mirror of
https://github.com/meilisearch/meilisearch.git
synced 2024-11-29 16:45:30 +08:00
fix tests
# Conflicts: # crates/index-scheduler/src/batch.rs # crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fifth_task_succeeds.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_bad_primary_key/fourth_task_fails.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/second_task_fails.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key/third_task_fails.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_multiple_primary_key_batch_wrong_key/second_and_third_tasks_fails.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/all_other_tasks_succeeds.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/second_task_fails.snap # crates/index-scheduler/src/snapshots/lib.rs/test_document_addition_with_set_and_null_primary_key_inference_works/third_task_succeeds.snap # Conflicts: # crates/index-scheduler/src/batch.rs # crates/meilisearch/src/search/mod.rs # crates/meilisearch/tests/vector/mod.rs
This commit is contained in:
airycanon
parent
bb3291fd49
commit
3cef31ada9
@ -29,7 +29,6 @@ use bumpalo::collections::CollectIn;
|
||||
use bumpalo::Bump;
|
||||
use dump::IndexMetadata;
|
||||
use meilisearch_types::batches::BatchId;
|
||||
use meilisearch_types::error::Code;
|
||||
use meilisearch_types::heed::{RoTxn, RwTxn};
|
||||
use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader, PrimaryKey};
|
||||
use meilisearch_types::milli::heed::CompactionOption;
|
||||
@ -781,7 +780,9 @@ 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(uuid.to_string())))?;
|
||||
}
|
||||
|
||||
drop(rtxn);
|
||||
@ -883,16 +884,19 @@ impl IndexScheduler {
|
||||
let content_file = self.file_store.get_update(content_file)?;
|
||||
|
||||
let reader = DocumentsBatchReader::from_reader(content_file)
|
||||
.map_err(milli::Error::from)?;
|
||||
.map_err(|e| Error::from_milli(e.into(), None))?;
|
||||
|
||||
let (mut cursor, documents_batch_index) =
|
||||
reader.into_cursor_and_fields_index();
|
||||
|
||||
while let Some(doc) =
|
||||
cursor.next_document().map_err(milli::Error::from)?
|
||||
while let Some(doc) = cursor
|
||||
.next_document()
|
||||
.map_err(|e| Error::from_milli(e.into(), None))?
|
||||
{
|
||||
dump_content_file
|
||||
.push_document(&obkv_to_object(doc, &documents_batch_index)?)?;
|
||||
dump_content_file.push_document(
|
||||
&obkv_to_object(doc, &documents_batch_index)
|
||||
.map_err(|e| Error::from_milli(e, None))?,
|
||||
)?;
|
||||
}
|
||||
dump_content_file.flush()?;
|
||||
}
|
||||
@ -906,27 +910,41 @@ 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;
|
||||
@ -937,7 +955,7 @@ impl IndexScheduler {
|
||||
.or_insert(serde_json::Value::Object(Default::default()));
|
||||
|
||||
let serde_json::Value::Object(vectors) = vectors else {
|
||||
return Err(milli::Error::UserError(
|
||||
let user_err = milli::Error::UserError(
|
||||
milli::UserError::InvalidVectorsMapType {
|
||||
document_id: {
|
||||
if let Ok(Some(Ok(index))) = index
|
||||
@ -951,8 +969,9 @@ impl IndexScheduler {
|
||||
},
|
||||
value: vectors.clone(),
|
||||
},
|
||||
)
|
||||
.into());
|
||||
);
|
||||
|
||||
return Err(Error::from_milli(user_err, Some(uid.to_string())));
|
||||
};
|
||||
|
||||
for (embedder_name, embeddings) in embeddings {
|
||||
@ -982,7 +1001,8 @@ 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(())
|
||||
})?;
|
||||
@ -1032,7 +1052,8 @@ 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.to_string())))?;
|
||||
let mut wtxn = self.env.write_txn()?;
|
||||
self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
|
||||
wtxn.commit()?;
|
||||
@ -1074,10 +1095,12 @@ 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.to_string())))?;
|
||||
index_wtxn.commit()?;
|
||||
}
|
||||
|
||||
@ -1094,7 +1117,8 @@ 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(())
|
||||
@ -1117,7 +1141,9 @@ 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.to_string())))
|
||||
}()
|
||||
.unwrap_or_default();
|
||||
|
||||
@ -1274,8 +1300,10 @@ impl IndexScheduler {
|
||||
};
|
||||
|
||||
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 {
|
||||
@ -1295,7 +1323,7 @@ impl IndexScheduler {
|
||||
Ok(tasks)
|
||||
}
|
||||
IndexOperation::DocumentOperation {
|
||||
index_uid: _,
|
||||
index_uid,
|
||||
primary_key,
|
||||
method,
|
||||
documents_counts: _,
|
||||
@ -1322,13 +1350,17 @@ impl IndexScheduler {
|
||||
|
||||
let mut content_files_iter = content_files.iter();
|
||||
let mut indexer = indexer::DocumentOperation::new(method);
|
||||
let embedders = index.embedding_configs(index_wtxn)?;
|
||||
let embedders = self.embedders(embedders)?;
|
||||
let embedders = index
|
||||
.embedding_configs(index_wtxn)
|
||||
.map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
|
||||
let embedders = self.embedders(index_uid.clone(), embedders)?;
|
||||
for operation in operations {
|
||||
match operation {
|
||||
DocumentOperation::Add(_content_uuid) => {
|
||||
let mmap = content_files_iter.next().unwrap();
|
||||
indexer.add_documents(mmap)?;
|
||||
indexer
|
||||
.add_documents(mmap)
|
||||
.map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
|
||||
}
|
||||
DocumentOperation::Delete(document_ids) => {
|
||||
let document_ids: bumpalo::collections::vec::Vec<_> = document_ids
|
||||
@ -1350,15 +1382,17 @@ impl IndexScheduler {
|
||||
}
|
||||
};
|
||||
|
||||
let (document_changes, operation_stats, primary_key) = indexer.into_changes(
|
||||
&indexer_alloc,
|
||||
index,
|
||||
&rtxn,
|
||||
primary_key.as_deref(),
|
||||
&mut new_fields_ids_map,
|
||||
&|| must_stop_processing.get(),
|
||||
&send_progress,
|
||||
)?;
|
||||
let (document_changes, operation_stats, primary_key) = indexer
|
||||
.into_changes(
|
||||
&indexer_alloc,
|
||||
index,
|
||||
&rtxn,
|
||||
primary_key.as_deref(),
|
||||
&mut new_fields_ids_map,
|
||||
&|| must_stop_processing.get(),
|
||||
&send_progress,
|
||||
)
|
||||
.map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
|
||||
|
||||
let mut addition = 0;
|
||||
for (stats, task) in operation_stats.into_iter().zip(&mut tasks) {
|
||||
@ -1407,14 +1441,15 @@ impl IndexScheduler {
|
||||
&send_progress,
|
||||
)
|
||||
})
|
||||
.unwrap()?;
|
||||
.unwrap()
|
||||
.map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
|
||||
|
||||
tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
|
||||
}
|
||||
|
||||
Ok(tasks)
|
||||
}
|
||||
IndexOperation::DocumentEdition { mut task, .. } => {
|
||||
IndexOperation::DocumentEdition { index_uid, mut task } => {
|
||||
let (filter, code) = if let KindWithContent::DocumentEdition {
|
||||
filter_expr,
|
||||
context: _,
|
||||
@ -1428,16 +1463,11 @@ impl IndexScheduler {
|
||||
};
|
||||
|
||||
let candidates = match filter.as_ref().map(Filter::from_json) {
|
||||
Some(Ok(Some(filter))) => {
|
||||
filter.evaluate(index_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(index_wtxn, index)
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
|
||||
None | Some(Ok(None)) => index.documents_ids(index_wtxn)?,
|
||||
Some(Err(e)) => return Err(e.into()),
|
||||
Some(Err(e)) => return Err(Error::from_milli(e, Some(index_uid.clone()))),
|
||||
};
|
||||
|
||||
let (original_filter, context, function) = if let Some(Details::DocumentEdition {
|
||||
@ -1472,8 +1502,9 @@ impl IndexScheduler {
|
||||
// candidates not empty => index not empty => a primary key is set
|
||||
let primary_key = index.primary_key(&rtxn)?.unwrap();
|
||||
|
||||
let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
|
||||
.map_err(milli::Error::from)?;
|
||||
let primary_key =
|
||||
PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
|
||||
.map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
|
||||
|
||||
let result_count = Ok((candidates.len(), candidates.len())) as Result<_>;
|
||||
|
||||
@ -1491,9 +1522,13 @@ impl IndexScheduler {
|
||||
pool.install(|| {
|
||||
let indexer =
|
||||
UpdateByFunction::new(candidates, context.clone(), code.clone());
|
||||
let document_changes = indexer.into_changes(&primary_key)?;
|
||||
let embedders = index.embedding_configs(index_wtxn)?;
|
||||
let embedders = self.embedders(embedders)?;
|
||||
let document_changes = indexer
|
||||
.into_changes(&primary_key)
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
|
||||
let embedders = index
|
||||
.embedding_configs(index_wtxn)
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
|
||||
let embedders = self.embedders(index_uid.clone(), embedders)?;
|
||||
|
||||
indexer::index(
|
||||
index_wtxn,
|
||||
@ -1506,7 +1541,8 @@ impl IndexScheduler {
|
||||
embedders,
|
||||
&|| must_stop_processing.get(),
|
||||
&send_progress,
|
||||
)?;
|
||||
)
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
|
||||
|
||||
Result::Ok(())
|
||||
})
|
||||
@ -1541,7 +1577,7 @@ 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();
|
||||
|
||||
@ -1562,35 +1598,23 @@ 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,
|
||||
Err(err) => {
|
||||
// theorically, this should be catched by deserr before reaching the index-scheduler and cannot happens
|
||||
task.status = Status::Failed;
|
||||
task.error = match err {
|
||||
milli::Error::UserError(
|
||||
milli::UserError::InvalidFilterExpression { .. },
|
||||
) => Some(
|
||||
Error::from(err)
|
||||
.with_custom_error_code(Code::InvalidDocumentFilter)
|
||||
.into(),
|
||||
),
|
||||
e => Some(e.into()),
|
||||
};
|
||||
task.error = Some(
|
||||
Error::from_milli(err, Some(index_uid.clone())).into(),
|
||||
);
|
||||
None
|
||||
}
|
||||
};
|
||||
if let Some(filter) = filter {
|
||||
let candidates =
|
||||
filter.evaluate(index_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(),
|
||||
});
|
||||
let candidates = filter
|
||||
.evaluate(index_wtxn, index)
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())));
|
||||
match candidates {
|
||||
Ok(candidates) => to_delete |= candidates,
|
||||
Err(err) => {
|
||||
@ -1626,8 +1650,9 @@ impl IndexScheduler {
|
||||
// to_delete not empty => index not empty => primary key set
|
||||
let primary_key = index.primary_key(&rtxn)?.unwrap();
|
||||
|
||||
let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
|
||||
.map_err(milli::Error::from)?;
|
||||
let primary_key =
|
||||
PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
|
||||
.map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
|
||||
|
||||
if !tasks.iter().all(|res| res.error.is_some()) {
|
||||
let local_pool;
|
||||
@ -1643,8 +1668,10 @@ impl IndexScheduler {
|
||||
let mut indexer = indexer::DocumentDeletion::new();
|
||||
indexer.delete_documents_by_docids(to_delete);
|
||||
let document_changes = indexer.into_changes(&indexer_alloc, primary_key);
|
||||
let embedders = index.embedding_configs(index_wtxn)?;
|
||||
let embedders = self.embedders(embedders)?;
|
||||
let embedders = index
|
||||
.embedding_configs(index_wtxn)
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
|
||||
let embedders = self.embedders(index_uid.clone(), embedders)?;
|
||||
|
||||
pool.install(|| {
|
||||
indexer::index(
|
||||
@ -1660,14 +1687,15 @@ impl IndexScheduler {
|
||||
&send_progress,
|
||||
)
|
||||
})
|
||||
.unwrap()?;
|
||||
.unwrap()
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
|
||||
|
||||
// tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
|
||||
}
|
||||
|
||||
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);
|
||||
|
||||
@ -1681,10 +1709,12 @@ impl IndexScheduler {
|
||||
task.status = Status::Succeeded;
|
||||
}
|
||||
|
||||
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(|err| Error::from_milli(err, Some(index_uid.clone())))?;
|
||||
|
||||
Ok(tasks)
|
||||
}
|
||||
|
||||
@ -1,13 +1,12 @@
|
||||
use std::fmt::Display;
|
||||
|
||||
use crate::TaskId;
|
||||
use meilisearch_types::batches::BatchId;
|
||||
use meilisearch_types::error::{Code, ErrorCode};
|
||||
use meilisearch_types::tasks::{Kind, Status};
|
||||
use meilisearch_types::{heed, milli};
|
||||
use thiserror::Error;
|
||||
|
||||
use crate::TaskId;
|
||||
|
||||
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
|
||||
pub enum DateField {
|
||||
BeforeEnqueuedAt,
|
||||
@ -122,11 +121,11 @@ pub enum Error {
|
||||
Dump(#[from] dump::Error),
|
||||
#[error(transparent)]
|
||||
Heed(#[from] heed::Error),
|
||||
#[error("{}", match .index_name {
|
||||
Some(name) if !name.is_empty() => format!("Index `{}`: {error}", name),
|
||||
#[error("{}", match .index_uid {
|
||||
Some(uid) if !uid.is_empty() => format!("Index `{}`: {error}", uid),
|
||||
_ => format!("{error}")
|
||||
})]
|
||||
Milli { error: milli::Error, index_name: Option<String> },
|
||||
Milli { error: milli::Error, index_uid: Option<String> },
|
||||
#[error("An unexpected crash occurred when processing the task.")]
|
||||
ProcessBatchPanicked,
|
||||
#[error(transparent)]
|
||||
@ -213,8 +212,18 @@ impl Error {
|
||||
Self::WithCustomErrorCode(code, Box::new(self))
|
||||
}
|
||||
|
||||
pub fn from_milli(error: milli::Error, index_name: Option<String>) -> Self {
|
||||
Self::Milli { error, index_name }
|
||||
pub fn from_milli(err: milli::Error, index_uid: Option<String>) -> Self {
|
||||
match err {
|
||||
milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
|
||||
Self::Milli { error: err, index_uid }
|
||||
.with_custom_error_code(Code::InvalidDocumentFilter)
|
||||
}
|
||||
milli::Error::UserError(milli::UserError::InvalidFilterExpression { .. }) => {
|
||||
Self::Milli { error: err, index_uid }
|
||||
.with_custom_error_code(Code::InvalidDocumentFilter)
|
||||
}
|
||||
_ => Self::Milli { error: err, index_uid },
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@ -8,9 +8,8 @@ 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};
|
||||
|
||||
/// 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.
|
||||
|
||||
@ -3,19 +3,19 @@ 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};
|
||||
use time::OffsetDateTime;
|
||||
use tracing::error;
|
||||
use uuid::Uuid;
|
||||
use meilisearch_types::milli;
|
||||
use self::index_map::IndexMap;
|
||||
use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
|
||||
use crate::uuid_codec::UuidCodec;
|
||||
use crate::{Error, Result};
|
||||
|
||||
mod index_map;
|
||||
|
||||
@ -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,
|
||||
).map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
|
||||
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 +362,8 @@ 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;
|
||||
}
|
||||
@ -373,13 +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,
|
||||
).map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
|
||||
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(_) => {
|
||||
@ -460,7 +468,8 @@ impl IndexMapper {
|
||||
None => {
|
||||
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())))
|
||||
IndexStats::new(&index, &index_rtxn)
|
||||
.map_err(|e| Error::from_milli(e, Some(uuid.to_string())))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -1678,8 +1678,9 @@ 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{
|
||||
error: milli::Error::InternalError(milli::InternalError::AbortedIndexation), ..
|
||||
Err(Error::Milli {
|
||||
error: milli::Error::InternalError(milli::InternalError::AbortedIndexation),
|
||||
..
|
||||
})
|
||||
| Err(Error::AbortedTask) => {
|
||||
#[cfg(test)]
|
||||
@ -1700,7 +1701,8 @@ impl IndexScheduler {
|
||||
// 3. resize it
|
||||
// 4. re-schedule tasks
|
||||
Err(Error::Milli {
|
||||
error: milli::Error::UserError(milli::UserError::MaxDatabaseSizeReached), ..
|
||||
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();
|
||||
@ -1953,11 +1955,12 @@ impl IndexScheduler {
|
||||
config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
|
||||
..
|
||||
}| {
|
||||
let prompt =
|
||||
Arc::new(prompt.try_into()
|
||||
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())))?
|
||||
);
|
||||
.map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
|
||||
);
|
||||
// optimistically return existing embedder
|
||||
{
|
||||
let embedders = self.embedders.read().unwrap();
|
||||
@ -1973,8 +1976,9 @@ 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(|e| Error::from_milli(e, Some(index_uid.clone())))?,
|
||||
.map_err(|err| {
|
||||
Error::from_milli(err.into(), Some(index_uid.clone()))
|
||||
})?,
|
||||
);
|
||||
{
|
||||
let mut embedders = self.embedders.write().unwrap();
|
||||
@ -6150,7 +6154,7 @@ 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"), None).unwrap();
|
||||
|
||||
@ -10,8 +10,8 @@ snapshot_kind: text
|
||||
0 {uid: 0, batch_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, batch_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, batch_uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
|
||||
3 {uid: 3, batch_uid: 2, 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, batch_uid: 2, 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, batch_uid: 2, 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, batch_uid: 2, 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, batch_uid: 2, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
|
||||
----------------------------------------------------------------------
|
||||
### Status:
|
||||
|
||||
@ -4,10 +4,10 @@ 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;
|
||||
use meilisearch_types::milli;
|
||||
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum MeilisearchHttpError {
|
||||
@ -67,7 +67,7 @@ pub enum MeilisearchHttpError {
|
||||
Some(name) if !name.is_empty() => format!("Index `{}`: {error}", name),
|
||||
_ => format!("{error}")
|
||||
})]
|
||||
Milli { error: meilisearch_types::milli::Error, index_name: Option<String> },
|
||||
Milli { error: milli::Error, index_name: Option<String> },
|
||||
#[error(transparent)]
|
||||
Payload(#[from] PayloadError),
|
||||
#[error(transparent)]
|
||||
@ -105,7 +105,7 @@ impl ErrorCode for MeilisearchHttpError {
|
||||
MeilisearchHttpError::SerdeJson(_) => Code::Internal,
|
||||
MeilisearchHttpError::HeedError(_) => Code::Internal,
|
||||
MeilisearchHttpError::IndexScheduler(e) => e.error_code(),
|
||||
MeilisearchHttpError::Milli{error, ..} => error.error_code(),
|
||||
MeilisearchHttpError::Milli { error, .. } => error.error_code(),
|
||||
MeilisearchHttpError::Payload(e) => e.error_code(),
|
||||
MeilisearchHttpError::FileStore(_) => Code::Internal,
|
||||
MeilisearchHttpError::DocumentFormat(e) => e.error_code(),
|
||||
|
||||
@ -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_uid.to_string(), &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(
|
||||
|
||||
@ -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).map_err(|e| Error::from_milli(e, Some(uid.to_string())))?))
|
||||
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();
|
||||
|
||||
@ -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_uid.to_string(), &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_uid.to_string(), &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_uid.to_string(), &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_uid.to_string(), &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;
|
||||
|
||||
@ -103,8 +103,13 @@ async fn similar(
|
||||
|
||||
let index = index_scheduler.index(&index_uid)?;
|
||||
|
||||
let (embedder_name, embedder, quantized) =
|
||||
SearchKind::embedder(&index_scheduler, index_uid.to_string(), &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(
|
||||
|
||||
@ -127,14 +127,26 @@ pub async fn multi_search_with_post(
|
||||
|
||||
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 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_uid_str.clone(), &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)?;
|
||||
|
||||
@ -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_uid.to_string(), &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(index_uid.to_string(), 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,
|
||||
@ -670,8 +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)
|
||||
.map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
|
||||
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,
|
||||
|
||||
@ -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)
|
||||
@ -890,6 +895,7 @@ fn prepare_search<'t>(
|
||||
}
|
||||
|
||||
pub fn perform_search(
|
||||
index_uid: String,
|
||||
index: &Index,
|
||||
query: SearchQuery,
|
||||
search_kind: SearchKind,
|
||||
@ -916,7 +922,7 @@ 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,
|
||||
@ -1069,17 +1075,27 @@ 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))
|
||||
}
|
||||
@ -1181,7 +1197,7 @@ 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);
|
||||
@ -1276,11 +1292,7 @@ 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()?;
|
||||
|
||||
@ -1323,7 +1335,10 @@ 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());
|
||||
}
|
||||
@ -1369,7 +1384,7 @@ 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)?;
|
||||
@ -1690,12 +1705,12 @@ 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);
|
||||
@ -1720,7 +1735,7 @@ 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();
|
||||
|
||||
@ -1898,7 +1913,7 @@ 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)]
|
||||
|
||||
@ -1462,7 +1462,7 @@ 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"
|
||||
@ -2279,7 +2279,7 @@ 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"
|
||||
|
||||
@ -604,7 +604,7 @@ 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"
|
||||
@ -636,7 +636,7 @@ 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"
|
||||
|
||||
@ -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"
|
||||
|
||||
@ -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"
|
||||
|
||||
@ -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"
|
||||
|
||||
@ -448,7 +448,7 @@ 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"
|
||||
|
||||
@ -318,7 +318,7 @@ 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"
|
||||
|
||||
@ -250,7 +250,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
|
||||
"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"
|
||||
@ -280,7 +280,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
|
||||
"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"
|
||||
@ -311,7 +311,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Could not parse `._vectors.manual.regenerate`: invalid type: string \"yes please\", expected a boolean at line 1 column 26",
|
||||
"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"
|
||||
@ -340,7 +340,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.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"
|
||||
@ -369,7 +369,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.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"
|
||||
@ -398,7 +398,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.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"
|
||||
@ -440,7 +440,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.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"
|
||||
@ -469,7 +469,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.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"
|
||||
@ -498,7 +498,7 @@ async fn user_provided_embeddings_error() {
|
||||
"indexedDocuments": 0
|
||||
},
|
||||
"error": {
|
||||
"message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.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"
|
||||
@ -539,7 +539,7 @@ 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"
|
||||
@ -569,7 +569,7 @@ 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"
|
||||
@ -599,7 +599,7 @@ 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"
|
||||
|
||||
@ -713,7 +713,7 @@ 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"
|
||||
@ -757,7 +757,7 @@ 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"
|
||||
|
||||
@ -985,7 +985,7 @@ 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"
|
||||
@ -1025,7 +1025,7 @@ 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"
|
||||
@ -1178,7 +1178,7 @@ 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"
|
||||
@ -1247,7 +1247,7 @@ 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"
|
||||
@ -1306,7 +1306,7 @@ 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"
|
||||
@ -1362,7 +1362,7 @@ 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"
|
||||
@ -1414,7 +1414,7 @@ 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"
|
||||
@ -1478,7 +1478,7 @@ 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"
|
||||
@ -1542,7 +1542,7 @@ 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"
|
||||
@ -1908,7 +1908,7 @@ 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"
|
||||
@ -1951,7 +1951,7 @@ 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"
|
||||
@ -2099,7 +2099,7 @@ 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"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user