From dfa5e41ea6fa37f1d5df6710da543b00050417d9 Mon Sep 17 00:00:00 2001
From: Louis Dureuil <louis@meilisearch.com>
Date: Mon, 25 Mar 2024 10:05:58 +0100
Subject: [PATCH] Check validity of the URL setting

---
 Cargo.lock                                 | 1 +
 meilisearch-types/src/error.rs             | 1 +
 meilisearch/src/routes/indexes/settings.rs | 1 +
 milli/Cargo.toml                           | 1 +
 milli/src/error.rs                         | 2 ++
 milli/src/update/settings.rs               | 8 ++++++++
 6 files changed, 14 insertions(+)

diff --git a/Cargo.lock b/Cargo.lock
index 6a8c20f12..214ba368f 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -3376,6 +3376,7 @@ dependencies = [
  "tokenizers",
  "tracing",
  "ureq",
+ "url",
  "uuid",
 ]
 
diff --git a/meilisearch-types/src/error.rs b/meilisearch-types/src/error.rs
index aed77411a..1b94201f2 100644
--- a/meilisearch-types/src/error.rs
+++ b/meilisearch-types/src/error.rs
@@ -353,6 +353,7 @@ impl ErrorCode for milli::Error {
                     | UserError::InvalidOpenAiModelDimensions { .. }
                     | UserError::InvalidOpenAiModelDimensionsMax { .. }
                     | UserError::InvalidSettingsDimensions { .. }
+                    | UserError::InvalidUrl { .. }
                     | UserError::InvalidPrompt(_) => Code::InvalidSettingsEmbedders,
                     UserError::TooManyEmbedders(_) => Code::InvalidSettingsEmbedders,
                     UserError::InvalidPromptForEmbeddings(..) => Code::InvalidSettingsEmbedders,
diff --git a/meilisearch/src/routes/indexes/settings.rs b/meilisearch/src/routes/indexes/settings.rs
index 5dabd7b0d..99c3d0fbb 100644
--- a/meilisearch/src/routes/indexes/settings.rs
+++ b/meilisearch/src/routes/indexes/settings.rs
@@ -605,6 +605,7 @@ fn embedder_analytics(
                 EmbedderSource::HuggingFace => sources.insert("huggingFace"),
                 EmbedderSource::UserProvided => sources.insert("userProvided"),
                 EmbedderSource::Ollama => sources.insert("ollama"),
+                EmbedderSource::Rest => sources.insert("rest"),
             };
         }
     };
diff --git a/milli/Cargo.toml b/milli/Cargo.toml
index 4833ad00b..9f5803f4e 100644
--- a/milli/Cargo.toml
+++ b/milli/Cargo.toml
@@ -86,6 +86,7 @@ arroy = "0.2.0"
 rand = "0.8.5"
 tracing = "0.1.40"
 ureq = { version = "2.9.6", features = ["json"] }
+url = "2.5.0"
 
 [dev-dependencies]
 mimalloc = { version = "0.1.39", default-features = false }
diff --git a/milli/src/error.rs b/milli/src/error.rs
index 1147085dd..aba80b475 100644
--- a/milli/src/error.rs
+++ b/milli/src/error.rs
@@ -243,6 +243,8 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
     },
     #[error("`.embedders.{embedder_name}.dimensions`: `dimensions` cannot be zero")]
     InvalidSettingsDimensions { embedder_name: String },
+    #[error("`.embedders.{embedder_name}.url`: could not parse `{url}`: {inner_error}")]
+    InvalidUrl { embedder_name: String, inner_error: url::ParseError, url: String },
 }
 
 impl From<crate::vector::Error> for Error {
diff --git a/milli/src/update/settings.rs b/milli/src/update/settings.rs
index 4c7289eb7..e902badc0 100644
--- a/milli/src/update/settings.rs
+++ b/milli/src/update/settings.rs
@@ -1199,6 +1199,14 @@ pub fn validate_embedding_settings(
         .into());
     }
 
+    if let Some(url) = url.as_ref().set() {
+        url::Url::parse(url).map_err(|error| crate::error::UserError::InvalidUrl {
+            embedder_name: name.to_owned(),
+            inner_error: error,
+            url: url.to_owned(),
+        })?;
+    }
+
     let Some(inferred_source) = source.set() else {
         return Ok(Setting::Set(EmbeddingSettings {
             source,