() {
+        let content = OutputFormatContent::target(FieldType::float()).build();
+        let rendered = content.render(RenderOptions::default()).unwrap();
+        assert_eq!(rendered, Some("Answer as a float".into()));
+    }
+
     #[test]
     fn render_array() {
         let content = OutputFormatContent::new_array();
diff --git a/fern/03-reference/baml/prompt-syntax/output-format.mdx b/fern/03-reference/baml/prompt-syntax/output-format.mdx
index 26b70cfcb..a632b43ba 100644
--- a/fern/03-reference/baml/prompt-syntax/output-format.mdx
+++ b/fern/03-reference/baml/prompt-syntax/output-format.mdx
@@ -71,7 +71,8 @@ BAML's default prefix varies based on the function's return type.
 | Fuction return type | Default Prefix |
 | --- | --- |
 | Primitive (String) |  |
-| Primitive (Other) | `Answer as a: ` |
+| Primitive (Int) | `Answer as an ` |
+| Primitive (Other) | `Answer as a ` |
 | Enum | `Answer with any of the categories:\n` |
 | Class | `Answer in JSON using this schema:\n` |
 | List | `Answer with a JSON Array using this schema:\n` |