diff --git a/crates/index-scheduler/src/batch.rs b/crates/index-scheduler/src/batch.rs
index 903ec1217..44b4663e2 100644
--- a/crates/index-scheduler/src/batch.rs
+++ b/crates/index-scheduler/src/batch.rs
@@ -627,6 +627,8 @@ impl IndexScheduler {
             self.breakpoint(crate::Breakpoint::InsideProcessBatch);
         }
 
+        let index_uid = batch.index_uid().map(String::from);
+
         match batch {
             Batch::TaskCancelation { mut task, previous_started_at, previous_processing_tasks } => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -765,7 +767,9 @@ impl IndexScheduler {
                     let index = self.index_mapper.index(&rtxn, name)?;
                     let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
                     fs::create_dir_all(&dst)?;
-                    index.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
+                    index
+                        .copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)
+                        .map_err(|e| Error::from_milli(e, Some(name.to_string())))?;
                 }
 
                 drop(rtxn);
@@ -843,7 +847,6 @@ impl IndexScheduler {
                     let (_, mut t) = ret?;
                     let status = t.status;
                     let content_file = t.content_uuid();
-
                     // In the case we're dumping ourselves we want to be marked as finished
                     // to not loop over ourselves indefinitely.
                     if t.uid == task.uid {
@@ -866,19 +869,21 @@ impl IndexScheduler {
                         if status == Status::Enqueued {
                             let content_file = self.file_store.get_update(content_file)?;
 
-                            let reader = DocumentsBatchReader::from_reader(content_file)
-                                .map_err(milli::Error::from)?;
+                            let reader =
+                                DocumentsBatchReader::from_reader(content_file).map_err(|e| {
+                                    Error::Milli { error: e.into(), index_name: index_uid.clone() }
+                                })?;
 
                             let (mut cursor, documents_batch_index) =
                                 reader.into_cursor_and_fields_index();
 
-                            while let Some(doc) =
-                                cursor.next_document().map_err(milli::Error::from)?
-                            {
-                                dump_content_file.push_document(&obkv_to_object(
-                                    &doc,
-                                    &documents_batch_index,
-                                )?)?;
+                            while let Some(doc) = cursor.next_document().map_err(|e| {
+                                Error::Milli { error: e.into(), index_name: index_uid.clone() }
+                            })? {
+                                dump_content_file.push_document(
+                                    &obkv_to_object(&doc, &documents_batch_index)
+                                        .map_err(|e| Error::from_milli(e, index_uid.clone()))?,
+                                )?;
                             }
                             dump_content_file.flush()?;
                         }
@@ -892,27 +897,41 @@ impl IndexScheduler {
                     let metadata = IndexMetadata {
                         uid: uid.to_owned(),
                         primary_key: index.primary_key(&rtxn)?.map(String::from),
-                        created_at: index.created_at(&rtxn)?,
-                        updated_at: index.updated_at(&rtxn)?,
+                        created_at: index
+                            .created_at(&rtxn)
+                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
+                        updated_at: index
+                            .updated_at(&rtxn)
+                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
                     };
                     let mut index_dumper = dump.create_index(uid, &metadata)?;
 
                     let fields_ids_map = index.fields_ids_map(&rtxn)?;
                     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
-                    let embedding_configs = index.embedding_configs(&rtxn)?;
+                    let embedding_configs = index
+                        .embedding_configs(&rtxn)
+                        .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                    let documents = index
+                        .all_documents(&rtxn)
+                        .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
 
                     // 3.1. Dump the documents
-                    for ret in index.all_documents(&rtxn)? {
+                    for ret in documents {
                         if self.must_stop_processing.get() {
                             return Err(Error::AbortedTask);
                         }
 
-                        let (id, doc) = ret?;
+                        let (id, doc) =
+                            ret.map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
 
-                        let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
+                        let mut document =
+                            milli::obkv_to_json(&all_fields, &fields_ids_map, doc)
+                                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
 
                         'inject_vectors: {
-                            let embeddings = index.embeddings(&rtxn, id)?;
+                            let embeddings = index
+                                .embeddings(&rtxn, id)
+                                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
 
                             if embeddings.is_empty() {
                                 break 'inject_vectors;
@@ -923,22 +942,24 @@ impl IndexScheduler {
                                 .or_insert(serde_json::Value::Object(Default::default()));
 
                             let serde_json::Value::Object(vectors) = vectors else {
-                                return Err(milli::Error::UserError(
-                                    milli::UserError::InvalidVectorsMapType {
-                                        document_id: {
-                                            if let Ok(Some(Ok(index))) = index
-                                                .external_id_of(&rtxn, std::iter::once(id))
-                                                .map(|it| it.into_iter().next())
-                                            {
-                                                index
-                                            } else {
-                                                format!("internal docid={id}")
-                                            }
+                                return Err(Error::from_milli(
+                                    milli::Error::UserError(
+                                        milli::UserError::InvalidVectorsMapType {
+                                            document_id: {
+                                                if let Ok(Some(Ok(index))) = index
+                                                    .external_id_of(&rtxn, std::iter::once(id))
+                                                    .map(|it| it.into_iter().next())
+                                                {
+                                                    index
+                                                } else {
+                                                    format!("internal docid={id}")
+                                                }
+                                            },
+                                            value: vectors.clone(),
                                         },
-                                        value: vectors.clone(),
-                                    },
-                                )
-                                .into());
+                                    ),
+                                    Some(uid.to_string()),
+                                ));
                             };
 
                             for (embedder_name, embeddings) in embeddings {
@@ -968,7 +989,8 @@ impl IndexScheduler {
                         index,
                         &rtxn,
                         meilisearch_types::settings::SecretPolicy::RevealSecrets,
-                    )?;
+                    )
+                    .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
                     index_dumper.settings(&settings)?;
                     Ok(())
                 })?;
@@ -1018,7 +1040,8 @@ impl IndexScheduler {
                 // the entire batch.
                 let res = || -> Result<()> {
                     let index_rtxn = index.read_txn()?;
-                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
+                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                     let mut wtxn = self.env.write_txn()?;
                     self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
                     wtxn.commit()?;
@@ -1057,10 +1080,12 @@ impl IndexScheduler {
                     );
                     builder.set_primary_key(primary_key);
                     let must_stop_processing = self.must_stop_processing.clone();
-                    builder.execute(
-                        |indexing_step| tracing::debug!(update = ?indexing_step),
-                        || must_stop_processing.get(),
-                    )?;
+                    builder
+                        .execute(
+                            |indexing_step| tracing::debug!(update = ?indexing_step),
+                            || must_stop_processing.get(),
+                        )
+                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                     index_wtxn.commit()?;
                 }
 
@@ -1077,7 +1102,8 @@ impl IndexScheduler {
                 let res = || -> Result<()> {
                     let mut wtxn = self.env.write_txn()?;
                     let index_rtxn = index.read_txn()?;
-                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
+                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                     self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
                     wtxn.commit()?;
                     Ok(())
@@ -1100,7 +1126,9 @@ impl IndexScheduler {
                 let number_of_documents = || -> Result<u64> {
                     let index = self.index_mapper.index(&wtxn, &index_uid)?;
                     let index_rtxn = index.read_txn()?;
-                    Ok(index.number_of_documents(&index_rtxn)?)
+                    index
+                        .number_of_documents(&index_rtxn)
+                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))
                 }()
                 .unwrap_or_default();
 
@@ -1219,8 +1247,10 @@ impl IndexScheduler {
         operation: IndexOperation,
     ) -> Result<Vec<Task>> {
         match operation {
-            IndexOperation::DocumentClear { mut tasks, .. } => {
-                let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;
+            IndexOperation::DocumentClear { index_uid, mut tasks, .. } => {
+                let count = milli::update::ClearDocuments::new(index_wtxn, index)
+                    .execute()
+                    .map_err(|e| Error::from_milli(e, Some(index_uid)))?;
 
                 let mut first_clear_found = false;
                 for task in &mut tasks {
@@ -1240,7 +1270,7 @@ impl IndexScheduler {
                 Ok(tasks)
             }
             IndexOperation::DocumentOperation {
-                index_uid: _,
+                index_uid,
                 primary_key,
                 method,
                 documents_counts: _,
@@ -1258,10 +1288,11 @@ impl IndexScheduler {
                         // but to a different value, we can make the whole batch fail.
                         Some(pk) => {
                             if primary_key != pk {
-                                return Err(milli::Error::from(
-                                    milli::UserError::PrimaryKeyCannotBeChanged(pk.to_string()),
-                                )
-                                .into());
+                                return Err(Error::from_milli(
+                                    milli::UserError::PrimaryKeyCannotBeChanged(pk.to_string())
+                                        .into(),
+                                    Some(index_uid.clone()),
+                                ));
                             }
                         }
                         // if the primary key was set and there was no primary key set for this index
@@ -1270,10 +1301,12 @@ impl IndexScheduler {
                             let mut builder =
                                 milli::update::Settings::new(index_wtxn, index, indexer_config);
                             builder.set_primary_key(primary_key);
-                            builder.execute(
-                                |indexing_step| tracing::debug!(update = ?indexing_step),
-                                || must_stop_processing.clone().get(),
-                            )?;
+                            builder
+                                .execute(
+                                    |indexing_step| tracing::debug!(update = ?indexing_step),
+                                    || must_stop_processing.clone().get(),
+                                )
+                                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                             primary_key_has_been_set = true;
                         }
                     }
@@ -1281,9 +1314,11 @@ impl IndexScheduler {
 
                 let config = IndexDocumentsConfig { update_method: method, ..Default::default() };
 
-                let embedder_configs = index.embedding_configs(index_wtxn)?;
+                let embedder_configs = index
+                    .embedding_configs(index_wtxn)
+                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                 // TODO: consider Arc'ing the map too (we only need read access + we'll be cloning it multiple times, so really makes sense)
-                let embedders = self.embedders(embedder_configs)?;
+                let embedders = self.embedders(index_uid.clone(), embedder_configs)?;
 
                 let mut builder = milli::update::IndexDocuments::new(
                     index_wtxn,
@@ -1292,15 +1327,20 @@ impl IndexScheduler {
                     config,
                     |indexing_step| tracing::trace!(?indexing_step, "Update"),
                     || must_stop_processing.get(),
-                )?;
+                )
+                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
 
                 for (operation, task) in operations.into_iter().zip(tasks.iter_mut()) {
                     match operation {
                         DocumentOperation::Add(content_uuid) => {
                             let content_file = self.file_store.get_update(content_uuid)?;
-                            let reader = DocumentsBatchReader::from_reader(content_file)
-                                .map_err(milli::Error::from)?;
-                            let (new_builder, user_result) = builder.add_documents(reader)?;
+                            let reader =
+                                DocumentsBatchReader::from_reader(content_file).map_err(|e| {
+                                    Error::from_milli(e.into(), Some(index_uid.clone()))
+                                })?;
+                            let (new_builder, user_result) = builder
+                                .add_documents(reader)
+                                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                             builder = new_builder;
 
                             builder = builder.with_embedders(embedders.clone());
@@ -1336,8 +1376,9 @@ impl IndexScheduler {
                             }
                         }
                         DocumentOperation::Delete(document_ids) => {
-                            let (new_builder, user_result) =
-                                builder.remove_documents(document_ids)?;
+                            let (new_builder, user_result) = builder
+                                .remove_documents(document_ids)
+                                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                             builder = new_builder;
                             // Uses Invariant: remove documents actually always returns Ok for the inner result
                             let count = user_result.unwrap();
@@ -1361,7 +1402,8 @@ impl IndexScheduler {
                 }
 
                 if !tasks.iter().all(|res| res.error.is_some()) {
-                    let addition = builder.execute()?;
+                    let addition =
+                        builder.execute().map_err(|e| Error::from_milli(e, Some(index_uid)))?;
                     tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 } else if primary_key_has_been_set {
                     // Everything failed but we've set a primary key.
@@ -1369,15 +1411,17 @@ impl IndexScheduler {
                     let mut builder =
                         milli::update::Settings::new(index_wtxn, index, indexer_config);
                     builder.reset_primary_key();
-                    builder.execute(
-                        |indexing_step| tracing::trace!(update = ?indexing_step),
-                        || must_stop_processing.clone().get(),
-                    )?;
+                    builder
+                        .execute(
+                            |indexing_step| tracing::trace!(update = ?indexing_step),
+                            || must_stop_processing.clone().get(),
+                        )
+                        .map_err(|e| Error::from_milli(e, Some(index_uid)))?;
                 }
 
                 Ok(tasks)
             }
-            IndexOperation::DocumentEdition { mut task, .. } => {
+            IndexOperation::DocumentEdition { index_uid, mut task } => {
                 let (filter, context, function) =
                     if let KindWithContent::DocumentEdition {
                         filter_expr, context, function, ..
@@ -1395,7 +1439,14 @@ impl IndexScheduler {
                     self.index_mapper.indexer_config(),
                     self.must_stop_processing.clone(),
                     index,
-                );
+                )
+                .map_err(|err| match err {
+                    milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
+                        Error::from_milli(err, Some(index_uid.clone()))
+                            .with_custom_error_code(Code::InvalidDocumentFilter)
+                    }
+                    e => Error::from_milli(e, Some(index_uid.clone())),
+                });
                 let (original_filter, context, function) = if let Some(Details::DocumentEdition {
                     original_filter,
                     context,
@@ -1435,7 +1486,7 @@ impl IndexScheduler {
 
                 Ok(vec![task])
             }
-            IndexOperation::DocumentDeletion { mut tasks, index_uid: _ } => {
+            IndexOperation::DocumentDeletion { mut tasks, index_uid } => {
                 let mut to_delete = RoaringBitmap::new();
                 let external_documents_ids = index.external_documents_ids();
 
@@ -1456,7 +1507,7 @@ impl IndexScheduler {
                                 deleted_documents: Some(will_be_removed),
                             });
                         }
-                        KindWithContent::DocumentDeletionByFilter { index_uid: _, filter_expr } => {
+                        KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } => {
                             let before = to_delete.len();
                             let filter = match Filter::from_json(filter_expr) {
                                 Ok(filter) => filter,
@@ -1467,7 +1518,7 @@ impl IndexScheduler {
                                         milli::Error::UserError(
                                             milli::UserError::InvalidFilterExpression { .. },
                                         ) => Some(
-                                            Error::from(err)
+                                            Error::from_milli(err, Some(index_uid.clone()))
                                                 .with_custom_error_code(Code::InvalidDocumentFilter)
                                                 .into(),
                                         ),
@@ -1481,9 +1532,9 @@ impl IndexScheduler {
                                     filter.evaluate(index_wtxn, index).map_err(|err| match err {
                                         milli::Error::UserError(
                                             milli::UserError::InvalidFilter(_),
-                                        ) => Error::from(err)
+                                        ) => Error::from_milli(err, Some(index_uid.clone()))
                                             .with_custom_error_code(Code::InvalidDocumentFilter),
-                                        e => e.into(),
+                                        e => Error::from_milli(e, Some(index_uid.clone())),
                                     });
                                 match candidates {
                                     Ok(candidates) => to_delete |= candidates,
@@ -1522,17 +1573,21 @@ impl IndexScheduler {
                     config,
                     |indexing_step| tracing::debug!(update = ?indexing_step),
                     || must_stop_processing.get(),
-                )?;
+                )
+                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
 
                 let (new_builder, _count) =
-                    builder.remove_documents_from_db_no_batch(&to_delete)?;
+                    builder
+                        .remove_documents_from_db_no_batch(&to_delete)
+                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                 builder = new_builder;
 
-                let _ = builder.execute()?;
+                let _ =
+                    builder.execute().map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
 
                 Ok(tasks)
             }
-            IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
+            IndexOperation::Settings { index_uid, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
                 let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config);
 
@@ -1547,10 +1602,12 @@ impl IndexScheduler {
                 }
 
                 let must_stop_processing = self.must_stop_processing.clone();
-                builder.execute(
-                    |indexing_step| tracing::debug!(update = ?indexing_step),
-                    || must_stop_processing.get(),
-                )?;
+                builder
+                    .execute(
+                        |indexing_step| tracing::debug!(update = ?indexing_step),
+                        || must_stop_processing.get(),
+                    )
+                    .map_err(|e| Error::from_milli(e, Some(index_uid)))?;
 
                 Ok(tasks)
             }
@@ -1742,16 +1799,11 @@ fn edit_documents_by_function<'a>(
     indexer_config: &IndexerConfig,
     must_stop_processing: MustStopProcessing,
     index: &'a Index,
-) -> Result<(u64, u64)> {
+) -> milli::Result<(u64, u64)> {
     let candidates = match filter.as_ref().map(Filter::from_json) {
-        Some(Ok(Some(filter))) => filter.evaluate(wtxn, index).map_err(|err| match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            e => e.into(),
-        })?,
+        Some(Ok(Some(filter))) => filter.evaluate(wtxn, index)?,
         None | Some(Ok(None)) => index.documents_ids(wtxn)?,
-        Some(Err(e)) => return Err(e.into()),
+        Some(Err(e)) => return Err(e),
     };
 
     let config = IndexDocumentsConfig {
diff --git a/crates/index-scheduler/src/error.rs b/crates/index-scheduler/src/error.rs
index 3bd378fd6..91579fd68 100644
--- a/crates/index-scheduler/src/error.rs
+++ b/crates/index-scheduler/src/error.rs
@@ -117,8 +117,11 @@ pub enum Error {
     Dump(#[from] dump::Error),
     #[error(transparent)]
     Heed(#[from] heed::Error),
-    #[error(transparent)]
-    Milli(#[from] milli::Error),
+    #[error("{}", match .index_name {
+        Some(name) if !name.is_empty() => format!("Index `{}`: {error}", name),
+        _ => format!("{error}")
+    })]
+    Milli { error: milli::Error, index_name: Option<String> },
     #[error("An unexpected crash occurred when processing the task.")]
     ProcessBatchPanicked,
     #[error(transparent)]
@@ -183,7 +186,7 @@ impl Error {
             | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
-            | Error::Milli(_)
+            | Error::Milli { .. }
             | Error::ProcessBatchPanicked
             | Error::FileStore(_)
             | Error::IoError(_)
@@ -202,6 +205,10 @@ impl Error {
     pub fn with_custom_error_code(self, code: Code) -> Self {
         Self::WithCustomErrorCode(code, Box::new(self))
     }
+
+    pub fn from_milli(error: milli::Error, index_name: Option<String>) -> Self {
+        Self::Milli { error, index_name }
+    }
 }
 
 impl ErrorCode for Error {
@@ -227,7 +234,7 @@ impl ErrorCode for Error {
             // TODO: not sure of the Code to use
             Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
             Error::Dump(e) => e.error_code(),
-            Error::Milli(e) => e.error_code(),
+            Error::Milli { error, .. } => error.error_code(),
             Error::ProcessBatchPanicked => Code::Internal,
             Error::Heed(e) => e.error_code(),
             Error::HeedTransaction(e) => e.error_code(),
diff --git a/crates/index-scheduler/src/index_mapper/index_map.rs b/crates/index-scheduler/src/index_mapper/index_map.rs
index f8080d23b..480dafa7c 100644
--- a/crates/index-scheduler/src/index_mapper/index_map.rs
+++ b/crates/index-scheduler/src/index_mapper/index_map.rs
@@ -3,14 +3,13 @@ use std::path::Path;
 use std::time::Duration;
 
 use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
-use meilisearch_types::milli::Index;
+use meilisearch_types::milli::{Index, Result};
 use time::OffsetDateTime;
 use uuid::Uuid;
 
 use super::IndexStatus::{self, Available, BeingDeleted, Closing, Missing};
+use crate::clamp_to_page_size;
 use crate::lru::{InsertionOutcome, LruMap};
-use crate::{clamp_to_page_size, Result};
-
 /// Keep an internally consistent view of the open indexes in memory.
 ///
 /// This view is made of an LRU cache that will evict the least frequently used indexes when new indexes are opened.
diff --git a/crates/index-scheduler/src/index_mapper/mod.rs b/crates/index-scheduler/src/index_mapper/mod.rs
index 3cccb5a69..8b9ef3597 100644
--- a/crates/index-scheduler/src/index_mapper/mod.rs
+++ b/crates/index-scheduler/src/index_mapper/mod.rs
@@ -3,8 +3,13 @@ use std::sync::{Arc, RwLock};
 use std::time::Duration;
 use std::{fs, thread};
 
+use self::index_map::IndexMap;
+use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
+use crate::uuid_codec::UuidCodec;
+use crate::{Error, Result};
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
+use meilisearch_types::milli;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
@@ -12,11 +17,6 @@ use time::OffsetDateTime;
 use tracing::error;
 use uuid::Uuid;
 
-use self::index_map::IndexMap;
-use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
-use crate::uuid_codec::UuidCodec;
-use crate::{Error, Result};
-
 mod index_map;
 
 const INDEX_MAPPING: &str = "index-mapping";
@@ -121,7 +121,7 @@ impl IndexStats {
     /// # Parameters
     ///
     /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
-    pub fn new(index: &Index, rtxn: &RoTxn) -> Result<Self> {
+    pub fn new(index: &Index, rtxn: &RoTxn) -> milli::Result<Self> {
         Ok(IndexStats {
             number_of_documents: index.number_of_documents(rtxn)?,
             database_size: index.on_disk_size()?,
@@ -183,13 +183,18 @@ impl IndexMapper {
                 // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
                 // This is very unlikely to happen in practice.
                 // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
-                let index = self.index_map.write().unwrap().create(
-                    &uuid,
-                    &index_path,
-                    date,
-                    self.enable_mdb_writemap,
-                    self.index_base_map_size,
-                )?;
+                let index = self
+                    .index_map
+                    .write()
+                    .unwrap()
+                    .create(
+                        &uuid,
+                        &index_path,
+                        date,
+                        self.enable_mdb_writemap,
+                        self.index_base_map_size,
+                    )
+                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
 
                 wtxn.commit()?;
 
@@ -357,7 +362,9 @@ impl IndexMapper {
                     };
                     let index_path = self.base_path.join(uuid.to_string());
                     // take the lock to reopen the environment.
-                    reopen.reopen(&mut self.index_map.write().unwrap(), &index_path)?;
+                    reopen
+                        .reopen(&mut self.index_map.write().unwrap(), &index_path)
+                        .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
                     continue;
                 }
                 BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
@@ -372,13 +379,15 @@ impl IndexMapper {
                         Missing => {
                             let index_path = self.base_path.join(uuid.to_string());
 
-                            break index_map.create(
-                                &uuid,
-                                &index_path,
-                                None,
-                                self.enable_mdb_writemap,
-                                self.index_base_map_size,
-                            )?;
+                            break index_map
+                                .create(
+                                    &uuid,
+                                    &index_path,
+                                    None,
+                                    self.enable_mdb_writemap,
+                                    self.index_base_map_size,
+                                )
+                                .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
                         }
                         Available(index) => break index,
                         Closing(_) => {
@@ -460,6 +469,7 @@ impl IndexMapper {
                 let index = self.index(rtxn, index_uid)?;
                 let index_rtxn = index.read_txn()?;
                 IndexStats::new(&index, &index_rtxn)
+                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))
             }
         }
     }
diff --git a/crates/index-scheduler/src/lib.rs b/crates/index-scheduler/src/lib.rs
index 336a43b1b..19998f7e6 100644
--- a/crates/index-scheduler/src/lib.rs
+++ b/crates/index-scheduler/src/lib.rs
@@ -1225,9 +1225,10 @@ impl IndexScheduler {
                 tracing::info!("A batch of tasks was successfully completed with {success} successful tasks and {failure} failed tasks.");
             }
             // If we have an abortion error we must stop the tick here and re-schedule tasks.
-            Err(Error::Milli(milli::Error::InternalError(
-                milli::InternalError::AbortedIndexation,
-            )))
+            Err(Error::Milli {
+                error: milli::Error::InternalError(milli::InternalError::AbortedIndexation),
+                ..
+            })
             | Err(Error::AbortedTask) => {
                 #[cfg(test)]
                 self.breakpoint(Breakpoint::AbortedIndexation);
@@ -1246,9 +1247,10 @@ impl IndexScheduler {
             // 2. close the associated environment
             // 3. resize it
             // 4. re-schedule tasks
-            Err(Error::Milli(milli::Error::UserError(
-                milli::UserError::MaxDatabaseSizeReached,
-            ))) if index_uid.is_some() => {
+            Err(Error::Milli {
+                error: milli::Error::UserError(milli::UserError::MaxDatabaseSizeReached),
+                ..
+            }) if index_uid.is_some() => {
                 // fixme: add index_uid to match to avoid the unwrap
                 let index_uid = index_uid.unwrap();
                 // fixme: handle error more gracefully? not sure when this could happen
@@ -1485,6 +1487,7 @@ impl IndexScheduler {
     // TODO: consider using a type alias or a struct embedder/template
     pub fn embedders(
         &self,
+        index_uid: String,
         embedding_configs: Vec<IndexEmbeddingConfig>,
     ) -> Result<EmbeddingConfigs> {
         let res: Result<_> = embedding_configs
@@ -1495,8 +1498,12 @@ impl IndexScheduler {
                      config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
                      ..
                  }| {
-                    let prompt =
-                        Arc::new(prompt.try_into().map_err(meilisearch_types::milli::Error::from)?);
+                    let prompt = Arc::new(
+                        prompt
+                            .try_into()
+                            .map_err(meilisearch_types::milli::Error::from)
+                            .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?,
+                    );
                     // optimistically return existing embedder
                     {
                         let embedders = self.embedders.read().unwrap();
@@ -1512,7 +1519,8 @@ impl IndexScheduler {
                     let embedder = Arc::new(
                         Embedder::new(embedder_options.clone())
                             .map_err(meilisearch_types::milli::vector::Error::from)
-                            .map_err(meilisearch_types::milli::Error::from)?,
+                            .map_err(meilisearch_types::milli::Error::from)
+                            .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?,
                     );
                     {
                         let mut embedders = self.embedders.write().unwrap();
@@ -5214,7 +5222,7 @@ mod tests {
             insta::assert_json_snapshot!(simple_hf_config.embedder_options);
             let simple_hf_name = name.clone();
 
-            let configs = index_scheduler.embedders(configs).unwrap();
+            let configs = index_scheduler.embedders("doggos".to_string(), configs).unwrap();
             let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
             let beagle_embed = hf_embedder.embed_one(S("Intel the beagle best doggo")).unwrap();
             let lab_embed = hf_embedder.embed_one(S("Max the lab best doggo")).unwrap();
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap b/crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap
index 82748751e..5a4d294a9 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap
@@ -9,8 +9,8 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
-3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
-4 {uid: 4, status: failed, error: ResponseError { code: 200, message: "Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
+3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
+4 {uid: 4, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
 5 {uid: 5, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
 ----------------------------------------------------------------------
 ### Status:
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fifth_task_succeeds.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fifth_task_succeeds.snap
index 85d7ba460..79bb76bc5 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fifth_task_succeeds.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fifth_task_succeeds.snap
@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: failed, error: ResponseError { code: 200, message: "Document doesn't have a `bork` attribute: `{\"id\":0,\"doggo\":\"jean bob\"}`.", error_code: "missing_document_id", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#missing_document_id" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Document doesn't have a `bork` attribute: `{\"id\":1,\"doggo\":\"jean bob\"}`.", error_code: "missing_document_id", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#missing_document_id" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
+3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
 4 {uid: 4, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000004, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fourth_task_fails.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fourth_task_fails.snap
index 2a8748657..f69ec0cd0 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fourth_task_fails.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fourth_task_fails.snap
@@ -9,7 +9,7 @@ source: index-scheduler/src/lib.rs
 0 {uid: 0, status: failed, error: ResponseError { code: 200, message: "Document doesn't have a `bork` attribute: `{\"id\":0,\"doggo\":\"jean bob\"}`.", error_code: "missing_document_id", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#missing_document_id" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Document doesn't have a `bork` attribute: `{\"id\":1,\"doggo\":\"jean bob\"}`.", error_code: "missing_document_id", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#missing_document_id" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
-3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
+3 {uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
 4 {uid: 4, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000004, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/second_task_fails.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/second_task_fails.snap
index 18db64ca4..f801efbbd 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/second_task_fails.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/second_task_fails.snap
@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bloup"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/third_task_fails.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/third_task_fails.snap
index 4a9edc602..2b40e4973 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/third_task_fails.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/third_task_fails.snap
@@ -7,8 +7,8 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
-2 {uid: 2, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bloup"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
+1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+2 {uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bloup"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key_batch_wrong_key/second_and_third_tasks_fails.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key_batch_wrong_key/second_and_third_tasks_fails.snap
index 05eca0af1..f16c00bc7 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key_batch_wrong_key/second_and_third_tasks_fails.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key_batch_wrong_key/second_and_third_tasks_fails.snap
@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `id`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/all_other_tasks_succeeds.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/all_other_tasks_succeeds.snap
index 1f55e8f6d..76ae1abbe 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/all_other_tasks_succeeds.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/all_other_tasks_succeeds.snap
@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `doggoid`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `doggoid`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("doggoid"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
 3 {uid: 3, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
 4 {uid: 4, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000004, documents_count: 1, allow_index_creation: true }}
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/second_task_fails.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/second_task_fails.snap
index 2920c3b2e..fc6473b74 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/second_task_fails.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/second_task_fails.snap
@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `doggoid`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `doggoid`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("doggoid"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
 3 {uid: 3, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
 4 {uid: 4, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000004, documents_count: 1, allow_index_creation: true }}
diff --git a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/third_task_succeeds.snap b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/third_task_succeeds.snap
index 8981dd8c3..dd802db4c 100644
--- a/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/third_task_succeeds.snap
+++ b/crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/third_task_succeeds.snap
@@ -7,7 +7,7 @@ source: index-scheduler/src/lib.rs
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
-1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index already has a primary key: `doggoid`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
+1 {uid: 1, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Index already has a primary key: `doggoid`.", error_code: "index_primary_key_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_primary_key_already_exists" }, details: { received_documents: 1, indexed_documents: Some(0) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("bork"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("doggoid"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000002, documents_count: 1, allow_index_creation: true }}
 3 {uid: 3, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000003, documents_count: 1, allow_index_creation: true }}
 4 {uid: 4, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000004, documents_count: 1, allow_index_creation: true }}
diff --git a/crates/meilisearch/src/error.rs b/crates/meilisearch/src/error.rs
index 5c4ce171f..b86ef699a 100644
--- a/crates/meilisearch/src/error.rs
+++ b/crates/meilisearch/src/error.rs
@@ -4,6 +4,7 @@ use byte_unit::{Byte, UnitType};
 use meilisearch_types::document_formats::{DocumentFormatError, PayloadType};
 use meilisearch_types::error::{Code, ErrorCode, ResponseError};
 use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError};
+use meilisearch_types::milli;
 use meilisearch_types::milli::OrderBy;
 use serde_json::Value;
 use tokio::task::JoinError;
@@ -62,8 +63,11 @@ pub enum MeilisearchHttpError {
     HeedError(#[from] meilisearch_types::heed::Error),
     #[error(transparent)]
     IndexScheduler(#[from] index_scheduler::Error),
-    #[error(transparent)]
-    Milli(#[from] meilisearch_types::milli::Error),
+    #[error("{}", match .index_name {
+        Some(name) if !name.is_empty() => format!("Index `{}`: {error}", name),
+        _ => format!("{error}")
+    })]
+    Milli { error: meilisearch_types::milli::Error, index_name: Option<String> },
     #[error(transparent)]
     Payload(#[from] PayloadError),
     #[error(transparent)]
@@ -76,6 +80,12 @@ pub enum MeilisearchHttpError {
     MissingSearchHybrid,
 }
 
+impl MeilisearchHttpError {
+    pub(crate) fn from_milli(error: milli::Error, index_name: Option<String>) -> Self {
+        Self::Milli { error, index_name }
+    }
+}
+
 impl ErrorCode for MeilisearchHttpError {
     fn error_code(&self) -> Code {
         match self {
@@ -95,7 +105,7 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::SerdeJson(_) => Code::Internal,
             MeilisearchHttpError::HeedError(_) => Code::Internal,
             MeilisearchHttpError::IndexScheduler(e) => e.error_code(),
-            MeilisearchHttpError::Milli(e) => e.error_code(),
+            MeilisearchHttpError::Milli { error, .. } => error.error_code(),
             MeilisearchHttpError::Payload(e) => e.error_code(),
             MeilisearchHttpError::FileStore(_) => Code::Internal,
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
diff --git a/crates/meilisearch/src/lib.rs b/crates/meilisearch/src/lib.rs
index 633ad2776..779af63f2 100644
--- a/crates/meilisearch/src/lib.rs
+++ b/crates/meilisearch/src/lib.rs
@@ -395,6 +395,7 @@ fn import_dump(
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
+        let uid = metadata.uid.clone();
         tracing::info!("Importing index `{}`.", metadata.uid);
 
         let date = Some((metadata.created_at, metadata.updated_at));
@@ -432,7 +433,7 @@ fn import_dump(
         let reader = DocumentsBatchReader::from_reader(reader)?;
 
         let embedder_configs = index.embedding_configs(&wtxn)?;
-        let embedders = index_scheduler.embedders(embedder_configs)?;
+        let embedders = index_scheduler.embedders(uid, embedder_configs)?;
 
         let builder = milli::update::IndexDocuments::new(
             &mut wtxn,
diff --git a/crates/meilisearch/src/routes/indexes/facet_search.rs b/crates/meilisearch/src/routes/indexes/facet_search.rs
index 99a4a4f28..ff11f1305 100644
--- a/crates/meilisearch/src/routes/indexes/facet_search.rs
+++ b/crates/meilisearch/src/routes/indexes/facet_search.rs
@@ -185,7 +185,8 @@ pub async fn search(
 
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
-    let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
+    let search_kind =
+        search_kind(&search_query, &index_scheduler, index_uid.to_string(), &index, features)?;
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(
diff --git a/crates/meilisearch/src/routes/indexes/mod.rs b/crates/meilisearch/src/routes/indexes/mod.rs
index 7d073ec5f..b2a85335b 100644
--- a/crates/meilisearch/src/routes/indexes/mod.rs
+++ b/crates/meilisearch/src/routes/indexes/mod.rs
@@ -5,7 +5,7 @@ use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::{DeserializeError, Deserr, ValuePointerRef};
-use index_scheduler::IndexScheduler;
+use index_scheduler::{Error, IndexScheduler};
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{immutable_field_error, DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
@@ -107,7 +107,10 @@ pub async fn list_indexes(
             if !filters.is_index_authorized(uid) {
                 return Ok(None);
             }
-            Ok(Some(IndexView::new(uid.to_string(), index)?))
+            Ok(Some(
+                IndexView::new(uid.to_string(), index)
+                    .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
+            ))
         })?;
     // Won't cause to open all indexes because IndexView doesn't keep the `Index` opened.
     let indexes: Vec<IndexView> = indexes.into_iter().flatten().collect();
diff --git a/crates/meilisearch/src/routes/indexes/search.rs b/crates/meilisearch/src/routes/indexes/search.rs
index 2f5cb4a36..fbaac67da 100644
--- a/crates/meilisearch/src/routes/indexes/search.rs
+++ b/crates/meilisearch/src/routes/indexes/search.rs
@@ -243,11 +243,19 @@ pub async fn search_with_url_query(
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
 
-    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let search_kind =
+        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index, features)?;
     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
-        perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
+        perform_search(
+            index_uid.to_string(),
+            &index,
+            query,
+            search_kind,
+            retrieve_vector,
+            index_scheduler.features(),
+        )
     })
     .await;
     permit.drop().await;
@@ -287,12 +295,20 @@ pub async fn search_with_post(
 
     let features = index_scheduler.features();
 
-    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let search_kind =
+        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index, features)?;
     let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
 
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
-        perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
+        perform_search(
+            index_uid.to_string(),
+            &index,
+            query,
+            search_kind,
+            retrieve_vectors,
+            index_scheduler.features(),
+        )
     })
     .await;
     permit.drop().await;
@@ -314,6 +330,7 @@ pub async fn search_with_post(
 pub fn search_kind(
     query: &SearchQuery,
     index_scheduler: &IndexScheduler,
+    index_uid: String,
     index: &milli::Index,
     features: RoFeatures,
 ) -> Result<SearchKind, ResponseError> {
@@ -332,7 +349,7 @@ pub fn search_kind(
         (None, _, None) => Ok(SearchKind::KeywordOnly),
         // hybrid.semantic_ratio == 1.0 => vector
         (_, Some(HybridQuery { semantic_ratio, embedder }), v) if **semantic_ratio == 1.0 => {
-            SearchKind::semantic(index_scheduler, index, embedder, v.map(|v| v.len()))
+            SearchKind::semantic(index_scheduler, index_uid, index, embedder, v.map(|v| v.len()))
         }
         // hybrid.semantic_ratio == 0.0 => keyword
         (_, Some(HybridQuery { semantic_ratio, embedder: _ }), _) if **semantic_ratio == 0.0 => {
@@ -340,13 +357,14 @@ pub fn search_kind(
         }
         // no query, hybrid, vector => semantic
         (None, Some(HybridQuery { semantic_ratio: _, embedder }), Some(v)) => {
-            SearchKind::semantic(index_scheduler, index, embedder, Some(v.len()))
+            SearchKind::semantic(index_scheduler, index_uid, index, embedder, Some(v.len()))
         }
         // query, no hybrid, no vector => keyword
         (Some(_), None, None) => Ok(SearchKind::KeywordOnly),
         // query, hybrid, maybe vector => hybrid
         (Some(_), Some(HybridQuery { semantic_ratio, embedder }), v) => SearchKind::hybrid(
             index_scheduler,
+            index_uid,
             index,
             embedder,
             **semantic_ratio,
diff --git a/crates/meilisearch/src/routes/indexes/similar.rs b/crates/meilisearch/src/routes/indexes/similar.rs
index 79f42f0aa..f47771061 100644
--- a/crates/meilisearch/src/routes/indexes/similar.rs
+++ b/crates/meilisearch/src/routes/indexes/similar.rs
@@ -103,8 +103,13 @@ async fn similar(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    let (embedder_name, embedder, quantized) =
-        SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
+    let (embedder_name, embedder, quantized) = SearchKind::embedder(
+        &index_scheduler,
+        index_uid.to_string(),
+        &index,
+        &query.embedder,
+        None,
+    )?;
 
     tokio::task::spawn_blocking(move || {
         perform_similar(
diff --git a/crates/meilisearch/src/routes/multi_search.rs b/crates/meilisearch/src/routes/multi_search.rs
index f8b1bc6ee..a2db0b22b 100644
--- a/crates/meilisearch/src/routes/multi_search.rs
+++ b/crates/meilisearch/src/routes/multi_search.rs
@@ -125,14 +125,28 @@ pub async fn multi_search_with_post(
                         })
                         .with_index(query_index)?;
 
-                    let search_kind =
-                        search_kind(&query, index_scheduler.get_ref(), &index, features)
-                            .with_index(query_index)?;
+                    let index_uid_str = index_uid.to_string();
+
+                    let search_kind = search_kind(
+                        &query,
+                        index_scheduler.get_ref(),
+                        index_uid_str.clone(),
+                        &index,
+                        features,
+                    )
+                    .with_index(query_index)?;
                     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)
                         .with_index(query_index)?;
 
                     let search_result = tokio::task::spawn_blocking(move || {
-                        perform_search(&index, query, search_kind, retrieve_vector, features)
+                        perform_search(
+                            index_uid_str.clone(),
+                            &index,
+                            query,
+                            search_kind,
+                            retrieve_vector,
+                            features,
+                        )
                     })
                     .await
                     .with_index(query_index)?;
diff --git a/crates/meilisearch/src/search/federated.rs b/crates/meilisearch/src/search/federated.rs
index 5279c26bb..c1c6bb7d7 100644
--- a/crates/meilisearch/src/search/federated.rs
+++ b/crates/meilisearch/src/search/federated.rs
@@ -560,7 +560,8 @@ pub fn perform_federated_search(
             // use an immediately invoked lambda to capture the result without returning from the function
 
             let res: Result<(), ResponseError> = (|| {
-                let search_kind = search_kind(&query, index_scheduler, &index, features)?;
+                let search_kind =
+                    search_kind(&query, index_scheduler, index_uid.to_string(), &index, features)?;
 
                 let canonicalization_kind = match (&search_kind, &query.q) {
                     (SearchKind::SemanticOnly { .. }, _) => {
@@ -636,7 +637,8 @@ pub fn perform_federated_search(
                 search.offset(0);
                 search.limit(required_hit_count);
 
-                let (result, _semantic_hit_count) = super::search_from_kind(search_kind, search)?;
+                let (result, _semantic_hit_count) =
+                    super::search_from_kind(index_uid.to_string(), search_kind, search)?;
                 let format = AttributesFormat {
                     attributes_to_retrieve: query.attributes_to_retrieve,
                     retrieve_vectors,
@@ -670,7 +672,10 @@ pub fn perform_federated_search(
 
                 let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
 
-                let hit_maker = HitMaker::new(&index, &rtxn, format, formatter_builder)?;
+                let hit_maker =
+                    HitMaker::new(&index, &rtxn, format, formatter_builder).map_err(|e| {
+                        MeilisearchHttpError::from_milli(e, Some(index_uid.to_string()))
+                    })?;
 
                 results_by_query.push(SearchResultByQuery {
                     federation_options,
diff --git a/crates/meilisearch/src/search/mod.rs b/crates/meilisearch/src/search/mod.rs
index 241c3ab81..aba172cee 100644
--- a/crates/meilisearch/src/search/mod.rs
+++ b/crates/meilisearch/src/search/mod.rs
@@ -19,7 +19,9 @@ use meilisearch_types::locales::Locale;
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::vector::Embedder;
-use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues, TimeBudget};
+use meilisearch_types::milli::{
+    FacetValueHit, InternalError, OrderBy, SearchForFacetValues, TimeBudget,
+};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::{Language, TokenizerBuilder};
@@ -281,35 +283,38 @@ pub enum SearchKind {
 impl SearchKind {
     pub(crate) fn semantic(
         index_scheduler: &index_scheduler::IndexScheduler,
+        index_uid: String,
         index: &Index,
         embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
         let (embedder_name, embedder, quantized) =
-            Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
+            Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
         Ok(Self::SemanticOnly { embedder_name, embedder, quantized })
     }
 
     pub(crate) fn hybrid(
         index_scheduler: &index_scheduler::IndexScheduler,
+        index_uid: String,
         index: &Index,
         embedder_name: &str,
         semantic_ratio: f32,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
         let (embedder_name, embedder, quantized) =
-            Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
+            Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
         Ok(Self::Hybrid { embedder_name, embedder, quantized, semantic_ratio })
     }
 
     pub(crate) fn embedder(
         index_scheduler: &index_scheduler::IndexScheduler,
+        index_uid: String,
         index: &Index,
         embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<(String, Arc<Embedder>, bool), ResponseError> {
         let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
-        let embedders = index_scheduler.embedders(embedder_configs)?;
+        let embedders = index_scheduler.embedders(index_uid, embedder_configs)?;
 
         let (embedder, _, quantized) = embedders
             .get(embedder_name)
@@ -888,6 +893,7 @@ fn prepare_search<'t>(
 }
 
 pub fn perform_search(
+    index_uid: String,
     index: &Index,
     query: SearchQuery,
     search_kind: SearchKind,
@@ -914,7 +920,7 @@ pub fn perform_search(
             used_negative_operator,
         },
         semantic_hit_count,
-    ) = search_from_kind(search_kind, search)?;
+    ) = search_from_kind(index_uid, search_kind, search)?;
 
     let SearchQuery {
         q,
@@ -1067,17 +1073,27 @@ fn compute_facet_distribution_stats<S: AsRef<str>>(
 }
 
 pub fn search_from_kind(
+    index_uid: String,
     search_kind: SearchKind,
     search: milli::Search<'_>,
 ) -> Result<(milli::SearchResult, Option<u32>), MeilisearchHttpError> {
     let (milli_result, semantic_hit_count) = match &search_kind {
-        SearchKind::KeywordOnly => (search.execute()?, None),
+        SearchKind::KeywordOnly => {
+            let results = search
+                .execute()
+                .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
+            (results, None)
+        }
         SearchKind::SemanticOnly { .. } => {
-            let results = search.execute()?;
+            let results = search
+                .execute()
+                .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
             let semantic_hit_count = results.document_scores.len() as u32;
             (results, Some(semantic_hit_count))
         }
-        SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
+        SearchKind::Hybrid { semantic_ratio, .. } => search
+            .execute_hybrid(*semantic_ratio)
+            .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid)))?,
     };
     Ok((milli_result, semantic_hit_count))
 }
@@ -1179,7 +1195,7 @@ impl<'a> HitMaker<'a> {
         rtxn: &'a RoTxn<'a>,
         format: AttributesFormat,
         mut formatter_builder: MatcherBuilder<'a>,
-    ) -> Result<Self, MeilisearchHttpError> {
+    ) -> milli::Result<Self> {
         formatter_builder.crop_marker(format.crop_marker);
         formatter_builder.highlight_prefix(format.highlight_pre_tag);
         formatter_builder.highlight_suffix(format.highlight_post_tag);
@@ -1274,11 +1290,7 @@ impl<'a> HitMaker<'a> {
         })
     }
 
-    pub fn make_hit(
-        &self,
-        id: u32,
-        score: &[ScoreDetails],
-    ) -> Result<SearchHit, MeilisearchHttpError> {
+    pub fn make_hit(&self, id: u32, score: &[ScoreDetails]) -> milli::Result<SearchHit> {
         let (_, obkv) =
             self.index.iter_documents(self.rtxn, std::iter::once(id))?.next().unwrap()?;
 
@@ -1321,7 +1333,10 @@ impl<'a> HitMaker<'a> {
                     .is_some_and(|conf| conf.user_provided.contains(id));
                 let embeddings =
                     ExplicitVectors { embeddings: Some(vector.into()), regenerate: !user_provided };
-                vectors.insert(name, serde_json::to_value(embeddings)?);
+                vectors.insert(
+                    name,
+                    serde_json::to_value(embeddings).map_err(InternalError::SerdeJson)?,
+                );
             }
             document.insert("_vectors".into(), vectors.into());
         }
@@ -1367,7 +1382,7 @@ fn make_hits<'a>(
     format: AttributesFormat,
     matching_words: milli::MatchingWords,
     documents_ids_scores: impl Iterator<Item = (u32, &'a Vec<ScoreDetails>)> + 'a,
-) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
+) -> milli::Result<Vec<SearchHit>> {
     let mut documents = Vec::new();
 
     let dictionary = index.dictionary(rtxn)?;
@@ -1688,12 +1703,12 @@ fn make_document(
     displayed_attributes: &BTreeSet<FieldId>,
     field_ids_map: &FieldsIdsMap,
     obkv: obkv::KvReaderU16,
-) -> Result<Document, MeilisearchHttpError> {
+) -> milli::Result<Document> {
     let mut document = serde_json::Map::new();
 
     // recreate the original json
     for (key, value) in obkv.iter() {
-        let value = serde_json::from_slice(value)?;
+        let value = serde_json::from_slice(value).map_err(InternalError::SerdeJson)?;
         let key = field_ids_map.name(key).expect("Missing field name").to_string();
 
         document.insert(key, value);
@@ -1718,7 +1733,7 @@ fn format_fields(
     displayable_ids: &BTreeSet<FieldId>,
     locales: Option<&[Language]>,
     localized_attributes: &[LocalizedAttributesRule],
-) -> Result<(Option<MatchesPosition>, Document), MeilisearchHttpError> {
+) -> milli::Result<(Option<MatchesPosition>, Document)> {
     let mut matches_position = compute_matches.then(BTreeMap::new);
     let mut document = document.clone();
 
@@ -1896,7 +1911,7 @@ fn parse_filter_array(arr: &[Value]) -> Result<Option<Filter>, MeilisearchHttpEr
         }
     }
 
-    Ok(Filter::from_array(ands)?)
+    Filter::from_array(ands).map_err(|e| MeilisearchHttpError::from_milli(e, None))
 }
 
 #[cfg(test)]
diff --git a/crates/meilisearch/tests/documents/add_documents.rs b/crates/meilisearch/tests/documents/add_documents.rs
index c37b3a5e3..964f51d4e 100644
--- a/crates/meilisearch/tests/documents/add_documents.rs
+++ b/crates/meilisearch/tests/documents/add_documents.rs
@@ -1446,7 +1446,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "A document cannot contain more than 65,535 fields.",
+        "message": "Index `test`: A document cannot contain more than 65,535 fields.",
         "code": "max_fields_limit_exceeded",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#max_fields_limit_exceeded"
@@ -2242,7 +2242,7 @@ async fn add_invalid_geo_and_then_settings() {
         ]
       },
       "error": {
-        "message": "Could not parse latitude in the document with the id: `\"11\"`. Was expecting a finite number but instead got `null`.",
+        "message": "Index `test`: Could not parse latitude in the document with the id: `\"11\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
diff --git a/crates/meilisearch/tests/documents/errors.rs b/crates/meilisearch/tests/documents/errors.rs
index 4c644ae98..9789e1eda 100644
--- a/crates/meilisearch/tests/documents/errors.rs
+++ b/crates/meilisearch/tests/documents/errors.rs
@@ -602,7 +602,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
+        "message": "Index `EMPTY_INDEX`: Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -633,7 +633,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"catto = jorts\""
       },
       "error": {
-        "message": "Attribute `catto` is not filterable. Available filterable attributes are: `id`, `title`.\n1:6 catto = jorts",
+        "message": "Index `SHARED_DOCUMENTS`: Attribute `catto` is not filterable. Available filterable attributes are: `id`, `title`.\n1:6 catto = jorts",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
diff --git a/crates/meilisearch/tests/index/update_index.rs b/crates/meilisearch/tests/index/update_index.rs
index 36ec27306..f991c3580 100644
--- a/crates/meilisearch/tests/index/update_index.rs
+++ b/crates/meilisearch/tests/index/update_index.rs
@@ -95,7 +95,7 @@ async fn error_update_existing_primary_key() {
     let response = index.wait_task(2).await;
 
     let expected_response = json!({
-        "message": "Index already has a primary key: `id`.",
+        "message": "Index `test`: Index already has a primary key: `id`.",
         "code": "index_primary_key_already_exists",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#index_primary_key_already_exists"
diff --git a/crates/meilisearch/tests/search/errors.rs b/crates/meilisearch/tests/search/errors.rs
index 6840f8fba..1401637ba 100644
--- a/crates/meilisearch/tests/search/errors.rs
+++ b/crates/meilisearch/tests/search/errors.rs
@@ -711,7 +711,7 @@ async fn filter_invalid_attribute_array() {
     index.wait_task(task.uid()).await;
 
     let expected_response = json!({
-        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
+        "message": format!("Index `{}`: Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass", index.uid),
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -733,7 +733,7 @@ async fn filter_invalid_attribute_string() {
     index.wait_task(task.uid()).await;
 
     let expected_response = json!({
-        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
+        "message": format!("Index `{}`: Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass", index.uid),
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -940,7 +940,7 @@ async fn sort_unsortable_attribute() {
     index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
-        "message": "Attribute `title` is not sortable. Available sortable attributes are: `id`.",
+        "message": format!("Index `{}`: Attribute `title` is not sortable. Available sortable attributes are: `id`.", index.uid),
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -998,7 +998,7 @@ async fn sort_unset_ranking_rule() {
     index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
-        "message": "You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.",
+        "message": format!("Index `{}`: You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.", index.uid),
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1018,8 +1018,8 @@ async fn sort_unset_ranking_rule() {
 
 #[actix_rt::test]
 async fn search_on_unknown_field() {
-    let server = Server::new_shared();
-    let index = server.unique_index();
+    let server = Server::new().await;
+    let index = server.index("test");
     let (response, _code) =
         index.update_settings_searchable_attributes(json!(["id", "title"])).await;
     index.wait_task(response.uid()).await.succeeded();
@@ -1031,7 +1031,7 @@ async fn search_on_unknown_field() {
                 snapshot!(code, @"400 Bad Request");
                 snapshot!(json_string!(response), @r###"
                 {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
+                  "message": "Index `test`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
                   "code": "invalid_search_attributes_to_search_on",
                   "type": "invalid_request",
                   "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
@@ -1044,8 +1044,8 @@ async fn search_on_unknown_field() {
 
 #[actix_rt::test]
 async fn search_on_unknown_field_plus_joker() {
-    let server = Server::new_shared();
-    let index = server.unique_index();
+    let server = Server::new().await;
+    let index = server.index("test");
     let (response, _code) =
         index.update_settings_searchable_attributes(json!(["id", "title"])).await;
     index.wait_task(response.uid()).await.succeeded();
@@ -1057,7 +1057,7 @@ async fn search_on_unknown_field_plus_joker() {
                 snapshot!(code, @"400 Bad Request");
                 snapshot!(json_string!(response), @r###"
                 {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
+                  "message": "Index `test`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
                   "code": "invalid_search_attributes_to_search_on",
                   "type": "invalid_request",
                   "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
@@ -1074,7 +1074,7 @@ async fn search_on_unknown_field_plus_joker() {
                 snapshot!(code, @"400 Bad Request");
                 snapshot!(json_string!(response), @r###"
                 {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
+                  "message": "Index `test`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
                   "code": "invalid_search_attributes_to_search_on",
                   "type": "invalid_request",
                   "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
@@ -1087,8 +1087,8 @@ async fn search_on_unknown_field_plus_joker() {
 
 #[actix_rt::test]
 async fn distinct_at_search_time() {
-    let server = Server::new_shared();
-    let index = server.unique_index();
+    let server = Server::new().await;
+    let index = server.index("test");
     let (task, _) = index.create(None).await;
     index.wait_task(task.uid()).await.succeeded();
 
@@ -1097,7 +1097,7 @@ async fn distinct_at_search_time() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(response, @r###"
     {
-      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. This index does not have configured filterable attributes.",
+      "message": "Index `test`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. This index does not have configured filterable attributes.",
       "code": "invalid_search_distinct",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
@@ -1112,7 +1112,7 @@ async fn distinct_at_search_time() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(response, @r###"
     {
-      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, machin`.",
+      "message": "Index `test`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, machin`.",
       "code": "invalid_search_distinct",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
@@ -1127,7 +1127,7 @@ async fn distinct_at_search_time() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(response, @r###"
     {
-      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, <..hidden-attributes>`.",
+      "message": "Index `test`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, <..hidden-attributes>`.",
       "code": "invalid_search_distinct",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
diff --git a/crates/meilisearch/tests/search/multi.rs b/crates/meilisearch/tests/search/multi.rs
index eaa1da15f..2735ab65c 100644
--- a/crates/meilisearch/tests/search/multi.rs
+++ b/crates/meilisearch/tests/search/multi.rs
@@ -1070,7 +1070,7 @@ async fn federation_one_query_error() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1102,7 +1102,7 @@ async fn federation_one_query_sort_error() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1166,7 +1166,7 @@ async fn federation_multiple_query_errors() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[0]`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
+      "message": "Inside `.queries[0]`: Index `test`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1198,7 +1198,7 @@ async fn federation_multiple_query_sort_errors() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[0]`: Attribute `title` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[0]`: Index `test`: Attribute `title` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1231,7 +1231,7 @@ async fn federation_multiple_query_errors_interleaved() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `doggos` is not filterable. This index does not have configured filterable attributes.\n1:7 doggos IN [intel, kefir]",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not filterable. This index does not have configured filterable attributes.\n1:7 doggos IN [intel, kefir]",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1264,7 +1264,7 @@ async fn federation_multiple_query_sort_errors_interleaved() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
diff --git a/crates/meilisearch/tests/tasks/mod.rs b/crates/meilisearch/tests/tasks/mod.rs
index 8cff3c447..f13a13f89 100644
--- a/crates/meilisearch/tests/tasks/mod.rs
+++ b/crates/meilisearch/tests/tasks/mod.rs
@@ -442,7 +442,7 @@ async fn test_summarized_delete_documents_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
+        "message": "Index `test`: Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
diff --git a/crates/meilisearch/tests/vector/binary_quantized.rs b/crates/meilisearch/tests/vector/binary_quantized.rs
index d3fe3c824..e344b8051 100644
--- a/crates/meilisearch/tests/vector/binary_quantized.rs
+++ b/crates/meilisearch/tests/vector/binary_quantized.rs
@@ -317,7 +317,7 @@ async fn try_to_disable_binary_quantization() {
         }
       },
       "error": {
-        "message": "`.embedders.manual.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors.",
+        "message": "Index `doggo`: `.embedders.manual.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors.",
         "code": "invalid_settings_embedders",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
diff --git a/crates/meilisearch/tests/vector/mod.rs b/crates/meilisearch/tests/vector/mod.rs
index 47d0c1051..023d263e4 100644
--- a/crates/meilisearch/tests/vector/mod.rs
+++ b/crates/meilisearch/tests/vector/mod.rs
@@ -249,7 +249,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -278,7 +278,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Missing field `regenerate` inside `.manual`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -308,7 +308,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.regenerate`: expected a boolean, but found a string: `\"yes please\"`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.regenerate`: expected a boolean, but found a string: `\"yes please\"`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -337,7 +337,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings`: expected null or an array, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings`: expected null or an array, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -366,7 +366,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -395,7 +395,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -436,7 +436,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -464,7 +464,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -492,7 +492,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
+        "message": "Index `doggo`: Bad embedder configuration in the document with id: `\"0\"`. Invalid value type at `.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -532,7 +532,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"40\" and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
+        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document \"40\" and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -561,7 +561,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
+        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -590,7 +590,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
+        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
diff --git a/crates/meilisearch/tests/vector/openai.rs b/crates/meilisearch/tests/vector/openai.rs
index 04c068c40..35979e8fb 100644
--- a/crates/meilisearch/tests/vector/openai.rs
+++ b/crates/meilisearch/tests/vector/openai.rs
@@ -700,7 +700,7 @@ async fn bad_api_key() {
         }
       },
       "error": {
-        "message": "While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"Incorrect API key provided: Bearer doggo. You can find your API key at https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"invalid_api_key\"}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        "message": "Index `doggo`: While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"Incorrect API key provided: Bearer doggo. You can find your API key at https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"invalid_api_key\"}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -743,7 +743,7 @@ async fn bad_api_key() {
         }
       },
       "error": {
-        "message": "While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":null}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        "message": "Index `doggo`: While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":null}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
diff --git a/crates/meilisearch/tests/vector/rest.rs b/crates/meilisearch/tests/vector/rest.rs
index 2748d0846..1e645d412 100644
--- a/crates/meilisearch/tests/vector/rest.rs
+++ b/crates/meilisearch/tests/vector/rest.rs
@@ -937,7 +937,7 @@ async fn bad_settings() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting a single \"{{embedding}}\", expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting a single \"{{embedding}}\", expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -976,7 +976,7 @@ async fn bad_settings() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `rest`: runtime error: was expecting embeddings of dimension `2`, got embeddings of dimensions `3`",
+        "message": "Index `doggo`: While embedding documents for embedder `rest`: runtime error: was expecting embeddings of dimension `2`, got embeddings of dimensions `3`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1127,7 +1127,7 @@ async fn server_returns_bad_request() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"test\\\", expected struct MultipleRequest at line 1 column 6\"}`",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"test\\\", expected struct MultipleRequest at line 1 column 6\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1194,7 +1194,7 @@ async fn server_returns_bad_request() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `rest`: user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 15\"}`",
+        "message": "Index `doggo`: While embedding documents for embedder `rest`: user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 15\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1252,7 +1252,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting the array of \"{{embedding}}\"s, configuration expects `response` to be an array with at least 1 item(s) but server sent an object with 1 field(s)",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting the array of \"{{embedding}}\"s, configuration expects `response` to be an array with at least 1 item(s) but server sent an object with 1 field(s)",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1307,7 +1307,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting item #0 from the array of \"{{embedding}}\"s, expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting item #0 from the array of \"{{embedding}}\"s, expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1358,7 +1358,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output`, while extracting a single \"{{embedding}}\", expected `output` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected f32",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output`, while extracting a single \"{{embedding}}\", expected `output` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected f32",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1421,7 +1421,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.embedding`, while extracting item #0 from the array of \"{{embedding}}\"s, configuration expects `embedding` to be an object with key `data` but server sent an array of size 3",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.embedding`, while extracting item #0 from the array of \"{{embedding}}\"s, configuration expects `embedding` to be an object with key `data` but server sent an array of size 3",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1484,7 +1484,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output[0]`, while extracting a single \"{{embedding}}\", configuration expects key \"embeddings\", which is missing in response\n  - Hint: item #0 inside `output` has key `embedding`, did you mean `response.output[0].embedding` in embedder configuration?",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output[0]`, while extracting a single \"{{embedding}}\", configuration expects key \"embeddings\", which is missing in response\n  - Hint: item #0 inside `output` has key `embedding`, did you mean `response.output[0].embedding` in embedder configuration?",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1846,7 +1846,7 @@ async fn server_custom_header() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1888,7 +1888,7 @@ async fn server_custom_header() {
         }
       },
       "error": {
-        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -2031,7 +2031,7 @@ async fn searchable_reindex() {
         ]
       },
       "error": {
-        "message": "While embedding documents for embedder `rest`: error: received unexpected HTTP 404 from embedding server\n  - server replied with `{\"error\":\"text not found\",\"text\":\"breed: patou\\n\"}`",
+        "message": "Index `doggo`: While embedding documents for embedder `rest`: error: received unexpected HTTP 404 from embedding server\n  - server replied with `{\"error\":\"text not found\",\"text\":\"breed: patou\\n\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"