diff --git a/backend/src/services/llm/schema.rs b/backend/src/services/llm/schema.rs
index f137b92..17a244d 100644
--- a/backend/src/services/llm/schema.rs
+++ b/backend/src/services/llm/schema.rs
@@ -107,6 +107,36 @@ pub fn build_classification_schema() -> Value {
})
}
+/// Build a JSON Schema for LLM link extraction response.
+pub fn build_link_extraction_schema() -> Value {
+ serde_json::json!({
+ "type": "object",
+ "properties": {
+ "urls": {
+ "type": "array",
+ "items": { "type": "string" }
+ }
+ },
+ "required": ["urls"],
+ "additionalProperties": false
+ })
+}
+
+/// Build a JSON Schema for LLM article content extraction response.
+pub fn build_article_extraction_schema() -> Value {
+ serde_json::json!({
+ "type": "object",
+ "properties": {
+ "title": { "type": "string", "description": "Article title" },
+ "published_date": { "type": "string", "description": "ISO 8601 date or empty string if not found" },
+ "body_text": { "type": "string", "description": "Main article content" },
+ "is_error_page": { "type": "boolean", "description": "True if this is an error/404 page" }
+ },
+ "required": ["title", "published_date", "body_text", "is_error_page"],
+ "additionalProperties": false
+ })
+}
+
#[cfg(test)]
mod tests {
use super::*;
@@ -299,4 +329,24 @@ mod tests {
assert_eq!(assignments["items"]["additionalProperties"], false);
assert_eq!(schema["additionalProperties"], false);
}
+
+ #[test]
+ fn link_extraction_schema_has_urls_array() {
+ let schema = build_link_extraction_schema();
+ assert_eq!(schema["properties"]["urls"]["type"], "array");
+ assert_eq!(schema["additionalProperties"], false);
+ }
+
+ #[test]
+ fn article_extraction_schema_strict_mode_compatible() {
+ let schema = build_article_extraction_schema();
+ let props = schema["properties"].as_object().unwrap();
+ assert!(props.contains_key("title"));
+ assert!(props.contains_key("published_date"));
+ assert!(props.contains_key("body_text"));
+ assert!(props.contains_key("is_error_page"));
+ assert_eq!(schema["additionalProperties"], false);
+ // published_date is string (not union type) for OpenAI strict mode
+ assert_eq!(props["published_date"]["type"], "string");
+ }
}
diff --git a/backend/src/services/prompts.rs b/backend/src/services/prompts.rs
index 6d13d47..5659664 100644
--- a/backend/src/services/prompts.rs
+++ b/backend/src/services/prompts.rs
@@ -156,6 +156,55 @@ pub fn build_rewrite_prompt(
(system_prompt, user_prompt)
}
+/// Build a prompt for LLM-assisted link extraction from a source page.
+pub fn build_link_extraction_prompt(head_html: &str, body_html: &str) -> (String, String) {
+ let system_prompt =
+ "Tu es un assistant qui analyse des pages web. \
+ Tu dois identifier les liens vers des articles d'actualite. \
+ Reponds uniquement au format JSON demande."
+ .to_string();
+
+ let body_truncated: String = body_html.chars().take(8000).collect();
+
+ let user_prompt = format!(
+ "Voici le contenu HTML d'une page de blog ou de site d'actualites.\n\n\
+ \n{head}\n\n\n\
+ \n{body}\n\n\n\
+ Extrais UNIQUEMENT les URLs qui pointent vers des articles \
+ (pas les liens de navigation, tags, categories, login, pages statiques, etc.).\n\
+ Retourne les URLs completes dans le format JSON demande.",
+ head = head_html,
+ body = body_truncated,
+ );
+
+ (system_prompt, user_prompt)
+}
+
+/// Build a prompt for LLM-assisted article content extraction.
+pub fn build_article_extraction_prompt(head_html: &str, body_text: &str) -> (String, String) {
+ let system_prompt =
+ "Tu es un assistant qui analyse des articles web. \
+ Tu dois extraire les informations structurees de l'article. \
+ Reponds uniquement au format JSON demande."
+ .to_string();
+
+ let user_prompt = format!(
+ "Voici le contenu d'une page web.\n\n\
+ \n{head}\n\n\n\
+ Contenu textuel de la page :\n{body}\n\n\
+ Extrais les informations suivantes :\n\
+ - title : le titre de l'article\n\
+ - published_date : la date de publication au format ISO 8601 (YYYY-MM-DDTHH:MM:SSZ), \
+ ou une chaine vide si introuvable\n\
+ - body_text : le contenu principal de l'article (pas la navigation, pas les pubs)\n\
+ - is_error_page : true si c'est une page d'erreur/404, false sinon",
+ head = head_html,
+ body = body_text,
+ );
+
+ (system_prompt, user_prompt)
+}
+
/// Build a prompt for classifying scraped articles into categories.
///
/// # Arguments
@@ -462,4 +511,27 @@ mod tests {
let (_, user_prompt) = build_search_prompt(&settings, &sources, date, &[], None);
assert!(user_prompt.contains("exactement"));
}
+
+ #[test]
+ fn link_extraction_prompt_includes_html() {
+ let (sys, user) = build_link_extraction_prompt("Blog", "P");
+ assert!(user.contains("Blog"));
+ assert!(user.contains("articles"));
+ assert!(sys.contains("liens"));
+ }
+
+ #[test]
+ fn link_extraction_prompt_truncates_body() {
+ let long_body = "x".repeat(20000);
+ let (_, user) = build_link_extraction_prompt("", &long_body);
+ assert!(user.len() < 15000);
+ }
+
+ #[test]
+ fn article_extraction_prompt_includes_content() {
+ let (_, user) = build_article_extraction_prompt("", "Article body here");
+ assert!(user.contains("Article body here"));
+ assert!(user.contains("published_date"));
+ assert!(user.contains("is_error_page"));
+ }
}